@inproceedings{bb153900,
AUTHOR = "Wu, Z.G.Y. and Chen, J.X. and Zhong, H. and Huang, D. and Wang, Y.H.",
TITLE = "Adalog: Post-training Quantization for Vision Transformers with
Adaptive Logarithm Quantizer",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXVII: 411-427",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149823"}
@inproceedings{bb153901,
AUTHOR = "Jie, S. and Tang, Y.H. and Guo, J.Y. and Deng, Z.H. and Han, K. and Wang, Y.H.",
TITLE = "Token Compensator: Altering Inference Cost of Vision Transformer
Without Re-tuning",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XVI: 76-94",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149824"}
@inproceedings{bb153902,
AUTHOR = "Xiao, H. and Zheng, W.Z. and Zuo, S.C. and Gao, P. and Zhou, J. and Lu, J.W.",
TITLE = "Spatialformer: Towards Generalizable Vision Transformers with Explicit
Spatial Understanding",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XIII: 37-54",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149825"}
@inproceedings{bb153903,
AUTHOR = "Heo, B. and Park, S. and Han, D.Y. and Yun, S.",
TITLE = "Rotary Position Embedding for Vision Transformer",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "X: 289-305",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149826"}
@inproceedings{bb153904,
AUTHOR = "Bellitto, G. and Sortino, R. and Spadaro, P. and Palazzo, S. and Salanitri, F.P. and Fiameni, G. and Gavves, E. and Spampinato, C.",
TITLE = "Vito: Vision Transformer Optimization Via Knowledge Distillation On
Decoders",
BOOKTITLE = ICIP24,
YEAR = "2024",
PAGES = "493-499",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149827"}
@inproceedings{bb153905,
AUTHOR = "Gani, H. and Saadi, N. and Hussein, N. and Nandakumar, K.",
TITLE = "Multi-Attribute Vision Transformers are Efficient and Robust Learners",
BOOKTITLE = ICIP24,
YEAR = "2024",
PAGES = "766-772",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149828"}
@inproceedings{bb153906,
AUTHOR = "Huang, W.X. and Shen, Y.H. and Xie, J. and Zhang, B.C. and He, G.Q. and Li, K. and Sun, X. and Lin, S.H.",
TITLE = "A General and Efficient Training for Transformer via Token Expansion",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "15783-15792",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149829"}
@inproceedings{bb153907,
AUTHOR = "Cho, J.H. and Krahenbuhl, P.",
TITLE = "Language-Conditioned Detection Transformer",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "16593-16603",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149830"}
@inproceedings{bb153908,
AUTHOR = "Lin, S. and Lyu, P. and Liu, D. and Tang, T. and Liang, X.D. and Song, A. and Chang, X.J.",
TITLE = "MLP Can Be a Good Transformer Learner",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "19489-19498",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149831"}
@inproceedings{bb153909,
AUTHOR = "Wang, A. and Chen, H. and Lin, Z.J. and Han, J.G. and Ding, G.G.",
TITLE = "Rep ViT: Revisiting Mobile CNN From ViT Perspective",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "15909-15920",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149832"}
@inproceedings{bb153910,
AUTHOR = "Weng, H.H. and Huang, D. and Qiao, Y. and Hu, Z. and Lin, C.Y. and Zhang, T. and Chen, C.L.P.",
TITLE = "Desigen: A Pipeline for Controllable Design Template Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "12721-12732",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149833"}
@inproceedings{bb153911,
AUTHOR = "Park, S. and Byun, H.R.",
TITLE = "Fair-VPT: Fair Visual Prompt Tuning for Image Classification",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "12268-12278",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149834"}
@inproceedings{bb153912,
AUTHOR = "Xu, H.Y. and Xiang, L. and Ye, H.Y. and Yao, D. and Chu, P.Z. and Li, B.C.",
TITLE = "Permutation Equivariance of Transformers and its Applications",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "5987-5996",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149835"}
@inproceedings{bb153913,
AUTHOR = "Zhang, Y.Y. and Ding, X.H. and Gong, K.X. and Ge, Y.X. and Shan, Y. and Yue, X.Y.",
TITLE = "Multimodal Pathway: Improve Transformers with Irrelevant Data from
Other Modalities",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6108-6117",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149836"}
@inproceedings{bb153914,
AUTHOR = "Kobayashi, T.",
TITLE = "Mean-Shift Feature Transformer",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6047-6056",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149837"}
@inproceedings{bb153915,
AUTHOR = "Wu, J. and Duan, B. and Kang, W.T. and Tang, H. and Yan, Y.",
TITLE = "Token Transformation Matters: Towards Faithful Post-Hoc Explanation
for Vision Transformer",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "10926-10935",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149838"}
@inproceedings{bb153916,
AUTHOR = "Shi, X.Y. and Hao, Z.C. and Yu, Z.F.",
TITLE = "SpikingResformer: Bridging ResNet and Vision Transformer in Spiking
Neural Networks",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "5610-5619",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149839"}
@inproceedings{bb153917,
AUTHOR = "Ye, H.C. and Yu, C. and Ye, P. and Xia, R. and Tang, Y.S. and Lu, J.W. and Chen, T. and Zhang, B.",
TITLE = "Once for Both: Single Stage of Importance and Sparsity Search for
Vision Transformer Compression",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "5578-5588",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149840"}
@inproceedings{bb153918,
AUTHOR = "Zhang, J. and Herrmann, C. and Hur, J. and Chen, E. and Jampani, V. and Sun, D.Q. and Yang, M.H.",
TITLE = "Telling Left from Right: Identifying Geometry-Aware Semantic
Correspondence",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "3076-3085",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149841"}
@inproceedings{bb153919,
AUTHOR = "Huang, N.C. and Chang, C.C. and Lin, W.C. and Taka, E. and Marculescu, D. and Wu, K.C.A.",
TITLE = "ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer
Acceleration",
BOOKTITLE = ECV24,
YEAR = "2024",
PAGES = "8006-8015",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149842"}
@inproceedings{bb153920,
AUTHOR = "Devulapally, A. and Khan, M.F.F. and Advani, S. and Narayanan, V.",
TITLE = "Multi-Modal Fusion of Event and RGB for Monocular Depth Estimation
Using a Unified Transformer-based Architecture",
BOOKTITLE = MULA24,
YEAR = "2024",
PAGES = "2081-2089",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149843"}
@inproceedings{bb153921,
AUTHOR = "Yang, Z.D. and Li, Z. and Zeng, A.L. and Li, Z.X. and Yuan, C. and Li, Y.",
TITLE = "ViTKD: Feature-based Knowledge Distillation for Vision Transformers",
BOOKTITLE = PBDL24,
YEAR = "2024",
PAGES = "1379-1388",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149844"}
@inproceedings{bb153922,
AUTHOR = "Mehri, F. and Baghshah, M.S. and Pilehvar, M.T.",
TITLE = "LibraGrad: Balancing Gradient Flow for Universally Better Vision
Transformer Attributions",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "67-78",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149845"}
@inproceedings{bb153923,
AUTHOR = "Mehri, F. and Fayyaz, M. and Baghshah, M.S. and Pilehvar, M.T.",
TITLE = "SkipPLUS: Skip the First Few Layers to Better Explain Vision
Transformers",
BOOKTITLE = FaDE-TCV24,
YEAR = "2024",
PAGES = "204-215",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149846"}
@inproceedings{bb153924,
AUTHOR = "Jain, S. and Dutta, T.",
TITLE = "Towards Understanding and Improving Adversarial Robustness of Vision
Transformers",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "24736-24745",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149847"}
@inproceedings{bb153925,
AUTHOR = "Yang, S. and Bai, J. and Gao, K. and Yang, Y. and Li, Y.M. and Xia, S.T.",
TITLE = "Not All Prompts Are Secure: A Switchable Backdoor Attack Against
Pre-trained Vision Transfomers",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "24431-24441",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149848"}
@inproceedings{bb153926,
AUTHOR = "Steitz, J.M.O. and Roth, S.",
TITLE = "Adapters Strike Back",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "23449-23459",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149849"}
@inproceedings{bb153927,
AUTHOR = "Rangwani, H. and Mondal, P. and Mondal, P. and Mishra, M. and Asokan, A.R. and Babu, R.V.",
TITLE = "DeiT-LT: Distillation Strikes Back for Vision Transformer Training on
Long-Tailed Datasets",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "23396-23406",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149850"}
@inproceedings{bb153928,
AUTHOR = "Liu, J.Y. and Teshome, W. and Ghimire, S. and Sznaier, M. and Camps, O.",
TITLE = "Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers*",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "23009-23018",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149851"}
@inproceedings{bb153929,
AUTHOR = "Kim, M. and Seo, P.H. and Schmid, C. and Cho, M.",
TITLE = "Learning Correlation Structures for Vision Transformers",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18941-18951",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149852"}
@inproceedings{bb153930,
AUTHOR = "Shi, D.",
TITLE = "TransNeXt: Robust Foveal Visual Perception for Vision Transformers",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "17773-17783",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149853"}
@inproceedings{bb153931,
AUTHOR = "Agiza, A. and Neseem, M. and Reda, S.",
TITLE = "MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task
Learning",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "16196-16205",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149854"}
@inproceedings{bb153932,
AUTHOR = "Dong, W. and Zhang, X. and Chen, B. and Yan, D.W. and Lin, Z.J. and Yan, Q. and Wang, P. and Yang, Y.",
TITLE = "Low-Rank Rescaled Vision Transformer Fine-Tuning:
A Residual Design Approach",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "16101-16110",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149855"}
@inproceedings{bb153933,
AUTHOR = "Wu, J. and Kang, W.T. and Tang, H. and Hong, Y. and Yan, Y.",
TITLE = "On the Faithfulness of Vision Transformer Explanations",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "10936-10945",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149856"}
@inproceedings{bb153934,
AUTHOR = "Navaneet, K.L. and Koohpayegani, S.A. and Sleiman, E. and Pirsiavash, H.",
TITLE = "SlowFormer: Adversarial Attack on Compute and Energy Consumption of
Efficient Vision Transformers",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "24786-24797",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149857"}
@inproceedings{bb153935,
AUTHOR = "Koyun, O.C. and Toreyin, B.U.",
TITLE = "HaLViT: Half of the Weights are Enough",
BOOKTITLE = LargeVM24,
YEAR = "2024",
PAGES = "3669-3678",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149858"}
@inproceedings{bb153936,
AUTHOR = "Bafghi, R.A. and Harilal, N. and Monteleoni, C. and Raissi, M.",
TITLE = "Parameter Efficient Fine-tuning of Self-supervised ViTs without
Catastrophic Forgetting",
BOOKTITLE = LargeVM24,
YEAR = "2024",
PAGES = "3679-3684",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149859"}
@inproceedings{bb153937,
AUTHOR = "Raissi, M. and Monteleoni, C. and Harilal, N. and Bafghi, R.A.",
TITLE = "Parameter Efficient Fine-tuning of Self-supervised ViTs without
Catastrophic Forgetting",
BOOKTITLE = LargeVM24,
YEAR = "2024",
PAGES = "7864-7869",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149859"}
@inproceedings{bb153938,
AUTHOR = "Yuan, X. and Fei, H.L. and Baek, J.",
TITLE = "Efficient Transformer Adaptation with Soft Token Merging",
BOOKTITLE = LargeVM24,
YEAR = "2024",
PAGES = "3658-3668",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149860"}
@inproceedings{bb153939,
AUTHOR = "Edalati, A. and Hameed, M.G.A. and Mosleh, A.",
TITLE = "Generalized Kronecker-based Adapters for Parameter-efficient
Fine-tuning of Vision Transformers",
BOOKTITLE = CRV23,
YEAR = "2023",
PAGES = "97-104",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149861"}
@inproceedings{bb153940,
AUTHOR = "Marouf, I.E. and Tartaglione, E. and Lathuiliere, S.",
TITLE = "Mini but Mighty: Finetuning ViTs with Mini Adapters",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "1721-1730",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149862"}
@inproceedings{bb153941,
AUTHOR = "Kim, G. and Kim, J. and Lee, J.S.",
TITLE = "Exploring Adversarial Robustness of Vision Transformers in the
Spectral Perspective",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "3964-3973",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149863"}
@inproceedings{bb153942,
AUTHOR = "Xu, X. and Wang, S. and Chen, Y.D. and Zheng, Y.P. and Wei, Z.W. and Liu, J.J.",
TITLE = "GTP-ViT: Efficient Vision Transformers via Graph-based Token
Propagation",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "86-95",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149864"}
@inproceedings{bb153943,
AUTHOR = "Han, Q. and Zhang, G.J. and Huang, J.X. and Gao, P. and Wei, Z. and Lu, S.J.",
TITLE = "Efficient MAE towards Large-Scale Vision Transformers",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "595-604",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149865"}
@inproceedings{bb153944,
AUTHOR = "Park, J.W. and Kahatapitiya, K. and Kim, D.H. and Sudalairaj, S. and Fan, Q.F. and Ryoo, M.S.",
TITLE = "Grafting Vision Transformers",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "1134-1143",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149866"}
@inproceedings{bb153945,
AUTHOR = "Shimizu, S. and Tamaki, T.",
TITLE = "Joint learning of images and videos with a single Vision Transformer",
BOOKTITLE = MVA23,
YEAR = "2023",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149867"}
@inproceedings{bb153946,
AUTHOR = "Ding, S.R. and Zhao, P.S. and Zhang, X.P. and Qian, R. and Xiong, H.K. and Tian, Q.",
TITLE = "Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "16899-16910",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149868"}
@inproceedings{bb153947,
AUTHOR = "Chen, M.Z. and Lin, M. and Lin, Z.H. and Zhang, Y.X. and Chao, F. and Ji, R.R.",
TITLE = "SMMix: Self-Motivated Image Mixing for Vision Transformers",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "17214-17224",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149869"}
@inproceedings{bb153948,
AUTHOR = "Kim, D. and Angelova, A. and Kuo, W.C.",
TITLE = "Contrastive Feature Masking Open-Vocabulary Vision Transformer",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15556-15566",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149870"}
@inproceedings{bb153949,
AUTHOR = "Li, Z.K. and Gu, Q.Y.",
TITLE = "I-ViT: Integer-only Quantization for Efficient Vision Transformer
Inference",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "17019-17029",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149871"}
@inproceedings{bb153950,
AUTHOR = "Frumkin, N. and Gope, D. and Marculescu, D.",
TITLE = "Jumping through Local Minima: Quantization in the Loss Landscape of
Vision Transformers",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "16932-16942",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149872"}
@inproceedings{bb153951,
AUTHOR = "Li, Z.K. and Xiao, J.R. and Yang, L.W. and Gu, Q.Y.",
TITLE = "RepQ-ViT: Scale Reparameterization for Post-Training Quantization of
Vision Transformers",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "17181-17190",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149873"}
@inproceedings{bb153952,
AUTHOR = "Havtorn, J.D. and Royer, A. and Blankevoort, T. and Bejnordi, B.E.",
TITLE = "MSViT: Dynamic Mixed-scale Tokenization for Vision Transformers",
BOOKTITLE = NIVT23,
YEAR = "2023",
PAGES = "838-848",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149874"}
@inproceedings{bb153953,
AUTHOR = "Haurum, J.B. and Escalera, S. and Taylor, G.W. and Moeslund, T.B.",
TITLE = "Which Tokens to Use? Investigating Token Reduction in Vision
Transformers",
BOOKTITLE = NIVT23,
YEAR = "2023",
PAGES = "773-783",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149875"}
@inproceedings{bb153954,
AUTHOR = "Wang, X. and Chu, X.J. and Han, C. and Zhang, X.Y.",
TITLE = "SCSC: Spatial Cross-scale Convolution Module to Strengthen both CNNs
and Transformers",
BOOKTITLE = NIVT23,
YEAR = "2023",
PAGES = "731-741",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149876"}
@inproceedings{bb153955,
AUTHOR = "Chen, Y.H. and Weng, Y.C. and Kao, C.H. and Chien, C. and Chiu, W.C. and Peng, W.H.",
TITLE = "TransTIC: Transferring Transformer-based Image Compression from Human
Perception to Machine Perception",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "23240-23250",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149877"}
@inproceedings{bb153956,
AUTHOR = "Li, Y. and Hu, J. and Wen, Y. and Evangelidis, G. and Salahi, K. and Wang, Y.Z. and Tulyakov, S. and Ren, J.",
TITLE = "Rethinking Vision Transformers for MobileNet Size and Speed",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "16843-16854",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149878"}
@inproceedings{bb153957,
AUTHOR = "Nurgazin, M. and Tu, N.A.",
TITLE = "A Comparative Study of Vision Transformer Encoders and Few-shot
Learning for Medical Image Classification",
BOOKTITLE = CVAMD23,
YEAR = "2023",
PAGES = "2505-2513",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149879"}
@inproceedings{bb153958,
AUTHOR = "Xie, W. and Zhao, Z. and Li, S.Y. and Zuo, B.H. and Wang, Y.G.",
TITLE = "Nonrigid Object Contact Estimation With Regional Unwrapping
Transformer",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "9308-9317",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149880"}
@inproceedings{bb153959,
AUTHOR = "Vasu, P.K.A. and Gabriel, J. and Zhu, J. and Tuzel, O. and Ranjan, A.",
TITLE = "FastViT: A Fast Hybrid Vision Transformer using Structural
Reparameterization",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5762-5772",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149881"}
@inproceedings{bb153960,
AUTHOR = "Tang, C. and Zhang, L.L. and Jiang, H.Q. and Xu, J.H. and Cao, T. and Zhang, Q. and Yang, Y.Q. and Wang, Z. and Yang, M.",
TITLE = "ElasticViT: Conflict-aware Supernet Training for Deploying Fast
Vision Transformer on Diverse Mobile Devices",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5806-5817",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149882"}
@inproceedings{bb153961,
AUTHOR = "Ren, S. and Yang, X.Y. and Liu, S. and Wang, X.C.",
TITLE = "SG-Former: Self-guided Transformer with Evolving Token Reallocation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5980-5991",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149883"}
@inproceedings{bb153962,
AUTHOR = "Lin, W.F. and Wu, Z.H. and Chen, J. and Huang, J. and Jin, L.W.",
TITLE = "Scale-Aware Modulation Meet Transformer",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5992-6003",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149884"}
@inproceedings{bb153963,
AUTHOR = "He, Y.F. and Lou, Z.Y. and Zhang, L. and Liu, J. and Wu, W.J. and Zhou, H. and Zhuang, B.",
TITLE = "BiViT: Extremely Compressed Binary Vision Transformers",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5628-5640",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149885"}
@inproceedings{bb153964,
AUTHOR = "Dutson, M. and Li, Y. and Gupta, M.",
TITLE = "Eventful Transformers:
Leveraging Temporal Redundancy in Vision Transformers",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "16865-16877",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149886"}
@inproceedings{bb153965,
AUTHOR = "Wang, Z.Q. and Fang, Y.T. and Cao, J.H. and Zhang, Q. and Wang, Z. and Xu, R.",
TITLE = "Masked Spiking Transformer",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "1761-1771",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149887"}
@inproceedings{bb153966,
AUTHOR = "Peebles, W. and Xie, S.",
TITLE = "Scalable Diffusion Models with Transformers",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "4172-4182",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149888"}
@inproceedings{bb153967,
AUTHOR = "Mentzer, F. and Agustson, E. and Tschannen, M.",
TITLE = "M2T: Masking Transformers Twice for Faster Decoding",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5317-5326",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149889"}
@inproceedings{bb153968,
AUTHOR = "Xiao, H. and Zheng, W.Z. and Zhu, Z. and Zhou, J. and Lu, J.W.",
TITLE = "Token-Label Alignment for Vision Transformers",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5472-5481",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149890"}
@inproceedings{bb153969,
AUTHOR = "Yu, R.Y. and Wang, Z.N. and Wang, Y.H. and Li, K. and Liu, C. and Duan, H.Y. and Ji, X.Y. and Chen, J.",
TITLE = "LaPE: Layer-adaptive Position Embedding for Vision Transformers with
Independent Layer Normalization",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5863-5873",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149891"}
@inproceedings{bb153970,
AUTHOR = "Roy, A. and Verma, V.K. and Voonna, S. and Ghosh, K. and Ghosh, S. and Das, A.",
TITLE = "Exemplar-Free Continual Transformer with Convolutions",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5874-5884",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149892"}
@inproceedings{bb153971,
AUTHOR = "Xu, Y.X. and Li, C. and Li, D. and Sheng, X. and Jiang, F. and Tian, L. and Sirasao, A.",
TITLE = "FDViT: Improve the Hierarchical Architecture of Vision Transformer",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5927-5937",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149893"}
@inproceedings{bb153972,
AUTHOR = "Chen, Y.J. and Liu, H.M. and Yin, H.R. and Fan, B.",
TITLE = "Building Vision Transformers with Hierarchy Aware Feature Aggregation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5885-5895",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149894"}
@inproceedings{bb153973,
AUTHOR = "Quetu, V. and Milovanovic, M. and Tartaglione, E.",
TITLE = "Sparse Double Descent in Vision Transformers: Real or Phantom Threat?",
BOOKTITLE = CIAP23,
YEAR = "2023",
PAGES = "II:490-502",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149895"}
@inproceedings{bb153974,
AUTHOR = "Ak, K.E. and Lee, G.G. and Xu, Y. and Shen, M.W.",
TITLE = "Leveraging Efficient Training and Feature Fusion in Transformers for
Multimodal Classification",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "1420-1424",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149896"}
@inproceedings{bb153975,
AUTHOR = "Popovic, N. and Paudel, D.P. and Probst, T. and Van Gool, L.J.",
TITLE = "Token-Consistent Dropout For Calibrated Vision Transformers",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "1030-1034",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149897"}
@inproceedings{bb153976,
AUTHOR = "Sajjadi, M.S.M. and Mahendran, A. and Kipf, T. and Pot, E. and Duckworth, D. and Lucic, M. and Greff, K.",
TITLE = "RUST: Latent Neural Scene Representations from Unposed Imagery",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "17297-17306",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149898"}
@inproceedings{bb153977,
AUTHOR = "Bowman, B. and Achille, A. and Zancato, L. and Trager, M. and Perera, P. and Paolini, G. and Soatto, S.",
TITLE = "À-la-carte Prompt Tuning (APT):
Combining Distinct Data Via Composable Prompting",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "14984-14993",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149899"}
@inproceedings{bb153978,
AUTHOR = "Nakhli, R. and Moghadam, P.A. and Mi, H.Y. and Farahani, H. and Baras, A. and Gilks, B. and Bashashati, A.",
TITLE = "Sparse Multi-Modal Graph Transformer with Shared-Context Processing
for Representation Learning of Giga-pixel Images",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "11547-11557",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149900"}
@inproceedings{bb153979,
AUTHOR = "Gartner, E. and Metz, L. and Andriluka, M. and Freeman, C.D. and Sminchisescu, C.",
TITLE = "Transformer-Based Learned Optimization",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "11970-11979",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149901"}
@inproceedings{bb153980,
AUTHOR = "Li, J.C. and Hassani, A. and Walton, S. and Shi, H.",
TITLE = "ConvMLP: Hierarchical Convolutional MLPs for Vision",
BOOKTITLE = WFM23,
YEAR = "2023",
PAGES = "6307-6316",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149902"}
@inproceedings{bb153981,
AUTHOR = "Walmer, M. and Suri, S. and Gupta, K. and Shrivastava, A.",
TITLE = "Teaching Matters:
Investigating the Role of Supervision in Vision Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "7486-7496",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149903"}
@inproceedings{bb153982,
AUTHOR = "Wang, S.G. and Xie, T. and Cheng, J. and Zhang, X.C. and Liu, H.J.",
TITLE = "MDL-NAS: A Joint Multi-domain Learning Framework for Vision
Transformer",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "20094-20104",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149904"}
@inproceedings{bb153983,
AUTHOR = "Ren, S. and Wei, F.Y. and Zhang, Z. and Hu, H.",
TITLE = "TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "3687-3697",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149905"}
@inproceedings{bb153984,
AUTHOR = "He, J.F. and Gao, Y. and Zhang, T.Z. and Zhang, Z. and Wu, F.",
TITLE = "D2Former: Jointly Learning Hierarchical Detectors and Contextual
Descriptors via Agent-Based Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2904-2914",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149906"}
@inproceedings{bb153985,
AUTHOR = "Chen, X.Y. and Liu, Z.J. and Tang, H.T. and Yi, L. and Zhao, H. and Han, S.",
TITLE = "SparseViT: Revisiting Activation Sparsity for Efficient
High-Resolution Vision Transformer",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2061-2070",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149907"}
@inproceedings{bb153986,
AUTHOR = "Wei, S.Y. and Ye, T.Z. and Zhang, S. and Tang, Y. and Liang, J.J.",
TITLE = "Joint Token Pruning and Squeezing Towards More Aggressive Compression
of Vision Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2092-2101",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149908"}
@inproceedings{bb153987,
AUTHOR = "Lin, Y.B. and Bertasius, G.",
TITLE = "Siamese Vision Transformers are Scalable Audio-Visual Learners",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XIV: 303-321",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149909"}
@inproceedings{bb153988,
AUTHOR = "Lin, Y.B. and Sung, Y.L. and Lei, J. and Bansal, M. and Bertasius, G.",
TITLE = "Vision Transformers are Parameter-Efficient Audio-Visual Learners",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2299-2309",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149910"}
@inproceedings{bb153989,
AUTHOR = "Das, R. and Dukler, Y. and Ravichandran, A. and Swaminathan, A.",
TITLE = "Learning Expressive Prompting With Residuals for Vision Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "3366-3377",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149911"}
@inproceedings{bb153990,
AUTHOR = "Zheng, M.X. and Lou, Q. and Jiang, L.",
TITLE = "TrojViT: Trojan Insertion in Vision Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "4025-4034",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149912"}
@inproceedings{bb153991,
AUTHOR = "Li, Y.X. and Xu, C.",
TITLE = "Trade-off between Robustness and Accuracy of Vision Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "7558-7568",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149913"}
@inproceedings{bb153992,
AUTHOR = "Tarasiou, M. and Chavez, E. and Zafeiriou, S.",
TITLE = "ViTs for SITS: Vision Transformers for Satellite Image Time Series",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10418-10428",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149914"}
@inproceedings{bb153993,
AUTHOR = "Yu, Z.Z. and Wu, S. and Fu, Y.G. and Zhang, S. and Lin, Y.Y.C.",
TITLE = "Hint-Aug: Drawing Hints from Foundation Vision Transformers towards
Boosted Few-shot Parameter-Efficient Tuning",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "11102-11112",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149915"}
@inproceedings{bb153994,
AUTHOR = "Hou, J. and Dai, X.L. and He, Z.J. and Dai, A. and Nießner, M.",
TITLE = "Mask3D: Pretraining 2D Vision Transformers by Learning Masked 3D
Priors",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "13510-13519",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149916"}
@inproceedings{bb153995,
AUTHOR = "Xu, Z.Z. and Liu, R.K. and Yang, S. and Chai, Z.H. and Yuan, C.",
TITLE = "Learning Imbalanced Data with Vision Transformers",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "15793-15803",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149917"}
@inproceedings{bb153996,
AUTHOR = "Zhang, J.P. and Huang, Y.Z. and Wu, W.B. and Lyu, M.R.",
TITLE = "Transferable Adversarial Attacks on Vision Transformers with Token
Gradient Regularization",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "16415-16424",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149918"}
@inproceedings{bb153997,
AUTHOR = "Yang, H. and Yin, H.X. and Shen, M. and Molchanov, P. and Li, H. and Kautz, J.",
TITLE = "Global Vision Transformer Pruning with Hessian-Aware Saliency",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18547-18557",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149919"}
@inproceedings{bb153998,
AUTHOR = "Nakamura, R. and Kataoka, H. and Takashima, S. and Noriega, E.J.M. and Yokota, R. and Inoue, N.",
TITLE = "Pre-training Vision Transformers with Very Limited Synthesized Images",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "20303-20312",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149920"}
@inproceedings{bb153999,
AUTHOR = "Takashima, S. and Hayamizu, R. and Inoue, N. and Kataoka, H. and Yokota, R.",
TITLE = "Visual Atoms: Pre-Training Vision Transformers with Sinusoidal Waves",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18579-18588",
BIBSOURCE = "http://www.visionbib.com/bibliography/pattern651vit2.html#TT149921"}
Last update:Oct 6, 2025 at 14:07:43