EDLCV20
* *Efficient Deep Learning for Computer Vision
* AdaMT-Net: An Adaptive Weight Learning Based Multi-Task Learning Model For Scene Understanding
* Adaptive Posit: Parameter aware numerical format for deep learning inference on the edge
* Any-Width Networks
* Attentive Semantic Preservation Network for Zero-Shot Learning
* BAMSProd: A Step towards Generalizing the Adaptive Optimization Methods to Deep Binary Model
* Computer-aided diagnosis system of lung carcinoma using Convolutional Neural Networks
* Constraint-Aware Importance Estimation for Global Filter Pruning under Multiple Resource Constraints
* Data-Free Network Quantization With Adversarial Knowledge Distillation
* Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training
* Dynamic Inference: A New Approach Toward Efficient Video Action Recognition
* Fast Hardware-Aware Neural Architecture Search
* FoNet: A Memory-efficient Fourier-based Orthogonal Network for Object Recognition
* Intelligent Scene Caching to Improve Accuracy for Energy-Constrained Embedded Vision
* Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification
* Learning Sparse Neural Networks Through Mixture-Distributed Regularization
* Learning Sparse Ternary Neural Networks with Entropy-Constrained Trained Ternarization (EC2T)
* Least squares binary quantization of neural networks
* Low-bit Quantization Needs Good Distribution
* LSQ+: Improving low-bit quantization through learnable offsets and better initialization
* Mimic The Raw Domain: Accelerating Action Recognition in the Compressed Domain
* Monte Carlo Gradient Quantization
* Neural Network Compression Using Higher-Order Statistics and Auxiliary Reconstruction Losses
* Now that I can see, I can improve: Enabling data-driven finetuning of CNNs on the edge
* Randaugment: Practical automated data augmentation with a reduced search space
* RefineDetLite: A Lightweight One-stage Object Detection Framework for CPU-only Devices
* Structured Weight Unification and Encoding for Neural Network Compression and Acceleration
* Ternary MobileNets via Per-Layer Hybrid Filter Banks
28 for EDLCV20