TCV20
* *Fair, Data-Efficient and Trusted Computer Vision
* Analytical Framework for Trusted Machine Learning and Computer Vision Running with Blockchain, An
* Attribute Aware Filter-Drop for Bias-Invariant Classification
* Bias in Multimodal AI: Testbed for Fair Automatic Recruitment
* DNDNet: Reconfiguring CNN for Adversarial Robustness
* Enhancing Facial Data Diversity with Style-based Face Aging
* Explaining Failure: Investigation of Surprise and Expectation in CNNs
* Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation
* Face Recognition: Too Bias, or Not Too Bias?
* Identity Preserve Transform: Understand What Activity Classification Models Have Learnt
* Imparting Fairness to Pre-Trained Biased Representations
* Interpreting Interpretations: Organizing Attribution Methods by Criteria
* Minimizing Supervision in Multi-label Categorization
* On Privacy Preserving Anonymization of Finger-selfies
* Plug-And-Pipeline: Efficient Regularization for Single-Step Adversarial Training
* Privacy Enhanced Decision Tree Inference
* Revisiting the Evaluation of Uncertainty Estimation and Its Application to Explore Model Complexity-Uncertainty Trade-Off
* SAM: The Sensitivity of Attribution Methods to Hyperparameters
* Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
19 for TCV20
TCV21
* *Fair, Data-Efficient and Trusted Computer Vision
* Adversarial Approach for Explaining the Predictions of Deep Neural Networks, An
* Estimating (and fixing) the Effect of Face Obfuscation in Video Recognition
* Explainable Deep Classification Models for Domain Generalization
* InfoScrub: Towards Attribute Privacy by Targeted Obfuscation
* Mathematical Analysis of Learning Loss for Active Learning in Regression, A
* MLCapsule: Guarded Offline Deployment of Machine Learning as a Service
* Renofeation: A Simple Transfer Learning Method for Improved Adversarial Robustness
* Sample-free white-box out-of-distribution detection for deep learning
* Theoretical-Empirical Approach to Estimating Sample Complexity of DNNs, A
* Towards Fair Federated Learning with Zero-Shot Data Augmentation
* Watermarking-Based Framework for Protecting Deep Image Classifiers Against Adversarial Attacks, A
* X-MAN: Explaining multiple sources of anomalies in video
13 for TCV21