FaDE-TCV22
* *Fair, Data-Efficient and Trusted Computer Vision
* Class-wise Thresholding for Robust Out-of-Distribution Detection
* Color Invariant Skin Segmentation
* DeSI: Deepfake Source Identifier for Social Media
* Doppelgänger Saliency: Towards More Ethical Person Re-Identification
* Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigation
* Examination of Bias of Facial Analysis based BMI Prediction Models, An
* Is Neuron Coverage Needed to Make Person Detection More Robust?
* medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space
* OPAD: An Optimized Policy-based Active Learning Framework for Document Content Analysis
* Pyramidal Attention for Saliency Detection
* Segmenting across places: The need for fair transfer learning with satellite imagery
* Visual Domain Bridge: A source-free domain adaptation for cross-domain few-shot learning
13 for FaDE-TCV22
FaDE-TCV23
* *Fair, Data-Efficient and Trusted Computer Vision
* Casual Conversations v2 Dataset: A diverse, large benchmark for measuring fairness and robustness in audio/vision/speech models, The
* Estimating and Maximizing Mutual Information for Knowledge Distillation
* Gradient Attention Balance Network: Mitigating Face Recognition Racial Bias via Gradient Attention
* Learning unbiased classifiers from biased data with meta-learning
* MMRNet: Improving Reliability for Multimodal Object Detection and Segmentation for Bin Picking via Multimodal Redundancy
* Robustness Against Gradient based Attacks through Cost Effective Network Fine-Tuning
* Schrödinger's Camera: First Steps Towards a Quantum-Based Privacy Preserving Camera
* Synthetic Sample Selection for Generalized Zero-Shot Learning
9 for FaDE-TCV23