Search Results for author:
Found 6 papers, 1 papers with code
De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts
Data-Free Knowledge Distillation (DFKD) is a promising task to train high-performance small models to enhance actual deployment without relying on the original training data.
Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation
In particular, CG2A develops a Gradient Agreement Solver to adaptively balance the varying gradient magnitudes, and introduces a Soft Gradient Surgery strategy to alleviate the gradient conflicts.
Sampling to Distill: Knowledge Transfer from Open-World Data
Then, we introduce a low-noise representation to alleviate the domain shifts and build a structured relationship of multiple data examples to exploit data knowledge.
Context De-confounded Emotion Recognition
However, a long-overlooked issue is that a context bias in existing datasets leads to a significantly unbalanced distribution of emotional states among different context scenarios.
Adversarial Contrastive Distillation with Adaptive Denoising
To this end, we propose a novel structured ARD method called Contrastive Relationship DeNoise Distillation (CRDND).
Efficient universal shuffle attack for visual object tracking
Recently, adversarial attacks have been applied in visual object tracking to deceive deep trackers by injecting imperceptible perturbations into video frames.
