Performance Analysis
Rank-DETR for High Quality Object Detection
A highly performant object detector requires accurate ranking for the bounding box predictions.
Overleaf Example
Experiments show that the proposed ReBalanced Adversarial Training (ReBA T) can attain good robustness and does not suffer from robust overfitting even after very long training.
Supplement to " Kernel-based tests for Likelihood-Free Hypothesis Testing " Patrik Róbert Gerber
As mentioned in the discussion succeeding Corollary 3.6, we do conjecture the tight
Kernel-Based Tests for Likelihood-Free Hypothesis Testing
Despite empirical advances, the theoretical study of frequentist LFI is still in its infancy.
Data Portraits: Recording Foundation Model Training Data
Foundation models are trained on increasingly immense and opaque datasets.
Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration
In this Few-Shot Class-Incremental Learning (FSCIL) scenario, existing methods either introduce extra learnable components or rely on a frozen feature extractor to mitigate catastrophic forgetting and overfitting problems.
