Search Results for author:
Found 1 papers, 0 papers with code
Navigate Beyond Shortcuts: Debiased Learning through the Lens of Neural Collapse
Recent studies have noted an intriguing phenomenon termed Neural Collapse, that is, when the neural networks establish the right correlation between feature spaces and the training targets, their last-layer features, together with the classifier weights, will collapse into a stable and symmetric structure.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
