conftrace_

neural collapse

51 papers

Explore in graph

Also known as

NC

Co-occurring keywords

representation learning (6206) feature learning (1311) deep neural network (1803) simplex equiangular tight frame (9) classifier weight (14) feature representation (505) class imbalance (555) feature alignment (416) continual learning (1181) long-tailed distribution (142)

Papers

Targeted Representation Alignment for Open-World Semi-Supervised Learning CVPR 2024
Navigate Beyond Shortcuts: Debiased Learning Through the Lens of Neural Collapse CVPR 2024
Neural collapse vs. low-rank bias: Is deep neural collapse really optimal? NIPS 2024
Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective NIPS 2024
Quantifying the Variability Collapse of Neural Networks ICML 2023
Perturbation Analysis of Neural Collapse ICML 2023
A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks NIPS 2023
Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations ICML 2023
No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier ICCV 2023
Inducing Neural Collapse to a Fixed Hierarchy-Aware Frame for Reducing Mistake Severity ICCV 2023
How Far Pre-trained Models Are from Neural Collapse on the Target Dataset Informs their Transferability ICCV 2023
Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data ICML 2023
Feature learning in deep classifiers through Intermediate Neural Collapse ICML 2023
Inducing Neural Collapse in Deep Long-tailed Learning AISTATS 2023
Residual Alignment: Uncovering the Mechanisms of Residual Networks NIPS 2023
Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model NIPS 2023
Neural (Tangent Kernel) Collapse NIPS 2023
Understanding Imbalanced Semantic Segmentation Through Neural Collapse CVPR 2023
Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold NIPS 2022
Imbalance Trouble: Revisiting Neural-Collapse Geometry NIPS 2022
On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features ICML 2022
Extended Unconstrained Features Model for Exploring Deep Neural Collapse ICML 2022
Are All Losses Created Equal: A Neural Collapse Perspective NIPS 2022
Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network? NIPS 2022
Revealing the Structure of Deep Neural Networks via Convex Duality ICML 2021