Understanding imbalanced semantic segmentation through neural collapse
A recent study has shown a phenomenon called neural collapse in that the within-class
means of features and the classifier weight vectors converge to the vertices of a simplex …
means of features and the classifier weight vectors converge to the vertices of a simplex …
Imbalance trouble: Revisiting neural-collapse geometry
Neural Collapse refers to the remarkable structural properties characterizing the geometry of
class embeddings and classifier weights, found by deep nets when trained beyond zero …
class embeddings and classifier weights, found by deep nets when trained beyond zero …
Neural collapse with normalized features: A geometric analysis over the riemannian manifold
When training overparameterized deep networks for classification tasks, it has been widely
observed that the learned features exhibit a so-called" neural collapse'" phenomenon. More …
observed that the learned features exhibit a so-called" neural collapse'" phenomenon. More …
Digeo: Discriminative geometry-aware learning for generalized few-shot object detection
Generalized few-shot object detection aims to achieve precise detection on both base
classes with abundant annotations and novel classes with limited training data. Existing …
classes with abundant annotations and novel classes with limited training data. Existing …
A neural collapse perspective on feature evolution in graph neural networks
Graph neural networks (GNNs) have become increasingly popular for classification tasks on
graph-structured data. Yet, the interplay between graph topology and feature evolution in …
graph-structured data. Yet, the interplay between graph topology and feature evolution in …
No fear of classifier biases: Neural collapse inspired federated learning with synthetic and fixed classifier
Data heterogeneity is an inherent challenge that hinders the performance of federated
learning (FL). Recent studies have identified the biased classifiers of local models as the key …
learning (FL). Recent studies have identified the biased classifiers of local models as the key …
Federated learning with bilateral curation for partially class-disjoint data
Partially class-disjoint data (PCDD), a common yet under-explored data formation where
each client contributes a part of classes (instead of all classes) of samples, severely …
each client contributes a part of classes (instead of all classes) of samples, severely …
Proxymix: Proxy-based mixup training with label refinery for source-free domain adaptation
Due to privacy concerns and data transmission issues, Source-free Unsupervised Domain
Adaptation (SFDA) has gained popularity. It exploits pre-trained source models, rather than …
Adaptation (SFDA) has gained popularity. It exploits pre-trained source models, rather than …