Learning semi-supervised gaussian mixture models for generalized category discovery
In this paper, we address the problem of generalized category discovery (GCD), ie, given a
set of images where part of them are labelled and the rest are not, the task is to automatically …
set of images where part of them are labelled and the rest are not, the task is to automatically …
Self-supervised visual representation learning with semantic grouping
X Wen, B Zhao, A Zheng… - Advances in neural …, 2022 - proceedings.neurips.cc
In this paper, we tackle the problem of learning visual representations from unlabeled scene-
centric data. Existing works have demonstrated the potential of utilizing the underlying …
centric data. Existing works have demonstrated the potential of utilizing the underlying …
Parametric classification for generalized category discovery: A baseline study
Abstract Generalized Category Discovery (GCD) aims to discover novel categories in
unlabelled datasets using knowledge learned from labelled samples. Previous studies …
unlabelled datasets using knowledge learned from labelled samples. Previous studies …
Margin-based few-shot class-incremental learning with class-level overfitting mitigation
Few-shot class-incremental learning (FSCIL) is designed to incrementally recognize novel
classes with only few training samples after the (pre-) training on base classes with sufficient …
classes with only few training samples after the (pre-) training on base classes with sufficient …
Exploring model transferability through the lens of potential energy
Transfer learning has become crucial in computer vision tasks due to the vast availability of
pre-trained deep learning models. However, selecting the optimal pre-trained model from a …
pre-trained deep learning models. However, selecting the optimal pre-trained model from a …
Ood-cv: A benchmark for robustness to out-of-distribution shifts of individual nuisances in natural images
Enhancing the robustness of vision algorithms in real-world scenarios is challenging. One
reason is that existing robustness benchmarks are limited, as they either rely on synthetic …
reason is that existing robustness benchmarks are limited, as they either rely on synthetic …
[HTML][HTML] Learning optimal inter-class margin adaptively for few-shot class-incremental learning via neural collapse-based meta-learning
Abstract Few-Shot Class-Incremental Learning (FSCIL) aims to learn new classes
incrementally with a limited number of samples per class. It faces issues of forgetting …
incrementally with a limited number of samples per class. It faces issues of forgetting …
Relaxed contrastive learning for federated learning
We propose a novel contrastive learning framework to effectively address the challenges of
data heterogeneity in federated learning. We first analyze the inconsistency of gradient …
data heterogeneity in federated learning. We first analyze the inconsistency of gradient …
Quantifying the variability collapse of neural networks
J Xu, H Liu - International Conference on Machine Learning, 2023 - proceedings.mlr.press
Recent studies empirically demonstrate the positive relationship between the transferability
of neural networks and the in-class variation of the last layer features. The recently …
of neural networks and the in-class variation of the last layer features. The recently …
Pick the best pre-trained model: Towards transferability estimation for medical image segmentation
Transfer learning is a critical technique in training deep neural networks for the challenging
medical image segmentation task that requires enormous resources. With the abundance of …
medical image segmentation task that requires enormous resources. With the abundance of …