6 papers
Learning Deep Modality-Shared Self-Expressiveness for Image Clustering with Textual Information
Xianghan Meng, Wei He, Zhiyuan Huang +1
Leveraging textual information for image clustering has emerged as a promising direction, largely owing to the powerful representations learned by Vision-Language Models (VLMs). Ex…
Multi-Modal Representation Learning via Semi-Supervised Rate Reduction for Generalized Category Discovery
Wei He, Xianghan Meng, Zhiyuan Huang +3
Generalized Category Discovery (GCD) aims to identify both known and unknown categories, with only partial labels given for the known categories, posing a challenging open-set reco…
DNT: a Deeply Normalized Transformer that can be trained by Momentum SGD
Xianbiao Qi, Marco Chen, Wenjie Xiao +4
Transformers have become the de facto backbone of modern deep learning, yet their training typically demands an advanced optimizer with adaptive learning rate like AdamW, rather th…
Taming Transformer Without Using Learning Rate Warmup
Xianbiao Qi, Yelin He, Jiaquan Ye +5
Scaling Transformer to a large scale without using some technical tricks such as learning rate warump and using an obviously lower learning rate is an extremely challenging task, a…
Exploring a Principled Framework for Deep Subspace Clustering
Xianghan Meng, Zhiyuan Huang, Wei He +3
Subspace clustering is a classical unsupervised learning task, built on a basic assumption that high-dimensional data can be approximated by a union of subspaces (UoS). Nevertheles…
Neural Normalized Cut: A Differential and Generalizable Approach for Spectral Clustering
Wei He, Shangzhi Zhang, Chun-Guang Li +3
Spectral clustering, as a popular tool for data clustering, requires an eigen-decomposition step on a given affinity to obtain the spectral embedding. Nevertheless, such a step suf…