Scholarlink

<p>Generalized category discovery (GCD) aims at addressing a more realistic and challenging setting of semi-supervised learning, where only part of the category labels are assigned to certain training samples, leaving some undiscovered semantic pattern within the unlabeled data. To obtain a more generalized classification model, it is crucial to discover potential novel categories with knowledge only from the labeled set. Previous methods generally achieve this goal by employing naive contrastive learning or unsupervised clustering for all the samples. Nevertheless, they usually ignore the inherent critical information within the historical predictions of the model being trained. Specifically, we empirically reveal that a significant number of unlabelled samples yield consistent historical predictions corresponding to their ground truth class. Motivated by this observation, we propose a <b>M</b>emory <b>C</b>onsistency guided <b>D</b>ivide-and-conquer <b>L</b>earning (MCDL) framework. In this framework, we introduce two online-updating memory banks to record historical predictions of unlabeled data, which are exploited to accurately measure the credibility of each sample in terms of its prediction consistency. With the guidance of credibility, we design a divide-and-conquer learning strategy to utilize the credible, discriminative information of unlabeled data while alleviating the negative influence of noisy labels. Extensive experimental results on multiple benchmarks demonstrate the generality and superiority of our method, where our method consistently outperforms state-of-the-art models by a large margin and boost their performance in a plug-in-play manner on both seen and unseen classes of the generic image recognition and challenging semantic shift settings (e.g., with +8.4% gain on CUB and +8.1% on Standford Cars).</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Memory Consistency Guided Divide-and-Conquer Learning for Generalized Category Discovery

  • 期刊论文

  • 发表日期：

    2026年3月6日

查看全文
  • Yuanpeng Tu,
  • Zhun Zhong,
  • Yuxi Li,
  • Hengshuang Zhao

摘要

Generalized category discovery (GCD) aims at addressing a more realistic and challenging setting of semi-supervised learning, where only part of the category labels are assigned to certain training samples, leaving some undiscovered semantic pattern within the unlabeled data. To obtain a more generalized classification model, it is crucial to discover potential novel categories with knowledge only from the labeled set. Previous methods generally achieve this goal by employing naive contrastive learning or unsupervised clustering for all the samples. Nevertheless, they usually ignore the inherent critical information within the historical predictions of the model being trained. Specifically, we empirically reveal that a significant number of unlabelled samples yield consistent historical predictions corresponding to their ground truth class. Motivated by this observation, we propose a Memory Consistency guided Divide-and-conquer Learning (MCDL) framework. In this framework, we introduce two online-updating memory banks to record historical predictions of unlabeled data, which are exploited to accurately measure the credibility of each sample in terms of its prediction consistency. With the guidance of credibility, we design a divide-and-conquer learning strategy to utilize the credible, discriminative information of unlabeled data while alleviating the negative influence of noisy labels. Extensive experimental results on multiple benchmarks demonstrate the generality and superiority of our method, where our method consistently outperforms state-of-the-art models by a large margin and boost their performance in a plug-in-play manner on both seen and unseen classes of the generic image recognition and challenging semantic shift settings (e.g., with +8.4% gain on CUB and +8.1% on Standford Cars).