跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.21440 · v1

[CLS] and [EOS] Tokens are not Enough for CLIP-based Class-Incremental Learning

首次提交 2026-11-17 01:28
版本更新 2026-11-17 01:28
雷达观测 2026-11-17 16:10
arXiv ↗PDF ↗

摘要

Class-Incremental Learning (CIL) aims to empower models to continuously acquire new knowledge while mitigating catastrophic forgetting. With the advent of vision-language models like CLIP, leveraging their cross-modal alignment capabilities to address CIL challenges has emerged as a dominant paradigm. Existing methods leverage CLIP's global representations (i.e., the visual [CLS] token and the textual [EOS] token) for cross-modal alignment. While achieving effective classification, they overlook the rich patch-level visual features and token-level textual semantics inherent in CLIP. For example, the [CLS] token aggregates local information to capture the general concept of "cat", while the patch-level details retain specific localized features essential for recognition, such as the tail, fur, and face. We propose PACE (PAtch-token Cross-modal Enhancement) to uncover the long-neglected local representations within CLIP. First, based on the global representations like [CLS] token and [EOS] token, we identify the top-k most crucial visual patches and textual tokens. Subsequently, to better utilize the extracted key local features, we design a cross-modal fusion module. This module leverages local textual semantics to refine visual representations, while augmenting textual semantics with local visual features. As the fusion module is shared across all tasks, directly fine-tuning it on new tasks would interfere with the knowledge learned from previous tasks, leading to catastrophic forgetting. To alleviate this, we employ a projection-based update strategy to effectively preserve the critical parameter space of previous tasks during the adaptation to new tasks. Extensive experiments demonstrate that PACE significantly outperforms state-of-the-art methods across multiple CIL benchmarks.

作者备注:Accepted to TMM. Code is available at: https://github.com/LAMDA-CL/PACE

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-17 01:28 · 最新观测版本

[CLS] and [EOS] Tokens are not Enough for CLIP-based Class-Incremental Learning

Class-Incremental Learning (CIL) aims to empower models to continuously acquire new knowledge while mitigating catastrophic forgetting. With the advent of vision-language models like CLIP, leveraging their cross-modal alignment capabilities to address CIL challenges has emerged as a dominant paradigm. Existing methods leverage CLIP's global representations (i.e., the visual [CLS] token and the textual [EOS] token) for cross-modal alignment. While achieving effective classification, they overlook the rich patch-level visual features and token-level textual semantics inherent in CLIP. For example, the [CLS] token aggregates local information to capture the general concept of "cat", while the patch-level details retain specific localized features essential for recognition, such as the tail, fur, and face. We propose PACE (PAtch-token Cross-modal Enhancement) to uncover the long-neglected local representations within CLIP. First, based on the global representations like [CLS] token and [EOS] token, we identify the top-k most crucial visual patches and textual tokens. Subsequently, to better utilize the extracted key local features, we design a cross-modal fusion module. This module leverages local textual semantics to refine visual representations, while augmenting textual semantics with local visual features. As the fusion module is shared across all tasks, directly fine-tuning it on new tasks would interfere with the knowledge learned from previous tasks, leading to catastrophic forgetting. To alleviate this, we employ a projection-based update strategy to effectively preserve the critical parameter space of previous tasks during the adaptation to new tasks. Extensive experiments demonstrate that PACE significantly outperforms state-of-the-art methods across multiple CIL benchmarks.

查看此版本解读 →查看此版本原文 ↗