paper-with-me

Papers

Towards Robust Visual Continual Learning with Multi-Prototype Supervision

2025-09-19 · Xiwei Liu, Yulong Li, Yichen Li, Xinlin Zhuang, Haolin Yang, Huifa Li, Imran Razzak arxiv

Language-guided supervision, which utilizes a frozen semantic target from a Pretrained Language Model (PLM), has emerged as a promising paradigm for visual Continual Learning (CL). However, relying on a single target introduces two critical limitations: 1) semantic ambiguity, where a polysemous category name results in conflicting visual representations, and 2) intra-class visual diversity, where a single prototype fails to capture the rich variety of visual appearances within a class. To this end, we propose MuproCL, a novel framework that replaces the single target with multiple, context-aware prototypes. Specifically, we employ a lightweight LLM agent to perform category disambiguation and visual-modal expansion to generate a robust set of semantic prototypes. A LogSumExp aggregation mechanism allows the vision model to adaptively align with the most relevant prototype for a given image. Extensive experiments across various CL baselines demonstrate that MuproCL consistently enhances performance and robustness, establishing a more effective path for language-guided continual learning.

📄 PDF Abstract BibTeX arXiv:2509.16011

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Continual Learning for Autonomous Robots: A Prototype-based Approach

2024-03-30 · Elvin Hajizada, Balachandran Swaminathan, Yulia Sandamirskaya

Humans and animals learn throughout their lives from limited amounts of sensed data, both with and without supervision. Autonomous, intelligent robots of the future are often expected to do the same. The existing continu…

Continual Learning

Continual Segmentation under Joint Nonstationarity

2026-05-19 · Prashant Pandey, Himanshu Kumar, Devineni Sri Venkatraya Chowdary, Brejesh Lall arxiv

Evolving data streams induce joint nonstationarity in continual semantic segmentation, where semantic classes, input distributions, and supervision availability change simultaneously over time. This setting reflects prac…

Continual Semantic SegmentationStructured PredictionContinual Learning

Online Continual Learning with Dynamic Label Hierarchies

2026-05-12 · Xinrui Wang, Shao-Yuan Li, Bartłomiej Twardowski, Alexandra Gomez-Villa 외 arxiv

Online Continual Learning (OCL) aims to learn from endless non\text{-}stationary data streams, yet most existing methods assume a flat label space and overlook the hierarchical organization of real\text{-}world concepts …

Continual Learning

Continual Learning with Vision-Language Models via Semantic-Geometry Preservation

2026-03-12 · Chiyuan He, Zihuan Qiu, Fanman Meng, Runtong Zhang 외 arxiv

Continual learning of pretrained vision-language models (VLMs) is prone to catastrophic forgetting, yet current approaches adapt to new tasks without explicitly preserving the cross-modal semantic geometry inherited from…

Continual Learning

PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding

2024-11-01 · Jincen Jiang, Qianyu Zhou, Yuhang Li, Xinkui Zhao 외

In this paper, we present PCoTTA, an innovative, pioneering framework for Continual Test-Time Adaptation (CoTTA) in multi-task point cloud understanding, enhancing the model's transferability towards the continually chan…

Test-time Adaptation