paper-with-me

홈 › Papers

Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learning

2024-05-08 · Haichen Zhou, Yixiong Zou, Ruixuan Li, Yuhua Li, Kui Xiao

Few-shot class-incremental learning (FSCIL) aims to acquire knowledge from novel classes with limited samples while retaining information about base classes. Existing methods address catastrophic forgetting and overfitting by freezing the feature extractor during novel-class learning. However, these methods usually tend to cause the confusion between base and novel classes, i.e., classifying novel-class samples into base classes. In this paper, we delve into this phenomenon to study its cause and solution. We first interpret the confusion as the collision between the novel-class and the base-class region in the feature space. Then, we find the collision is caused by the label-irrelevant redundancies within the base-class feature and pixel space. Through qualitative and quantitative experiments, we identify this redundancy as the shortcut in the base-class training, which can be decoupled to alleviate the collision. Based on this analysis, to alleviate the collision between base and novel classes, we propose a method for FSCIL named Redundancy Decoupling and Integration (RDI). RDI first decouples redundancies from base-class space to shrink the intra-base-class feature space. Then, it integrates the redundancies as a dummy class to enlarge the inter-base-class feature space. This process effectively compresses the base-class feature space, creating buffer space for novel classes and alleviating the model's confusion between the base and novel classes. Extensive experiments across benchmark datasets, including CIFAR-100, miniImageNet, and CUB-200-2011 demonstrate that our method achieves state-of-the-art performance.

📄 PDF Abstract BibTeX arXiv:2405.04918

Code (0)

등록된 구현이 없습니다.

Tasks

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Resolving Causal Confusion in Reinforcement Learning via Robust Exploration

2021-03-09 · ICLR Workshop SSL-RL 2021 5 · Clare Lyle, Amy Zhang, Minqi Jiang, Joelle Pineau 외

A reinforcement learning agent must distinguish between spurious correlations and causal relationships in its environment in order to robustly achieve its goals. Contrary to popular belief, such cases of causal confusion…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin

2025-05-04 · Yuchen Wang, Xuefeng Bai, Xiucheng Li, Weili Guan 외

Adapting vision-language models (VLMs) to downstream tasks with pseudolabels has gained increasing attention. A major obstacle is that the pseudolabels generated by VLMs tend to be imbalanced, leading to inferior perform…

Concept Alignment

Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networks

2024-01-05 · Kevin Everson, Yile Gu, Huck Yang, Prashanth Gurunath Shivakumar 외

In the realm of spoken language understanding (SLU), numerous natural language understanding (NLU) methodologies have been adapted by supplying large language models (LLMs) with transcribed speech instead of conventional…

In-Context Learningintent-classificationIntent ClassificationNatural Language Understanding+4

Hilbert-Augmented Reinforcement Learning for Scalable Multi-Robot Coverage and Exploration

2026-02-23 · Tamil Selvan Gurunathan, Aryya Gangopadhyay arxiv

We present a coverage framework that integrates Hilbert space-filling priors into decentralized multi-robot learning and execution. We augment DQN and PPO with Hilbert-based spatial indices to structure exploration and r…

Reinforcement Learning

Minimum Class Confusion for Versatile Domain Adaptation

2019-12-08 · ECCV 2020 8 · Ying Jin, Ximei Wang, Mingsheng Long, Jian-Min Wang

There are a variety of Domain Adaptation (DA) scenarios subject to label sets and domain configurations, including closed-set and partial-set DA, as well as multi-source and multi-target DA. It is notable that existing D…

Domain AdaptationInductive BiasMulti-target Domain AdaptationPartial Domain Adaptation