Breaking Fine-Grained Classification Barriers with Cost-Free Data in Few-Shot Class-Incremental Learning

2024-12-29

AI Summary

Fine-grained classification faces challenges of data scarcity, high annotation cost, and dynamic class evolution. To address these, this paper proposes a novel continual learning paradigm that requires no additional labeled data. Our core innovation is an “Explore-Exploit” (EXP2) two-stage online optimization mechanism: before inference, it actively selects representative unlabeled samples based on class prototypes, adaptively reweights them in feature space, and performs lightweight classifier fine-tuning. This eliminates dependence on supervised incremental data, enabling autonomous model evolution during deployment. Extensive experiments on multiple fine-grained benchmarks demonstrate significant improvements over state-of-the-art methods. Notably, with only 0.5% newly annotated samples, our approach achieves over 92% accuracy—validating the effective, zero-cost utilization of unlabeled data for continual adaptation.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Current fine-grained classification research mainly concentrates on fine-grained feature learning, but in real-world applications, the bigger issue often lies in the data. Fine-grained data annotation is challenging, and the features and semantics are highly diverse and frequently changing, making traditional methods less effective in real-world scenarios. Although some studies have provided potential solutions to this issue, most are limited to making use of limited supervised information. In this paper, we propose a novel learning paradigm to break barriers in fine-grained classification. It enables the model to learn beyond the standard training phase and benefit from cost-free data encountered during system operation. On this basis, an efficient EXPloring and EXPloiting strategy and method (EXP2) is designed. Thereinto, before the final classification results are obtained, representative inference data samples are explored according to class templates and exploited to optimize classifiers. Experimental results demonstrate the general effectiveness of EXP2.

Problem

• Fine-grained Classification
• Data Scarcity
• Unsupervised Learning

Innovation

• EXP2 Strategy
• Unlabeled Data Utilization
• Dynamic Learning for Fine-grained Classification