Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery

TL;DR

This paper introduces ATCG, a module that enhances generalized category discovery by using analogical textual concepts to improve recognition of known and novel categories in visual data.

Contribution

The paper presents ATCG, a plug-and-play module that fuses textual analogies with visual features to improve category discovery, especially for fine-grained categories.

Findings

Consistently improves performance across six benchmarks.

Significant gains on fine-grained data.

Compatible with existing GCD pipelines without modifications.

Abstract

Generalized Category Discovery (GCD) seeks to uncover novel categories in unlabeled data while preserving recognition of known categories, yet prevailing visual-only pipelines and the loose coupling between supervised learning and discovery often yield brittle boundaries on fine-grained, look-alike categories. We introduce the Analogical Textual Concept Generator (ATCG), a plug-and-play module that analogizes from labeled knowledge to new observations, forming textual concepts for unlabeled samples. Fusing these analogical textual concepts with visual features turns discovery into a visual-textual reasoning process, transferring prior knowledge to novel data and sharpening category separation. ATCG attaches to both parametric and clustering style GCD pipelines and requires no changes to their overall design. Across six benchmarks, ATCG consistently improves overall, known-class, and novel-class performance, with the largest gains on fine-grained data. Our code is available at: https://github.com/zhou-9527/AnaLogical-GCD.