Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917354778132480 |
|---|---|
| author | Han, Jizhou Ding, Chenhao He, Yuhang Wang, Qiang Wang, Shaokun Dong, SongLin Gong, Yihong |
| author_facet | Han, Jizhou Ding, Chenhao He, Yuhang Wang, Qiang Wang, Shaokun Dong, SongLin Gong, Yihong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_19918 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery Han, Jizhou Ding, Chenhao He, Yuhang Wang, Qiang Wang, Shaokun Dong, SongLin Gong, Yihong Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.19918 |