Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917569974239232 |
|---|---|
| author | Rastegar, Sarah Doughty, Hazel Snoek, Cees G. M. |
| author_facet | Rastegar, Sarah Doughty, Hazel Snoek, Cees G. M. |
| contents | In the quest for unveiling novel categories at test time, we confront the inherent limitations of traditional supervised recognition models that are restricted by a predefined category set. While strides have been made in the realms of self-supervised and open-world learning towards test-time category discovery, a crucial yet often overlooked question persists: what exactly delineates a category? In this paper, we conceptualize a category through the lens of optimization, viewing it as an optimal solution to a well-defined problem. Harnessing this unique conceptualization, we propose a novel, efficient and self-supervised method capable of discovering previously unknown categories at test time. A salient feature of our approach is the assignment of minimum length category codes to individual data instances, which encapsulates the implicit category hierarchy prevalent in real-world datasets. This mechanism affords us enhanced control over category granularity, thereby equipping our model to handle fine-grained categories adeptly. Experimental evaluations, bolstered by state-of-the-art benchmark comparisons, testify to the efficacy of our solution in managing unknown categories at test time. Furthermore, we fortify our proposition with a theoretical foundation, providing proof of its optimality. Our code is available at https://github.com/SarahRastegar/InfoSieve. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_19776 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery Rastegar, Sarah Doughty, Hazel Snoek, Cees G. M. Computer Vision and Pattern Recognition Artificial Intelligence Information Theory Machine Learning I.2.1.b; I.2.6.g; I.5.4.b; I.4 In the quest for unveiling novel categories at test time, we confront the inherent limitations of traditional supervised recognition models that are restricted by a predefined category set. While strides have been made in the realms of self-supervised and open-world learning towards test-time category discovery, a crucial yet often overlooked question persists: what exactly delineates a category? In this paper, we conceptualize a category through the lens of optimization, viewing it as an optimal solution to a well-defined problem. Harnessing this unique conceptualization, we propose a novel, efficient and self-supervised method capable of discovering previously unknown categories at test time. A salient feature of our approach is the assignment of minimum length category codes to individual data instances, which encapsulates the implicit category hierarchy prevalent in real-world datasets. This mechanism affords us enhanced control over category granularity, thereby equipping our model to handle fine-grained categories adeptly. Experimental evaluations, bolstered by state-of-the-art benchmark comparisons, testify to the efficacy of our solution in managing unknown categories at test time. Furthermore, we fortify our proposition with a theoretical foundation, providing proof of its optimality. Our code is available at https://github.com/SarahRastegar/InfoSieve. |
| title | Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Information Theory Machine Learning I.2.1.b; I.2.6.g; I.5.4.b; I.4 |
| url | https://arxiv.org/abs/2310.19776 |