Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery

TL;DR

This paper introduces a novel self-supervised method for discovering unknown categories at test time by conceptualizing categories as optimization solutions, enabling fine-grained and hierarchical categorization with proven optimality.

Contribution

It proposes a new category discovery approach based on category codes and optimization, with theoretical proof and state-of-the-art experimental results.

Findings

Effective discovery of unknown categories at test time.

Enhanced control over category granularity and hierarchy.

State-of-the-art performance on benchmark datasets.

Abstract

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.