Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery
NeurIPS(2023)
摘要
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.
更多查看译文
关键词
categorize,category,discovery,generalized
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要