Fugu-MT: arxivの論文翻訳

Semantic Mismapping in Generalized Category Discovery: Evaluation and Mitigation

Authors Zitai Wang, Qianqian Xu, Cong Hua, Xi Chen, Zhiyong Yang, Xiaochun Cao, Qingming Huang
Affiliations Chinese Academy of Sciences / University of the Chinese Academy of Sciences / Beijing Academy of Artificial Intelligence / Sun Yat-Sen University
Categories Evaluation / Semantic Consistency Evaluation / Semantic preservation evaluation in category discovery, Method / Category Discovery / Generalized category discovery with semantic constraints, Application / Image Classification / Old and new category recognition
License CC BY 4.0

Abstract Overview

Generalized category discovery aims to recognize known categories and discover new ones in the same unlabeled dataset. The paper identifies semantic mismapping: global Hungarian matching can reassign supervised old-category outputs and count prediction errors as correct. It proposes Semantics-Preserving Evaluation (SPE), which fixes old-output meanings and matches only new outputs, and Mismapping-Mitigating Optimization (MMO), which regularizes old–new prediction balance and new-prototype diversity. Experiments show substantial evaluation gaps on fine-grained benchmarks and generally improved new-category accuracy with MMO, though improvements are not universal.

Novelty

The work adapts evaluation to the partially exchangeable outputs of parametric category-discovery models and characterizes score gains from mismapping through permutation cycles. It also introduces two auxiliary training losses motivated by this evaluation issue, along with extensions of SPE to non-parametric methods and estimated category counts.

Results

On Herbarium 19, global matching reported new-category accuracy 17.40–25.63 percentage points higher than SPE across seven configurations and altered method rankings. MMO improved new-category accuracy in 23 of 28 fine-grained configurations under both protocols, although some settings exhibited old–new accuracy trade-offs.

Key Points

  1. SPE preserves supervised old-category labels, matches new outputs locally, and counts cross-region predictions as errors.
  2. MMO combines a region-balance loss based on estimated old–new sample proportions with a loss encouraging diversity among new-category prototypes.
  3. Experiments also demonstrate SPE with estimated category numbers and with non-parametric clusters calibrated using labeled data.

References

This page was created using generative AI such as GPT-5, Claude Opus 4, Gemini 3, Gemini 3.1 Flash Image, and their higher-end successor versions. No guarantee can be made regarding its contents.