Pith. sign in

Generalized Categories Discovery for Long-tailed Recognition

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Generalized Class Discovery (GCD) plays a pivotal role in discerning both known and unknown categories from unlabeled datasets by harnessing the insights derived from a labeled set comprising recognized classes. A significant limitation in prevailing GCD methods is their presumption of an equitably distributed category occurrence in unlabeled data. Contrary to this assumption, visual classes in natural environments typically exhibit a long-tailed distribution, with known or prevalent categories surfacing more frequently than their rarer counterparts. Our research endeavors to bridge this disconnect by focusing on the long-tailed Generalized Category Discovery (Long-tailed GCD) paradigm, which echoes the innate imbalances of real-world unlabeled datasets. In response to the unique challenges posed by Long-tailed GCD, we present a robust methodology anchored in two strategic regularizations: (i) a reweighting mechanism that bolsters the prominence of less-represented, tail-end categories, and (ii) a class prior constraint that aligns with the anticipated class distribution. Comprehensive experiments reveal that our proposed method surpasses previous state-of-the-art GCD methods by achieving an improvement of approximately 6 - 9% on ImageNet100 and competitive performance on CIFAR100.

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Generalized Class Discovery in Instance Segmentation

cs.CV · 2025-02-12 · conditional · novelty 6.0

A new method combining instance-wise temperature assignment, class-wise dynamic pseudo-label reliability, and a soft attention module achieves state-of-the-art results in generalized class discovery for instance segmentation.

citing papers explorer

Showing 1 of 1 citing paper.

  • Generalized Class Discovery in Instance Segmentation cs.CV · 2025-02-12 · conditional · none · ref 28 · internal anchor

    A new method combining instance-wise temperature assignment, class-wise dynamic pseudo-label reliability, and a soft attention module achieves state-of-the-art results in generalized class discovery for instance segmentation.