Fourier Self-Supervision for Fine-Grained Generalized Category Discovery

2026-08-09

AI Summary

This work addresses the vulnerability of existing generalized category discovery methods to superficial visual cues, which hinders their ability to capture intrinsic attributes of fine-grained novel categories. To overcome this limitation, the authors propose a self-supervised dual-frequency filtering mechanism based on Fourier transform: low-pass filtering extracts high-level semantic content, while high-pass filtering preserves edge and texture details. These components are processed separately in distinct latent spaces and subsequently fused to construct a more robust and comprehensive feature representation. Notably, this is the first approach to incorporate frequency-domain information into generalized category discovery. Without requiring prior knowledge of the number of unknown classes, the method significantly enhances fine-grained novel category recognition and achieves state-of-the-art performance across multiple benchmark datasets.

Abstract

Generalized Category Discovery aims to recognize known categories while identifying novel ones within unlabeled data. Existing methods, typically based on self-supervision and contrastive learning, often struggle to capture fine-grained distinctions, relying on superficial visual cues rather than the intrinsic attributes humans use for categorization. We introduce Fourier Self-Supervision, that leverages the Fourier transform of images to enhance the discrimination of subtle differences and support the discovery of new categories. Our method employs a dual frequency filtering strategy: a low-pass filter first extracts broad, abstract attributes that capture high-level category information, while a high-pass filter emphasizes fine details such as edges and textures that are essential for fine-grained recognition. Each operates on a dedicated latent space, and their overlapping representations together yield a richer, more complete feature space. This dual-frequency approach not only refines feature extraction to identify novel categories, but also strengthens the model's discriminative power in fine-grained category discovery. Experiments on multiple fine-grained datasets show that incorporating Fourier Self-Supervision outperforms state-of-the-art methods, even when the number of classes is unknown, demonstrating its effectiveness for Generalized Category Discovery. Our code is available at: https://github.com/SarahRastegar/FourEx.

Problem

• Generalized Category Discovery
• Fine-Grained Recognition
• Self-Supervision
• Novel Category Discovery
• Feature Discrimination

Innovation

• Fourier Self-Supervision
• Generalized Category Discovery
• fine-grained recognition
• dual frequency filtering
• self-supervised learning