发表机构
University of Amsterdam; University of Technology Nuremberg（阿姆斯特丹大学; 纽伦堡工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出傅里叶自监督学习，通过双频率过滤策略优化特征空间，在多细粒度数据集上实现优于现有方法的广义类别发现性能。
AI 中文摘要
广义类别发现旨在识别已知类别，同时从未标记数据中找出新类别。现有方法通常基于自监督学习和对比学习，往往难以捕捉细粒度差异，依赖表面视觉线索而非人类用于分类的内在属性。我们提出傅里叶自监督学习（Fourier Self-Supervision），利用图像的傅里叶变换增强细微差异的区分度，支持新类别发现。该方法采用双频率过滤策略：低通滤波器先提取捕获高级类别信息的宽泛抽象属性，高通滤波器则强调边缘、纹理等对细粒度识别至关重要的精细细节，两者在各自的潜在空间中运行，其重叠表示共同生成更丰富、更完整的特征空间。这种双频率方法不仅优化特征提取以识别新类别，还增强模型在细粒度类别发现中的区分能力。在多个细粒度数据集上的实验表明，引入傅里叶自监督学习后，即便类别数量未知，其性能也优于现有最先进方法，证明了其在广义类别发现中的有效性。代码可访问：this https URL。
英文摘要
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.
CommentsAccepted by ECCV 2026
