{"ID":2829499,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.12219","arxiv_id":"2512.12219","title":"Fine-Grained Zero-Shot Learning with Attribute-Centric Representations","abstract":"Recognizing unseen fine-grained categories demands a model that can distinguish subtle visual differences. This is typically achieved by transferring visual-attribute relationships from seen classes to unseen classes. The core challenge is attribute entanglement, where conventional models collapse distinct attributes like color, shape, and texture into a single visual embedding. This causes interference that masks these critical distinctions. The post-hoc solutions of previous work are insufficient, as they operate on representations that are already mixed. We propose a zero-shot learning framework that learns AttributeCentric Representations (ACR) to tackle this problem by imposing attribute disentanglement during representation learning. ACR is achieved with two mixture-of-experts components, including Mixture of Patch Experts (MoPE) and Mixture of Attribute Experts (MoAE). First, MoPE is inserted into the transformer using a dual-level routing mechanism to conditionally dispatch image patches to specialized experts. This ensures coherent attribute families are processed by dedicated experts. Finally, the MoAE head projects these expert-refined features into sparse, partaware attribute maps for robust zero-shot classification. On zero-shot learning benchmark datasets CUB, AwA2, and SUN, our ACR achieves consistent state-of-the-art results.","short_abstract":"Recognizing unseen fine-grained categories demands a model that can distinguish subtle visual differences. This is typically achieved by transferring visual-attribute relationships from seen classes to unseen classes. The core challenge is attribute entanglement, where conventional models collapse distinct attributes l...","url_abs":"https://arxiv.org/abs/2512.12219","url_pdf":"https://arxiv.org/pdf/2512.12219v1","authors":"[\"Zhi Chen\",\"Jingcai Guo\",\"Taotao Cai\",\"Yuxiang Cai\"]","published":"2025-12-13T07:12:09Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}