# Fine-Grained Zero-Shot Learning with Attribute-Centric Representations Source: [Fine-Grained Zero-Shot Learning with Attribute-Centric Representations]() Collection index: [llms.txt]() Data updated: 2025-12-17T05:03:46.185Z Authors: Zhi Chen, Jingcai Guo, Taotao Cai, Yuxiang Cai Published: 2025-12-13T07:12:09.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Zero-shot Image Classification on AwA2 (test)](): Zero-shot Image Classification; AWA2 (test); Metric U: 74.1. - [Zero-Shot Image Classification on CUB](): Zero-shot Image Classification; CUB; U Score: 72.8. - [Zero-Shot Classification on SUN (T1, U, S, H metrics)](): Zero-shot Classification; SUN; U Score: 60. ## Original sources and implementation [Original paper]() [PDF]()