{"ID":2825202,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.21617","arxiv_id":"2512.21617","title":"CausalFSFG: Rethinking Few-Shot Fine-Grained Visual Categorization from Causal Perspective","abstract":"Few-shot fine-grained visual categorization (FS-FGVC) focuses on identifying various subcategories within a common superclass given just one or few support examples. Most existing methods aim to boost classification accuracy by enriching the extracted features with discriminative part-level details. However, they often overlook the fact that the set of support samples acts as a confounding variable, which hampers the FS-FGVC performance by introducing biased data distribution and misguiding the extraction of discriminative features. To address this issue, we propose a new causal FS-FGVC (CausalFSFG) approach inspired by causal inference for addressing biased data distributions through causal intervention. Specifically, based on the structural causal model (SCM), we argue that FS-FGVC infers the subcategories (i.e., effect) from the inputs (i.e., cause), whereas both the few-shot condition disturbance and the inherent fine-grained nature (i.e., large intra-class variance and small inter-class variance) lead to unobservable variables that bring spurious correlations, compromising the final classification performance. To further eliminate the spurious correlations, our CausalFSFG approach incorporates two key components: (1) Interventional multi-scale encoder (IMSE) conducts sample-level interventions, (2) Interventional masked feature reconstruction (IMFR) conducts feature-level interventions, which together reveal real causalities from inputs to subcategories. Extensive experiments and thorough analyses on the widely-used public datasets, including CUB-200-2011, Stanford Dogs, and Stanford Cars, demonstrate that our CausalFSFG achieves new state-of-the-art performance. The code is available at https://github.com/PKU-ICST-MIPL/CausalFSFG_TMM.","short_abstract":"Few-shot fine-grained visual categorization (FS-FGVC) focuses on identifying various subcategories within a common superclass given just one or few support examples. Most existing methods aim to boost classification accuracy by enriching the extracted features with discriminative part-level details. However, they often...","url_abs":"https://arxiv.org/abs/2512.21617","url_pdf":"https://arxiv.org/pdf/2512.21617v1","authors":"[\"Zhiwen Yang\",\"Jinglin Xu\",\"Yuxin Pen\"]","published":"2025-12-25T10:26:17Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":605649,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2825202,"paper_url":"https://arxiv.org/abs/2512.21617","paper_title":"CausalFSFG: Rethinking Few-Shot Fine-Grained Visual Categorization from Causal Perspective","repo_url":"https://github.com/PKU-ICST-MIPL/CausalFSFG_TMM","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}