{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/compare-more-nuancedpairwise-alignment","title":"Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning","arxiv_id":"1904.03580","date":"2019-04-07","proceeding":null,"authors":["Huaxi Huang","Jun-Jie Zhang","Jian Zhang","Qiang Wu","Jingsong Xu"],"abstract":"The recognition ability of human beings is developed in a progressive way.\nUsually, children learn to discriminate various objects from coarse to\nfine-grained with limited supervision. Inspired by this learning process, we\npropose a simple yet effective model for the Few-Shot Fine-Grained (FSFG)\nrecognition, which tries to tackle the challenging fine-grained recognition\ntask using meta-learning. The proposed method, named Pairwise Alignment\nBilinear Network (PABN), is an end-to-end deep neural network. Unlike\ntraditional deep bilinear networks for fine-grained classification, which adopt\nthe self-bilinear pooling to capture the subtle features of images, the\nproposed model uses a novel pairwise bilinear pooling to compare the nuanced\ndifferences between base images and query images for learning a deep distance\nmetric. In order to match base image features with query image features, we\ndesign feature alignment losses before the proposed pairwise bilinear pooling.\nExperiment results on four fine-grained classification datasets and one generic\nfew-shot dataset demonstrate that the proposed model outperforms both the\nstate-ofthe-art few-shot fine-grained and general few-shot methods.","url_abs":"http://arxiv.org/abs/1904.03580v2","url_pdf":"http://arxiv.org/pdf/1904.03580v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"compare-more-nuancedpairwise-alignment","repo_url":"https://github.com/msfuxian/DualAttentionNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}