Compare More Nuanced:pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning

Abstract

The recognition ability of human beings is developed in a progressive way. Usually, children learn to discriminate various objects from coarse to fine-grained with limited supervision. Inspired by this learning process, we propose a simple yet effective model for the Few-Shot Fine-Grained (FSFG) recognition, which tries to tackle the challenging fine-grained recognition task using meta-learning. The proposed method, named Pairwise Alignment Bilinear Network (PABN), is an end-to-end deep neural network. Unlike traditional deep bilinear networks for fine-grained classification, which adopt the self-bilinear pooling to capture the subtle features of images, the proposed model uses a novel pairwise bilinear pooling to compare the nuanced differences between base images and query images for learning a deep distance metric. In order to match base image features with query image features, we design feature alignment losses before the proposed pairwise bilinear pooling. Experiment results on f

Stats

• citations32
• S2 citations—
• github stars0
• HF likes0
• heat score11.39
• arxiv keyhuang2019compare

Related papers

• Bsnet: Bi-similarity Network For Few-shot Fine-grained Image Classification (2020)20.42
• Relationnet2: Deep Comparison Columns For Few-shot Learning (2018)0.00
• Ndpnet: A Novel Non-linear Data Projection Network For Few-shot Fine-grained Image Classification (2021)0.00
• Part-aligned Bilinear Representations For Person Re-identification (2018)19.30
• Effectively Leveraging Attributes For Visual Similarity (2021)3.66
• Query-guided Networks For Few-shot Fine-grained Classification And Person Search (2022)11.29
• Pairwise Similarity Learning Is Simple (2023)7.50
• Pairingnet: A Learning-based Pair-searching And -matching Network For Image Fragments (2023)4.52