TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples

Abstract

The challenges of high intra-class variance yet low inter-class fluctuations in fine-grained visual categorization are more severe with few labeled samples, \textit{i.e.,} Fine-Grained categorization problems under the Few-Shot setting (FGFS). High-order features are usually developed to uncover subtle differences between sub-categories in FGFS, but they are less effective in handling the high intra-class variance. In this paper, we propose a Target-Oriented Alignment Network (TOAN) to investigate the fine-grained relation between the target query image and support classes. The feature of each support image is transformed to match the query ones in the embedding feature space, which reduces the disparity explicitly within each category. Moreover, different from existing FGFS approaches devise the high-order features over the global image with less explicit consideration of discriminative parts, we generate discriminative fine-grained features by integrating compositional concept representations to global second-order pooling. Extensive experiments are conducted on four fine-grained benchmarks to demonstrate the effectiveness of TOAN compared with the state-of-the-art models.

arXiv commentT-CSVT Accepted

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
• Meta-Learning with Implicit Gradients
• Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification
• Hadamard Product for Low-rank Bilinear Pooling
• Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples
• Cross Attention Network for Few-shot Classification
• Fine-grained Visual-textual Representation Learning
• Hyperspherical Prototype Networks
• Learning Deep Bilinear Transformation for Fine-grained Image Representation
• Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning
• Weakly-supervised Compositional FeatureAggregation for Few-shot Recognition
• Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition
• Fine-Grain Few-Shot Vision via Domain Knowledge as Hyperspherical Priors

Cited by in corpus (2)

• Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment
• Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition