Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification

Abstract

Deep neural networks have demonstrated advanced abilities on various visual classification tasks, which heavily rely on the large-scale training samples with annotated ground-truth. However, it is unrealistic always to require such annotation in real-world applications. Recently, Few-Shot learning (FS), as an attempt to address the shortage of training samples, has made significant progress in generic classification tasks. Nonetheless, it is still challenging for current FS models to distinguish the subtle differences between fine-grained categories given limited training data. To filling the classification gap, in this paper, we address the Few-Shot Fine-Grained (FSFG) classification problem, which focuses on tackling the fine-grained classification under the challenging few-shot learning setting. A novel low-rank pairwise bilinear pooling operation is proposed to capture the nuanced differences between the support and query images for learning an effective distance metric. Moreover, a feature alignment layer is designed to match the support image features with query ones before the comparison. We name the proposed model Low-Rank Pairwise Alignment Bilinear Network (LRPABN), which is trained in an end-to-end fashion. Comprehensive experimental results on four widely used fine-grained classification datasets demonstrate that our LRPABN model achieves the superior performances compared to state-of-the-art methods.

References in corpus (14)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Theoretical Models of Learning to Learn
• Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
• Object-Part Attention Model for Fine-grained Image Classification
• Diversified Visual Attention Networks for Fine-Grained Object Classification
• Weakly Supervised Fine-Grained Image Categorization
• Hadamard Product for Low-rank Bilinear Pooling
• Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples
• A comparison of dense region detectors for image search and fine-grained classification
• Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning
• Cross-modal Hallucination for Few-shot Fine-grained Recognition

Cited by in corpus (15)

• Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment
• TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples
• Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model
• Latent Heterogeneous Graph Network for Incomplete Multi-View Learning
• Multi-level Second-order Few-shot Learning
• APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation
• Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition
• Multi-scale Adaptive Task Attention Network for Few-Shot Learning
• Dynamic Relevance Learning for Few-Shot Object Detection
• Shaping Visual Representations with Attributes for Few-Shot Recognition
• NDPNet: A novel non-linear data projection network for few-shot fine-grained image classification
• Parsing Objects at a Finer Granularity: A Survey
• Hierarchical Representation based Query-Specific Prototypical Network for Few-Shot Image Classification
• Variational Feature Disentangling for Fine-Grained Few-Shot Classification
• Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification