BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification

Abstract

Few-shot learning for fine-grained image classification has gained recent attention in computer vision. Among the approaches for few-shot learning, due to the simplicity and effectiveness, metric-based methods are favorably state-of-the-art on many tasks. Most of the metric-based methods assume a single similarity measure and thus obtain a single feature space. However, if samples can simultaneously be well classified via two distinct similarity measures, the samples within a class can distribute more compactly in a smaller feature space, producing more discriminative feature maps. Motivated by this, we propose a so-called \textit{Bi-Similarity Network} (\textit{BSNet}) that consists of a single embedding module and a bi-similarity module of two similarity measures. After the support images and the query images pass through the convolution-based embedding module, the bi-similarity module learns feature maps according to two similarity measures of diverse characteristics. In this way, the model is enabled to learn more discriminative and less similarity-biased features from few shots of fine-grained images, such that the model generalization ability can be significantly improved. Through extensive experiments by slightly modifying established metric/similarity based networks, we show that the proposed approach produces a substantial improvement on several fine-grained image benchmark datasets. Codes are available at: https://github.com/spraise/BSNet

arXiv commentIEEE TIP 2020

References in corpus (16)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Fine-Grained Visual Classification of Aircraft
• Matching Networks for One Shot Learning
• The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification
• Recent Advances in Convolutional Neural Networks
• Learning feed-forward one-shot learners
• Infinite Mixture Prototypes for Few-Shot Learning
• Learning Correspondence Structures for Person Re-identification
• Partition-Aware Adaptive Switching Neural Networks for Post-Processing in HEVC
• A Tube-and-Droplet-based Approach for Representing and Analyzing Motion Trajectories
• OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
• LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning
• Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning
• Edge-labeling Graph Neural Network for Few-shot Learning

Cited by in corpus (6)

• AI based Service Management for 6G Green Communications
• Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment
• Efficient Few-Shot Object Detection via Knowledge Inheritance
• Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition
• Parsing Objects at a Finer Granularity: A Survey
• Dual Discriminator Adversarial Distillation for Data-free Model Compression