Hybrid Feature Collaborative Reconstruction Network for Few-Shot Fine-Grained Image Classification

TL;DR

This paper introduces HFCR-Net, a novel approach combining spatial and channel features through collaborative reconstruction to improve few-shot fine-grained image classification by enhancing inter-class differences.

Contribution

The paper proposes a Hybrid Feature Collaborative Reconstruction Network that fuses spatial and channel features with dynamic weighting for better class distinction in few-shot scenarios.

Findings

Outperforms existing methods on three fine-grained datasets.

Effectively increases inter-class differences while reducing intra-class differences.

Demonstrates robustness with limited samples.

Abstract

Our research focuses on few-shot fine-grained image classification, which faces two major challenges: appearance similarity of fine-grained objects and limited number of samples. To preserve the appearance details of images, traditional feature reconstruction networks usually enhance the representation ability of key features by spatial feature reconstruction and minimizing the reconstruction error. However, we find that relying solely on a single type of feature is insufficient for accurately capturing inter-class differences of fine-grained objects in scenarios with limited samples. In contrast, the introduction of channel features provides additional information dimensions, aiding in better understanding and distinguishing the inter-class differences of fine-grained objects. Therefore, in this paper, we design a new Hybrid Feature Collaborative Reconstruction Network (HFCR-Net) for few-shot fine-grained image classification, which includes a Hybrid Feature Fusion Process (HFFP) and a Hybrid Feature Reconstruction Process (HFRP). In HFRP, we fuse the channel features and the spatial features. Through dynamic weight adjustment, we aggregate the spatial dependencies between arbitrary two positions and the correlations between different channels of each image to increase the inter-class differences. Additionally, we introduce the reconstruction of channel dimension in HFRP. Through the collaborative reconstruction of channel dimension and spatial dimension, the inter-class differences are further increased in the process of support-to-query reconstruction, while the intra-class differences are reduced in the process of query-to-support reconstruction. Ultimately, our extensive experiments on three widely used fine-grained datasets demonstrate the effectiveness and superiority of our approach.