Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

TALDS-Net: Task-Aware Adaptive Local Descriptors Selection for Few-shot Image Classification

Qian Qiao, Yu Xie, Ziyin Zeng, Fanzhang Li

TL;DR

This work tackles N-way K-shot few-shot image classification by leveraging local descriptors rather than global image features. It introduces TALDS-Net, which uses two learnable modules to adaptively select task-aware support and query descriptors, forming discriminative descriptor subsets through adaptive thresholds and attention maps. The approach, validated by extensive experiments on miniImageNet, tieredImageNet, and CUB-200, achieves state-of-the-art or competitive results across general and fine-grained datasets and backbone configurations, with ablations confirming the benefit of both adaptive modules. The findings highlight the practical significance of adaptive local-descriptor selection for robust few-shot recognition in diverse domains.

Abstract

Few-shot image classification aims to classify images from unseen novel classes with few samples. Recent works demonstrate that deep local descriptors exhibit enhanced representational capabilities compared to image-level features. However, most existing methods solely rely on either employing all local descriptors or directly utilizing partial descriptors, potentially resulting in the loss of crucial information. Moreover, these methods primarily emphasize the selection of query descriptors while overlooking support descriptors. In this paper, we propose a novel Task-Aware Adaptive Local Descriptors Selection Network (TALDS-Net), which exhibits the capacity for adaptive selection of task-aware support descriptors and query descriptors. Specifically, we compare the similarity of each local support descriptor with other local support descriptors to obtain the optimal support descriptor subset and then compare the query descriptors with the optimal support subset to obtain discriminative query descriptors. Extensive experiments demonstrate that our TALDS-Net outperforms state-of-the-art methods on both general and fine-grained datasets.

TALDS-Net: Task-Aware Adaptive Local Descriptors Selection for Few-shot Image Classification

TL;DR

This work tackles N-way K-shot few-shot image classification by leveraging local descriptors rather than global image features. It introduces TALDS-Net, which uses two learnable modules to adaptively select task-aware support and query descriptors, forming discriminative descriptor subsets through adaptive thresholds and attention maps. The approach, validated by extensive experiments on miniImageNet, tieredImageNet, and CUB-200, achieves state-of-the-art or competitive results across general and fine-grained datasets and backbone configurations, with ablations confirming the benefit of both adaptive modules. The findings highlight the practical significance of adaptive local-descriptor selection for robust few-shot recognition in diverse domains.

Abstract

Few-shot image classification aims to classify images from unseen novel classes with few samples. Recent works demonstrate that deep local descriptors exhibit enhanced representational capabilities compared to image-level features. However, most existing methods solely rely on either employing all local descriptors or directly utilizing partial descriptors, potentially resulting in the loss of crucial information. Moreover, these methods primarily emphasize the selection of query descriptors while overlooking support descriptors. In this paper, we propose a novel Task-Aware Adaptive Local Descriptors Selection Network (TALDS-Net), which exhibits the capacity for adaptive selection of task-aware support descriptors and query descriptors. Specifically, we compare the similarity of each local support descriptor with other local support descriptors to obtain the optimal support descriptor subset and then compare the query descriptors with the optimal support subset to obtain discriminative query descriptors. Extensive experiments demonstrate that our TALDS-Net outperforms state-of-the-art methods on both general and fine-grained datasets.
Paper Structure (10 sections, 9 equations, 1 figure, 3 tables)

This paper contains 10 sections, 9 equations, 1 figure, 3 tables.

Table of Contents

  1. Introduction
  2. METHOD
  3. Problem Definition
  4. Image Representation Based on Local Descriptors
  5. Local Descriptors Selection
  6. EXPERIMENTS
  7. Datasets and Implementation Details
  8. Comparisons with State-of-the-art Methods
  9. Ablation Study
  10. CONCLUSIONS

Figures (1)

  • Figure 1: The overall architecture of the proposed TALDS-Net. TALDS-Net extracts descriptors from support and query images using $f_\theta$. Support descriptors are selected into an optimal subset through the adaptive selection module $\mathcal{F}_\Gamma$. Subsequently, query descriptors are adaptively selected through $\mathcal{F}_{\Psi}$.