Fine-grained Image Retrieval via Dual-Vision Adaptation

TL;DR

This paper introduces a Dual-Vision Adaptation method for fine-grained image retrieval that enhances generalization by collaboratively adapting samples and features while leveraging pre-trained models.

Contribution

The proposed DVA approach enables effective fine-grained image retrieval by combining sample and feature adaptation without overfitting, utilizing knowledge transfer from pre-trained models.

Findings

DVA outperforms existing methods on multiple datasets.

Fewer learnable parameters than traditional fine-tuning.

Effective in both in-distribution and out-of-distribution scenarios.

Abstract

Fine-Grained Image Retrieval~(FGIR) faces challenges in learning discriminative visual representations to retrieve images with similar fine-grained features. Current leading FGIR solutions typically follow two regimes: enforce pairwise similarity constraints in the semantic embedding space, or incorporate a localization sub-network to fine-tune the entire model. However, such two regimes tend to overfit the training data while forgetting the knowledge gained from large-scale pre-training, thus reducing their generalization ability. In this paper, we propose a Dual-Vision Adaptation (DVA) approach for FGIR, which guides the frozen pre-trained model to perform FGIR through collaborative sample and feature adaptation. Specifically, we design Object-Perceptual Adaptation, which modifies input samples to help the pre-trained model perceive critical objects and elements within objects that are helpful for category prediction. Meanwhile, we propose In-Context Adaptation, which introduces a small set of parameters for feature adaptation without modifying the pre-trained parameters. This makes the FGIR task using these adjusted features closer to the task solved during the pre-training. Additionally, to balance retrieval efficiency and performance, we propose Discrimination Perception Transfer to transfer the discriminative knowledge in the object-perceptual adaptation to the image encoder using the knowledge distillation mechanism. Extensive experiments show that DVA has fewer learnable parameters and performs well on three in-distribution and three out-of-distribution fine-grained datasets.