Improving Image Recognition By Retrieving From Web-scale Image-text Data

Abstract

Retrieval augmented models are becoming increasingly popular for computer vision tasks after their recent success in NLP problems. The goal is to enhance the recognition capabilities of the model by retrieving similar examples for the visual input from an external memory set. In this work, we introduce an attention-based memory module, which learns the importance of each retrieved example from the memory. Compared to existing approaches, our method removes the influence of the irrelevant retrieved examples, and retains those that are beneficial to the input query. We also thoroughly study various ways of constructing the memory dataset. Our experiments show the benefit of using a massive-scale memory dataset of 1B image-text pairs, and demonstrate the performance of different memory representations. We evaluate our method in three different classification tasks, namely long-tailed recognition, learning with noisy labels, and fine-grained classification, and show that it achieves state-

Stats

• citations17
• S2 citations—
• github stars0
• HF likes0
• heat score9.41
• arxiv keyiscen2023improving

Related papers

• Towards Retrieval-augmented Architectures For Image Captioning (2024)9.41
• Retrieval Augmentation For Deep Neural Networks (2021)5.84
• IMRAM: Iterative Matching With Recurrent Attention Memory For Cross-modal Image-text Retrieval (2020)19.22
• Using Text To Teach Image Retrieval (2020)5.24
• Learning Customized Visual Models With Retrieval-augmented Knowledge (2023)11.58
• Generative Cross-modal Retrieval: Memorizing Images In Multimodal Language Models For Retrieval And Beyond (2024)8.35
• Revising Image-text Retrieval Via Multi-modal Entailment (2022)0.00
• Retrieval Augmented Classification For Long-tail Visual Recognition (2022)13.39