Improving Image Recognition by Retrieving from Web-Scale Image-Text Data

CVPR 2023  ·  Ahmet Iscen, Alireza Fathi, Cordelia Schmid ·

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-of-the-art accuracies in ImageNet-LT, Places-LT and Webvision datasets.

PDF Abstract CVPR 2023 PDF CVPR 2023 Abstract

Results from the Paper


 Ranked #1 on Image Classification on WebVision-1000 (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Benchmark
Long-tail Learning ImageNet-LT MAM (ViT-B/16) Top-1 Accuracy 82.3 # 2
Long-tail Learning Places-LT MAM (ViT-B/16) Top-1 Accuracy 51.4 # 2
Image Classification WebVision-1000 MAM (ViT-B/16) Top-1 Accuracy 83.6 # 1

Methods


No methods listed for this paper. Add relevant methods here