TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Long-tail Learning	iNaturalist 2018	RAC (ViT-B-16)	Top-1 Accuracy	80.24%	# 4
Long-tail Learning	Places-LT	RAC (ViT-B-16)	Top-1 Accuracy	47.17	# 8

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/retrieval-augmented-classification-for-long/long-tail-learning-on-inaturalist-2018)](https://paperswithcode.com/sota/long-tail-learning-on-inaturalist-2018?p=retrieval-augmented-classification-for-long)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/retrieval-augmented-classification-for-long/long-tail-learning-on-places-lt)](https://paperswithcode.com/sota/long-tail-learning-on-places-lt?p=retrieval-augmented-classification-for-long)`

Retrieval Augmented Classification for Long-Tail Visual Recognition

CVPR 2022 · Alexander Long, Wei Yin, Thalaiyasingam Ajanthan, Vu Nguyen, Pulak Purkait, Ravi Garg, Alan Blair, Chunhua Shen, Anton Van Den Hengel ·

We introduce Retrieval Augmented Classification (RAC), a generic approach to augmenting standard image classification pipelines with an explicit retrieval module. RAC consists of a standard base image encoder fused with a parallel retrieval branch that queries a non-parametric external memory of pre-encoded images and associated text snippets. We apply RAC to the problem of long-tail classification and demonstrate a significant improvement over previous state-of-the-art on Places365-LT and iNaturalist-2018 (14.5% and 6.7% respectively), despite using only the training datasets themselves as the external information source. We demonstrate that RAC's retrieval module, without prompting, learns a high level of accuracy on tail classes. This, in turn, frees the base encoder to focus on common classes, and improve its performance thereon. RAC represents an alternative approach to utilizing large, pretrained models without requiring fine-tuning, as well as a first step towards more effectively making use of external memory within common computer vision architectures.