Large-Scale Long-Tailed Recognition in an Open World

TL;DR

This paper introduces an integrated algorithm for open long-tailed recognition that effectively handles imbalanced classes, few-shot learning, and open-set recognition by mapping images into a shared feature space with a learned metric.

Contribution

The authors propose a novel dynamic meta-embedding method that combines image and memory features, improving recognition across diverse class distributions in open long-tailed data.

Findings

Outperforms state-of-the-art on three large-scale OLTR datasets

Effectively balances recognition of head, tail, and open classes

Provides publicly available code, datasets, and models for future research

Abstract

Real world data often have a long-tailed and open-ended distribution. A practical recognition system must classify among majority and minority classes, generalize from a few known instances, and acknowledge novelty upon a never seen instance. We define Open Long-Tailed Recognition (OLTR) as learning from such naturally distributed data and optimizing the classification accuracy over a balanced test set which include head, tail, and open classes. OLTR must handle imbalanced classification, few-shot learning, and open-set recognition in one integrated algorithm, whereas existing classification approaches focus only on one aspect and deliver poorly over the entire class spectrum. The key challenges are how to share visual knowledge between head and tail classes and how to reduce confusion between tail and open classes. We develop an integrated OLTR algorithm that maps an image to a feature space such that visual concepts can easily relate to each other based on a learned metric that respects the closed-world classification while acknowledging the novelty of the open world. Our so-called dynamic meta-embedding combines a direct image feature and an associated memory feature, with the feature norm indicating the familiarity to known classes. On three large-scale OLTR datasets we curate from object-centric ImageNet, scene-centric Places, and face-centric MS1M data, our method consistently outperforms the state-of-the-art. Our code, datasets, and models enable future OLTR research and are publicly available at https://liuziwei7.github.io/projects/LongTail.html.