# Train a One-Million-Way Instance Classifier for Unsupervised Visual Representation Learning

Source: [Train a One-Million-Way Instance Classifier for Unsupervised Visual Representation Learning](<https://www.sota2.com/research/paper/68fa69371e209131cea20e38>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:55:51.498Z

Authors: Yu Liu, Lianghua Huang, Pan Pan, Bin Wang, Yinghui Xu, Rong Jin

Published: 2021-02-09T14:44:18.000Z

## Abstract

This paper presents a simple unsupervised visual representation learning method with a pretext task of discriminating all images in a dataset using a parametric, instance-level classifier. The overall framework is a replica of a supervised classification model, where semantic classes (e.g., dog, bird, and ship) are replaced by instance IDs. However, scaling up the classification task from thousands of semantic labels to millions of instance labels brings specific challenges including 1) the large-scale softmax computation; 2) the slow convergence due to the infrequent visiting of instance samples; and 3) the massive number of negative classes that can be noisy. This work presents several novel techniques to handle these difficulties. First, we introduce a hybrid parallel training framework to make large-scale training feasible. Second, we present a raw-feature initialization mechanism for classification weights, which we assume offers a contrastive prior for instance discrimination and can clearly speed up converge in our experiments. Finally, we propose to smooth the labels of a few hardest classes to avoid optimizing over very similar negative pairs. While being conceptually simple, our framework achieves competitive or superior performance compared to state-of-the-art unsupervised approaches, i.e., SimCLR, MoCoV2, and PIC under ImageNet linear evaluation protocol and on several downstream visual tasks, verifying that full instance classification is a strong pretraining technique for many semantic visual tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2102.04848>)

[PDF](<https://arxiv.org/pdf/2102.04848.pdf>)
