Improving memory banks for unsupervised learning with large mini-batch, consistency and hard negative mining

TL;DR

This paper enhances unsupervised instance discrimination by improving memory banks through large mini-batches, consistency enforcement, and hard negative mining, leading to significant accuracy improvements over existing methods.

Contribution

The paper introduces three novel improvements to memory bank-based unsupervised learning: large mini-batches, consistency regularization, and a hard negative mining strategy.

Findings

Significant accuracy gains over baseline methods.

Outperforms existing approaches on seen and unseen categories.

Effective memory bank updates with large mini-batches and hard negative merging.

Abstract

An important component of unsupervised learning by instance-based discrimination is a memory bank for storing a feature representation for each training sample in the dataset. In this paper, we introduce 3 improvements to the vanilla memory bank-based formulation which brings massive accuracy gains: (a) Large mini-batch: we pull multiple augmentations for each sample within the same batch and show that this leads to better models and enhanced memory bank updates. (b) Consistency: we enforce the logits obtained by different augmentations of the same sample to be close without trying to enforce discrimination with respect to negative samples as proposed by previous approaches. (c) Hard negative mining: since instance discrimination is not meaningful for samples that are too visually similar, we devise a novel nearest neighbour approach for improving the memory bank that gradually merges extremely similar data samples that were previously forced to be apart by the instance level classification loss. Overall, our approach greatly improves the vanilla memory-bank based instance discrimination and outperforms all existing methods for both seen and unseen testing categories with cosine similarity.