Improving Memory Banks for Unsupervised Learning with Large Mini-Batch, Consistency and Hard Negative Mining

• Main Authors: Bulat, Adrian, Sanchez-Lozano, Enrique, Tzimiropoulos, Georgios
• Format: Conference Proceeding
• Language: English
• Subjects: Acoustics; Conferences; constrastive loss; Data mining; Data models; memory banks; Signal processing; Speech processing; Training; unsupervised learning
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP39728.2021.9414389

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.