Online Continual Learning via Multiple Deep Metric Learning and Uncertainty-guided Episodic Memory Replay -- 3rd Place Solution for ICCV 2021 Workshop SSLAD Track 3A Continual Object Classification

TL;DR

This paper presents a novel online continual learning approach that combines deep metric learning, uncertainty-guided memory replay, and class-balanced loss to improve object classification in long-tailed, shifting distributions, achieving state-of-the-art results.

Contribution

It introduces a multi-faceted method integrating deep metric learning, uncertainty-based sample selection, and specialized loss functions for continual learning in challenging, real-world scenarios.

Findings

Achieved 64.01% AMCA on validation set.

Demonstrated improved generalization over existing methods.

Effectively handled long-tailed and distribution-shifted data.

Abstract

Online continual learning in the wild is a very difficult task in machine learning. Non-stationarity in online continual learning potentially brings about catastrophic forgetting in neural networks. Specifically, online continual learning for autonomous driving with SODA10M dataset exhibits extra problems on extremely long-tailed distribution with continuous distribution shift. To address these problems, we propose multiple deep metric representation learning via both contrastive and supervised contrastive learning alongside soft labels distillation to improve model generalization. Moreover, we exploit modified class-balanced focal loss for sensitive penalization in class imbalanced and hard-easy samples. We also store some samples under guidance of uncertainty metric for rehearsal and perform online and periodical memory updates. Our proposed method achieves considerable generalization with average mean class accuracy (AMCA) 64.01% on validation and 64.53% AMCA on test set.