InsCLR: Improving Instance Retrieval with Self-Supervision
This work addresses instance retrieval for computer vision applications, presenting an incremental improvement over existing self-supervised learning methods.
The paper tackles the problem of instance retrieval by identifying that existing self-supervised learning methods fail to improve performance due to insufficient invariance to viewpoint and background variations, and proposes InsCLR, a new method that achieves similar or better performance than state-of-the-art SSL methods on instance retrieval.
This work aims at improving instance retrieval with self-supervision. We find that fine-tuning using the recently developed self-supervised (SSL) learning methods, such as SimCLR and MoCo, fails to improve the performance of instance retrieval. In this work, we identify that the learnt representations for instance retrieval should be invariant to large variations in viewpoint and background etc., whereas self-augmented positives applied by the current SSL methods can not provide strong enough signals for learning robust instance-level representations. To overcome this problem, we propose InsCLR, a new SSL method that builds on the \textit{instance-level} contrast, to learn the intra-class invariance by dynamically mining meaningful pseudo positive samples from both mini-batches and a memory bank during training. Extensive experiments demonstrate that InsCLR achieves similar or even better performance than the state-of-the-art SSL methods on instance retrieval. Code is available at https://github.com/zeludeng/insclr.