Instance Segmentation Challenge Track Technical Report, VIPriors Workshop at ICCV 2021: Task-Specific Copy-Paste Data Augmentation Method for Instance Segmentation

TL;DR

This paper presents a task-specific Copy-Paste data augmentation method combined with other techniques to improve instance segmentation performance, achieving state-of-the-art AP scores in the VIPriors challenge.

Contribution

The paper introduces a novel task-specific Copy-Paste augmentation method for instance segmentation and demonstrates its effectiveness within a comprehensive training pipeline.

Findings

Achieved 0.477 AP@0.50:0.95 on test set.

Combined Copy-Paste with RandAugment and GridMask.

Used HTC detector with CBSwin-B backbone.

Abstract

Copy-Paste has proven to be a very effective data augmentation for instance segmentation which can improve the generalization of the model. We used a task-specific Copy-Paste data augmentation method to achieve good performance on the instance segmentation track of the 2nd VIPriors workshop challenge. We also applied additional data augmentation techniques including RandAugment and GridMask. Our segmentation model is the HTC detector on the CBSwin-B with CBFPN with some tweaks. This model was trained at the multi-scale mode by a random sampler on the 6x schedule and tested at the single-scale mode. By combining these techniques, we achieved 0.398 AP@0.50:0.95 with the validation set and 0.433 AP@0.50:0.95 with the test set. Finally, we reached 0.477 AP@0.50:0.95 with the test set by adding the validation set to the training data. Source code is available at https://github.com/jahongir7174/VIP2021.