Can I read RecursiveMix: Mixed Learning with History on EtoBox?

RecursiveMix: Mixed Learning with History by Yang, Lingfeng; Li, Xiang; Zhao, Borui; Song, Renjie; Yang, Jian is a scholarly article available to read on EtoBox.

What is RecursiveMix: Mixed Learning with History about?

Mix-based augmentation has been proven fundamental to the generalization of deep vision models. However, current augmentations only mix samples at the current data batch during training, which ignores the possible knowledge accumulated in the learning history. In this paper, we propose a recursive mixed-sample learning paradigm, termed "RecursiveMix" (RM), by exploring a novel training strategy that leverages the historical input-prediction-label triplets. More specifically, we iteratively resize the input image batch from the previous iteration and paste it into the current batch while their labels are fused proportionally to the area of the operated patches. Further, a consistency loss is introduced to align the identical image semantics across the iterations, which helps the learning of scale-invariant feature representations. Based on ResNet-50, RM largely improves classification accuracy by $\sim$3.2\% on CIFAR100 and $\sim$2.8\% on ImageNet with negligible extra computation/storage costs. In the downstream object detection task, the RM pretrained model outperforms the baseline by 2.1 AP points and surpasses CutMix by 1.4 AP points under the ATSS detector on COCO. In semantic

Author

Yang, Lingfeng; Li, Xiang; Zhao, Borui; Song, Renjie; Yang, Jian

Published

2022

Language

EN