Timezone: »

 
Poster
RecursiveMix: Mixed Learning with History
Lingfeng Yang · Xiang Li · Borui Zhao · Renjie Song · Jian Yang

Wed Nov 30 02:00 PM -- 04:00 PM (PST) @ Hall J #633
in Poster Session 4 »
Mix-based augmentation has been proven fundamental to the generalization of deep vision models. However, current augmentations only mix samples from 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. Furthermore, 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 CIFAR-100 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 segmentation, RM also surpasses the baseline and CutMix by 1.9 and 1.1 mIoU points under UperNet on ADE20K, respectively. Codes and pretrained models are available at https://github.com/implus/RecursiveMix.
Keywords: Data Augmentation · Historical Knowledge
[ Paper]  [ Slides]  [ Poster]  [ OpenReview] 

Author Information

Lingfeng Yang (Nanjing University of Science and Technology)
Xiang Li (Nankai University)
Borui Zhao (MEGVII TECHNOLOGY INC)
Renjie Song (Megvii Technology Inc.)
Jian Yang (Nanjing University of Science and Technology)

More from the Same Authors