# RecursiveMix: Mixed Learning with History Source: [RecursiveMix: Mixed Learning with History]() Collection index: [llms.txt]() Data updated: 2026-01-04T05:10:29.531Z Authors: Lingfeng Yang, Xiang Li, Borui Zhao, Renjie Song, Jian Yang Published: 2022-03-14T03:59:47.000Z ## Abstract 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 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 \\url{https://github.com/megvii-research/RecursiveMix}. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on COCO 2017 (val)](): Object Detection; COCO 2017 (val); AP: 43. - [Semantic Segmentation on ADE20K (val)](): Semantic segmentation; ADE20K (val); mIoU: 43.26. - [Instance Segmentation on COCO 2017 (val)](): Instance Segmentation; COCO 2017 (val); APm: not recorded. - [Image Classification on ImageNet (val)](): Image Classification; ImageNet (val); Top-1 Acc: not recorded. - [Image Classification on CIFAR-10](): Image Classification; CIFAR-10; Accuracy: not recorded. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()