RecursiveMix: Mixed Learning with History

• URL: http://arxiv.org/abs/2203.06844v1
• Date: Mon, 14 Mar 2022 03:59:47 GMT
• Title: RecursiveMix: Mixed Learning with History
• Authors: Lingfeng Yang, Xiang Li, Borui Zhao, Renjie Song, Jian Yang
• Abstract summary: "RecursiveMix" (RM) is a mixed-sample learning paradigm that leverages the historical input-prediction-label triplets. 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.
• Score: 21.865332756486314
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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}.

Related papers

• SUMix: Mixup with Semantic and Uncertain Information [41.99721365685618]
  Mixup data augmentation approaches have been applied for various tasks of deep learning. We propose a novel approach named SUMix to learn the mixing ratio as well as the uncertainty for the mixed samples during the training process.
  arXiv  Detail & Related papers  (2024-07-10T16:25:26Z)
• BackMix: Mitigating Shortcut Learning in Echocardiography with Minimal Supervision [1.3708815960776262]
  We propose a simple, yet effective random background augmentation method called BackMix. By enforcing the background to be uncorrelated with the outcome, the model learns to focus on the data within the ultrasound sector. We extend our method in a semi-supervised setting, finding that the positive effects of BackMix are maintained with as few as 5% of segmentation labels.
  arXiv  Detail & Related papers  (2024-06-27T13:06:47Z)
• MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation [110.09800389100599]
  We propose MixReorg, a novel and straightforward pre-training paradigm for semantic segmentation. Our approach involves generating fine-grained patch-text pairs data by mixing image patches while preserving the correspondence between patches and text. With MixReorg as a mask learner, conventional text-supervised semantic segmentation models can achieve highly generalizable pixel-semantic alignment ability.
  arXiv  Detail & Related papers  (2023-08-09T09:35:16Z)
• Exploring the Limits of Deep Image Clustering using Pretrained Models [1.1060425537315088]
  We present a methodology that learns to classify images without labels by leveraging pretrained feature extractors. We propose a novel objective that learns associations between image features by introducing a variant of pointwise mutual information together with instance weighting.
  arXiv  Detail & Related papers  (2023-03-31T08:56:29Z)
• Co-training $2^L$ Submodels for Visual Recognition [67.02999567435626]
  Submodel co-training is a regularization method related to co-training, self-distillation and depth. We show that submodel co-training is effective to train backbones for recognition tasks such as image classification and semantic segmentation.
  arXiv  Detail & Related papers  (2022-12-09T14:38:09Z)
• ReMix: A General and Efficient Framework for Multiple Instance Learning based Whole Slide Image Classification [14.78430890440035]
  Whole slide image (WSI) classification often relies on weakly supervised multiple instance learning (MIL) methods to handle gigapixel resolution images and slide-level labels. We propose ReMix, a general and efficient framework for MIL based WSI classification.
  arXiv  Detail & Related papers  (2022-07-05T04:21:35Z)
• Bootstrap Your Object Detector via Mixed Training [82.98619147880397]
  MixTraining is a new training paradigm for object detection that can improve the performance of existing detectors for free. It enhances data augmentation by utilizing augmentations of different strengths while excluding the strong augmentations of certain training samples that may be detrimental to training. MixTraining is found to bring consistent improvements across various detectors on the COCO dataset.
  arXiv  Detail & Related papers  (2021-11-04T17:58:26Z)
• Evolving Image Compositions for Feature Representation Learning [22.22790506995431]
  We propose PatchMix, a data augmentation method that creates new samples by composing patches from pairs of images in a grid-like pattern. A ResNet-50 model trained on ImageNet using PatchMix exhibits superior transfer learning capabilities across a wide array of benchmarks.
  arXiv  Detail & Related papers  (2021-06-16T17:57:18Z)
• Jigsaw Clustering for Unsupervised Visual Representation Learning [68.09280490213399]
  We propose a new jigsaw clustering pretext task in this paper. Our method makes use of information from both intra- and inter-images. It is even comparable to the contrastive learning methods when only half of training batches are used.
  arXiv  Detail & Related papers  (2021-04-01T08:09:26Z)
• ReMix: Towards Image-to-Image Translation with Limited Data [154.71724970593036]
  We propose a data augmentation method (ReMix) to tackle this issue. We interpolate training samples at the feature level and propose a novel content loss based on the perceptual relations among samples. The proposed approach effectively reduces the ambiguity of generation and renders content-preserving results.
  arXiv  Detail & Related papers  (2021-03-31T06:24:10Z)
• Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning [108.999497144296]
  Recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. This work aims to involve the distance concept on label space in the unsupervised learning and let the model be aware of the soft degree of similarity between positive or negative pairs. Despite its conceptual simplicity, we show empirically that with the solution -- Unsupervised image mixtures (Un-Mix), we can learn subtler, more robust and generalized representations from the transformed input and corresponding new label space.
  arXiv  Detail & Related papers  (2020-03-11T17:59:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.