arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.13409cs.CV
收藏

语义分割的多尺度和跨尺度对比学习

Multi-scale and Cross-scale Contrastive Learning for Semantic Segmentation

University College London(伦敦大学学院);King’s College London(伦敦国王学院);Moorfields Eye Hospital(摩尔菲尔兹眼科医院)

Theodoros Pissas, Claudio S. Ravasio, Lyndon Da Cruz, Christos Bergeles

摘要:

这项工作认为监督对比学习的语义分割。我们应用对比学习来增强语义分割网络提取的多尺度特征的区分能力。我们的关键方法见解是利用来自模型编码器本身的多个阶段的特征空间的样本,既不需要数据增强也不需要在线存储体来获得不同的样本集。为了允许这样的扩展,我们引入了一个高效且有效的采样过程,该过程使得能够在多个尺度上对编码器的特征应用对比度损失。此外,通过首先将编码器的多尺度表示映射到一个公共的特征空间,我们通过引入跨尺度对比学习将高分辨率局部特征与低分辨率全局特征联系起来,实例化了一种新形式的监督局部全局约束。结合起来,我们的多尺度和跨尺度对比损失提高了具有CNN和Transformer主干的各种模型(DeepLabV3,HRNet,OCRNet,UPerNet)的性能,当在来自自然(Cityscapes,PascalContext,ADE 20 K)和手术(CaDIS)领域的4个不同数据集上进行评估时。我们的代码可在https://github.com/RViMLab/MS_CS_ContrSeg上获得。数据集来自自然(Cityscapes,PascalContext,ADE20K)和外科(CaDIS)领域。

英文摘要:

This work considers supervised contrastive learning for semantic segmentation. We apply contrastive learning to enhance the discriminative power of the multi-scale features extracted by semantic segmentation networks. Our key methodological insight is to leverage samples from the feature spaces emanating from multiple stages of a model's encoder itself requiring neither data augmentation nor online memory banks to obtain a diverse set of samples. To allow for such an extension we introduce an efficient and effective sampling process, that enables applying contrastive losses over the encoder's features at multiple scales. Furthermore, by first mapping the encoder's multi-scale representations to a common feature space, we instantiate a novel form of supervised local-global constraint by introducing cross-scale contrastive learning linking high-resolution local features to low-resolution global features. Combined, our multi-scale and cross-scale contrastive losses boost performance of various models (DeepLabV3, HRNet, OCRNet, UPerNet) with both CNN and Transformer backbones, when evaluated on 4 diverse datasets from natural (Cityscapes, PascalContext, ADE20K) but also surgical (CaDIS) domains. Our code is available at https://github.com/RViMLab/MS_CS_ContrSeg. datasets from natural (Cityscapes, PascalContext, ADE20K) but also surgical (CaDIS) domains.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑