Scale Equalization for Multi-Level Feature Fusion
Deep neural networks have exhibited remarkable performance in a variety of computer vision fields, especially in semantic segmentation tasks. Their success is often attributed to multi-level feature fusion, which enables them to understand both global and local information from an image. However, we found that multi-level features from parallel branches are on different scales. The scale disequilibrium is a universal and unwanted flaw that leads to detrimental gradient descent, thereby degrading performance in semantic segmentation. We discover that scale disequilibrium is caused by bilinear upsampling, which is supported by both theoretical and empirical evidence. Based on this observation, we propose injecting scale equalizers to achieve scale equilibrium across multi-level features after bilinear upsampling. Our proposed scale equalizers are easy to implement, applicable to any architecture, hyperparameter-free, implementable without requiring extra computational cost, and guarantee scale equilibrium for any dataset. Experiments showed that adopting scale equalizers consistently improved the mIoU index across various target datasets, including ADE20K, PASCAL VOC 2012, and Cityscapes, as well as various decoder choices, including UPerHead, PSPHead, ASPPHead, SepASPPHead, and FCNHead.
Code (1)
Tasks
DecoderSemantic SegmentationSimilar Papers 제목 키워드 기반
EqGAN: Feature Equalization Fusion for Few-shot Image Generation
Due to the absence of fine structure and texture information, existing fusion-based few-shot image generation methods suffer from unsatisfactory generation quality and diversity. To address this problem, we propose a nov…
DecoderDiversityGenerative Adversarial NetworkImage GenerationDFEN: Dual Feature Equalization Network for Medical Image Segmentation
Current methods for medical image segmentation primarily focus on extracting contextual feature information from the perspective of the whole image. While these methods have shown effective performance, none of them take…
Image SegmentationMedical Image SegmentationSemantic SegmentationRethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations
Deep encoder-decoder based CNNs have advanced image inpainting methods for hole filling. While existing methods recover structures and textures step-by-step in the hole regions, they typically use two encoder-decoders fo…
DecoderImage GenerationImage InpaintingAndroid Malware Detection Based on RGB Images and Multi-feature Fusion
With the widespread adoption of smartphones, Android malware has become a significant challenge in the field of mobile device security. Current Android malware detection methods often rely on feature engineering to const…
Android Malware DetectionEdge DetectionFeature Engineeringimage-classification+2Synergy or Rivalry? Glimpses of Regional Modernization and Public Service Equalization: A Case Study from China
For most developing countries, increasing the equalization of basic public services is widely recognized as an effective channel to improve people's sense of contentment. However, for many emerging economies like China, …