The Devil is in the Decoder
Zbigniew Wojna,Vittorio Ferrari,Sergio Guadarrama,Nathan Silberman,Liang-Chieh Chen,Alireza Fathi,Jasper Uijlings +6 more
TLDR
In this paper, the authors present an extensive comparison of a variety of decoders for pixel-wise prediction tasks and identify two decoder types which give a consistently high performance.Abstract:
Many machine vision applications require predictions for every pixel of the input image (for example semantic segmentation, boundary detection). Models for such problems usually consist of encoders which decreases spatial resolution while learning a high-dimensional representation, followed by decoders who recover the original input resolution and result in low-dimensional predictions. While encoders have been studied rigorously, relatively few studies address the decoder side. Therefore this paper presents an extensive comparison of a variety of decoders for a variety of pixel-wise prediction tasks. Our contributions are: (1) Decoders matter: we observe significant variance in results between different types of decoders on various problems. (2) We introduce a novel decoder: bilinear additive upsampling. (3) We introduce new residual-like connections for decoders. (4) We identify two decoder types which give a consistently high performance.read more
Citations
More filters
Book ChapterDOI
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
TL;DR: This work extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries and applies the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network.
Posted Content
Deep High-Resolution Representation Learning for Visual Recognition
Jingdong Wang,Ke Sun,Tianheng Cheng,Borui Jiang,Chaorui Deng,Yang Zhao,Dong Liu,Yadong Mu,Mingkui Tan,Xinggang Wang,Wenyu Liu,Bin Xiao +11 more
TL;DR: The superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, is shown, suggesting that the HRNet is a stronger backbone for computer vision problems.
Posted Content
High-Resolution Representations for Labeling Pixels and Regions
Ke Sun,Yang Zhao,Borui Jiang,Tianheng Cheng,Bin Xiao,Dong Liu,Yadong Mu,Xinggang Wang,Wenyu Liu,Jingdong Wang +9 more
TL;DR: A simple modification is introduced to augment the high-resolution representation by aggregating the (upsampled) representations from all the parallel convolutions rather than only the representation from thehigh-resolution convolution, which leads to stronger representations, evidenced by superior results.
Proceedings ArticleDOI
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
TL;DR: HigherHRNet is presented, a novel bottom-up human pose estimation method for learning scale-aware representations using high-resolution feature pyramids that surpasses all top-down methods on CrowdPose test and achieves new state-of-the-art result on COCO test-dev, suggesting its robustness in crowded scene.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Journal ArticleDOI
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.
Posted Content
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Posted Content
Rethinking the Inception Architecture for Computer Vision
TL;DR: This work is exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization.
Posted Content
Fully Convolutional Networks for Semantic Segmentation
TL;DR: It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation.