paper-with-me

홈 › Papers

Learning a Discriminative Feature Network for Semantic Segmentation

2018-04-25 · CVPR 2018 6 · Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang

Most existing methods of semantic segmentation still suffer from two aspects of challenges: intra-class inconsistency and inter-class indistinction. To tackle these two problems, we propose a Discriminative Feature Network (DFN), which contains two sub-networks: Smooth Network and Border Network. Specifically, to handle the intra-class inconsistency problem, we specially design a Smooth Network with Channel Attention Block and global average pooling to select the more discriminative features. Furthermore, we propose a Border Network to make the bilateral features of boundary distinguishable with deep semantic boundary supervision. Based on our proposed DFN, we achieve state-of-the-art performance 86.2% mean IOU on PASCAL VOC 2012 and 80.3% mean IOU on Cityscapes dataset.

📄 PDF Abstract BibTeX arXiv:1804.09337

Code (3)

YuhuiMa/DFN-tensorflow tf
akinoriosamura/TorchSeg-mirror pytorch
ycszen/TorchSeg pytorch

Tasks

Semantic SegmentationThermal Image Segmentation

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
Residual Connection 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Similar Papers 제목 키워드 기반

A Gift from the Integration of Discriminative and Diffusion-based Generative Learning: Boundary Refinement Remote Sensing Semantic Segmentation

2025-07-02 · Hao Wang, Keyan Hu, Xin Guo, Haifeng Li 외 arxiv

Remote sensing semantic segmentation must address both what the ground objects are within an image and where they are located. Consequently, segmentation models must ensure not only the semantic correctness of large-scal…

Semantic Segmentation

Recursive Training for Zero-Shot Semantic Segmentation

2021-02-26 · Ce Wang, Moshiur Farazi, Nick Barnes

General purpose semantic segmentation relies on a backbone CNN network to extract discriminative features that help classify each image pixel into a 'seen' object class (ie., the object classes available during training)…

SegmentationSemantic SegmentationZero-Shot Semantic Segmentation

GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models

2022-10-05 · Chen Liang, Wenguan Wang, Jiaxu Miao, Yi Yang

Prevalent semantic segmentation solutions are, in essence, a dense discriminative classifier of p(class|pixel feature). Though straightforward, this de facto paradigm neglects the underlying data distribution p(pixel fea…

Out-of-Distribution DetectionSegmentationSemantic Segmentation

ELKPPNet: An Edge-aware Neural Network with Large Kernel Pyramid Pooling for Learning Discriminative Features in Semantic Segmentation

2019-06-27 · Xianwei Zheng, Linxi Huan, Hanjiang Xiong, Jianya Gong

Semantic segmentation has been a hot topic across diverse research fields. Along with the success of deep convolutional neural networks, semantic segmentation has made great achievements and improvements, in terms of bot…

DecoderScene ParsingSegmentationSemantic Segmentation

Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation

2024-08-04 · Ye Du, Zehua Fu, Qingjie Liu

Recent attention has been devoted to the pursuit of learning semantic segmentation models exclusively from image tags, a paradigm known as image-level Weakly Supervised Semantic Segmentation (WSSS). Existing attempts ado…

Domain AdaptationObjectSegmentationSemantic Segmentation+2