Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task
Not on the map. Why?
Abstract (arXiv)
The semantic segmentation (SS) task aims to create a dense classification by labeling at the pixel level each object present on images. Convolutional neural network (CNN) approaches have been widely used, and exhibited the best results in this task. However, the loss of spatial precision on the results is a main drawback that has not been solved. In this work, we propose to use a multi-task approach by complementing the semantic segmentation task with edge detection, semantic contour, and distance transform tasks. We propose that by sharing a common latent space, the complementary tasks can produce more robust representations that can enhance the semantic labels. We explore the influence of contour-based tasks on latent space, as well as their impact on the final results of SS. We demonstrate the effectiveness of learning in a multi-task setting for hourglass models in the Cityscapes, CamVid, and Freiburg Forest datasets by improving the state-of-the-art without any refinement post-processing.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 60 of its 102 references that are in the map. First posted on arXiv 28 May 2021.
Builds on
60 of 102 references.
References · 60
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2017Mask R-CNNcited by 7,277
- 2016Feature Pyramid Networks for Object Detectioncited by 5,036
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
- 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
- 2016Pyramid Scene Parsing Networkcited by 2,479
- 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
- 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
- 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
- 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
38 more
- 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
- 2017A Survey on Multi-Task Learningcited by 840
- 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 803
- 2018Path Aggregation Network for Instance Segmentationcited by 798
- 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 718
- 2015Holistically-Nested Edge Detectioncited by 592
- 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 576
- 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
- 2016Cross-stitch Networks for Multi-task Learningcited by 467
- 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 465
- 2017Deep Layer Aggregationcited by 436
- 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
- 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
- 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
- 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
- 2015Conditional Random Fields as Recurrent Neural Networkscited by 214
- 2020Hierarchical Multi-Scale Attention for Semantic Segmentationcited by 183
- 2015ParseNet: Looking Wider to See Bettercited by 177
- 2019UPSNet: A Unified Panoptic Segmentation Networkcited by 175
- 2017Understanding Convolution for Semantic Segmentationcited by 168
- 2019Gated-SCNN: Gated Shape CNNs for Semantic Segmentationcited by 166
- 2016The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentationcited by 122
- 2015Instance-aware Semantic Segmentation via Multi-task Network Cascadescited by 121
- 2018Graph-Based Global Reasoning Networkscited by 120
- 2020Learning to Branch for Multi-Task Learningcited by 115
- 2018Learning a Discriminative Feature Network for Semantic Segmentationcited by 114
- 2019Boundary-Aware Feature Propagation for Scene Segmentationcited by 107
- 2019DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentationcited by 100
- 2016MultiNet: Real-time Joint Semantic Reasoning for Autonomous Drivingcited by 90
- 2018Self-Supervised Model Adaptation for Multimodal Semantic Segmentationcited by 73
- 2019FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentationcited by 70
- 2016Learning to Refine Object Segmentscited by 67
- 2019GFF: Gated Fully Fusion for Semantic Segmentationcited by 57
- 2017MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Featurescited by 54
- 2016Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detectioncited by 38
- 2019Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregationcited by 34
- 2019Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotationscited by 32
- 2016A Survey of Semantic Segmentationcited by 30
50 most cited of 60 All 60 (JSON)
Built on by
Citing papers per year: 2022: 1.
1 paper.