TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency
Not on the map. Why?
Abstract (arXiv)
This paper addresses the task of semantic segmentation in computer vision, aiming to achieve precise pixel-wise classification. We investigate the joint training of models for semantic edge detection and semantic segmentation, which has shown promise. However, implicit cross-task consistency learning in multi-task networks is limited. To address this, we propose a novel "decoupled cross-task consistency loss" that explicitly enhances cross-task consistency. Our semantic segmentation network, TriangleNet, achieves a substantial 2.88% improvement over the Baseline in mean Intersection over Union (mIoU) on the Cityscapes test set. Notably, TriangleNet operates at 77.4% mIoU/46.2 FPS on Cityscapes, showcasing real-time inference capabilities at full resolution. With multi-scale inference, performance is further enhanced to 77.8%. Furthermore, TriangleNet consistently outperforms the Baseline on the FloodNet dataset, demonstrating its robust generalization capabilities. The proposed method underscores the significance of multi-task learning and explicit cross-task consistency enhancement for advancing semantic segmentation and highlights the potential of multitasking in real-time semantic segmentation.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 67 of its 85 references that are in the map. First posted on arXiv 11 Oct 2022.
Builds on
67 of 85 references.
References · 67
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2015Distilling the Knowledge in a Neural Networkcited by 10,324
- 2017Mask R-CNNcited by 7,277
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2016Feature Pyramid Networks for Object Detectioncited by 5,036
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
- 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
38 more
- 2017Non-local Neural Networkscited by 2,293
- 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
- 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
- 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
- 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
- 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
- 2018Dual Attention Network for Scene Segmentationcited by 1,003
- 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 803
- 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
- 2020Image Segmentation Using Deep Learning: A Surveycited by 660
- 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
- 2015Holistically-Nested Edge Detectioncited by 592
- 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 554
- 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 375
- 2017Dilated Residual Networkscited by 294
- 2020BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentationcited by 294
- 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
- 2019Structured Knowledge Distillation for Dense Predictioncited by 279
- 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
- 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
- 2015Conditional Random Fields as Recurrent Neural Networkscited by 214
- 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
- 2020FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understandingcited by 181
- 2019Gated-SCNN: Gated Shape CNNs for Semantic Segmentationcited by 166
- 2018ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentationcited by 133
- 2021Rethinking BiSeNet For Real-time Semantic Segmentationcited by 124
- 2019Boundary-Aware Feature Propagation for Scene Segmentationcited by 107
- 2019Knowledge Adaptation for Efficient Semantic Segmentationcited by 105
- 2020Robust Learning Through Cross-Task Consistencycited by 105
- 2018ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Networkcited by 90
- 2019FasterSeg: Searching for Faster Real-time Semantic Segmentationcited by 73
- 2020The Edge of Depth: Explicit Constraints between Segmentation and Depthcited by 72
- 2019FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentationcited by 70
- 2021SwiftNet: Real-time Video Object Segmentationcited by 67
- 2020HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentationcited by 66
- 2019Dual Graph Convolutional Network for Semantic Segmentationcited by 59
- 2018Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotationscited by 51
- 2020Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contextscited by 51
50 most cited of 67 All 67 (JSON)
Built on by
Citing papers per year: 2025: 1.
1 paper.