Learning to Detect Semantic Boundaries with Image-level Class Labels
Not on the map. Why?
Abstract (arXiv)
This paper presents the first attempt to learn semantic boundary detection using image-level class labels as supervision. Our method starts by estimating coarse areas of object classes through attentions drawn by an image classification network. Since boundaries will locate somewhere between such areas of different classes, our task is formulated as a multiple instance learning (MIL) problem, where pixels on a line segment connecting areas of two different classes are regarded as a bag of boundary candidates. Moreover, we design a new neural network architecture that can learn to estimate semantic boundaries reliably even with uncertain supervision given by the MIL strategy. Our network is used to generate pseudo semantic boundary labels of training images, which are in turn used to train fully supervised models. The final model trained with our pseudo labels achieves an outstanding performance on the SBD dataset, where it is as competitive as some of previous arts trained with stronger supervision.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 38 of its 61 references that are in the map. First posted on arXiv 15 Dec 2022.
Builds on
38 of 61 references.
References · 38
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
- 2015Learning Deep Features for Discriminative Localizationcited by 2,430
- 2015Holistically-Nested Edge Detectioncited by 590
- 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
- 2019Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relationscited by 245
- 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 226
26 more
- 2017Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approachcited by 201
- 2016Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentationcited by 198
- 2016Wider or Deeper: Revisiting the ResNet Model for Visual Recognitioncited by 184
- 2015Weakly Supervised Deep Detection Networkscited by 183
- 2016Richer Convolutional Features for Edge Detectioncited by 141
- 2017Multiple Instance Detection Network with Online Instance Classifier Refinementcited by 117
- 2018Learning random-walk label propagation for weakly-supervised semantic segmentationcited by 101
- 2018Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Featurescited by 81
- 2018Weakly Supervised Instance Segmentation using Class Peak Responsecited by 74
- 2014Fast Edge Detection Using Structured Forestscited by 64
- 2020Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentationcited by 52
- 2014DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detectioncited by 50
- 2015Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transformcited by 46
- 2018Learning to Segment via Cut-and-Pastecited by 42
- 2016ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localizationcited by 39
- 2017Weakly Supervised Semantic Segmentation using Web-Crawled Videoscited by 38
- 2015Semantic Segmentation with Boundary Neural Fieldscited by 37
- 2017CASENet: Deep Category-Aware Semantic Edge Detectioncited by 37
- 2016Object Contour Detection with a Fully Convolutional Encoder-Decoder Networkcited by 34
- 2017Exploiting saliency for object segmentation from image level labelscited by 33
- 2019Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotationscited by 32
- 2015High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and its Applications to High-Level Visioncited by 24
- 2018Simultaneous Edge Alignment and Learningcited by 22
- 2019Dynamic Feature Fusion for Semantic Edge Detectioncited by 16
- 2015Weakly Supervised Object Boundariescited by 4
- 2019Boundary Cues for 3D Object Shape Recoverycited by 4
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.