mlsanityData to 7 Oct 2026

Exploiting saliency for object segmentation from image level labels

arXiv 1701.08261 ↗First posted 28 Jan 2017cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

There have been remarkable improvements in the semantic labelling task in the recent years. However, the state of the art methods rely on large-scale pixel-level annotations. This paper studies the problem of training a pixel-wise semantic labeller network from image-level annotations of the present object classes. Recently, it has been shown that high quality seeds indicating discriminative object regions can be obtained from image-level labels. Without additional information, obtaining the full extent of the object is an inherently ill-posed problem due to co-occurrences. We propose using a saliency model as additional information and hereby exploit prior knowledge on the object extent and image statistics. We show how to combine both information sources in order to recover 80% of the fully supervised performance - which is the new state of the art in weakly supervised training for pixel-wise semantic labelling. The code is available at https://goo.gl/KygSeb.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Jan 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 14; 2022: 10; 2023: 7; 2024: 1; 2025: 1.

33 papers.

Sort:

By area:

  1. 2021Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentationcited by 127
  2. 2021Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentationcited by 95
  3. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  4. 2022Weakly Supervised Semantic Segmentation using Out-of-Distribution Datacited by 58
  5. 2021A Closer Look at Self-training for Zero-Label Semantic Segmentationcited by 57
  6. 2022Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentationcited by 41
  7. 2021Incremental Learning in Semantic Segmentation from Image Labelscited by 39
  8. 2021Unsupervised Foreground Extraction via Deep Region Competitioncited by 26
  9. 2021Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinementcited by 25
  10. 2022From colouring-in to pointillism: revisiting semantic segmentation supervisioncited by 22
  11. 2021Salient Objects in Cluttercited by 19
  12. 2021Weakly supervised segmentation with cross-modality equivariant constraintscited by 18
21 more
  1. 2023Sketch2Saliency: Learning to Detect Salient Objects from Human Drawingscited by 17
  2. 2021Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Miningcited by 15
  3. 2022Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentationcited by 15
  4. 2021Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentationcited by 13
  5. 2022On Label Granularity and Object Localizationcited by 12
  6. 2022Urban Scene Semantic Segmentation with Low-Cost Coarse Annotationcited by 11
  7. 2023Interaction-aware Joint Attention Estimation Using People Attributescited by 6
  8. 2023Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentationcited by 3
  9. 2023Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localizationcited by 3
  10. 2022Modeling the Background for Incremental and Weakly-Supervised Semantic Segmentationcited by 2
  11. 2022Learning to Detect Semantic Boundaries with Image-level Class Labelscited by 2
  12. 2021Simpler Does It: Generating Semantic Labels with Objectness Guidancecited by 1
  13. 2025SketchYourSeg: Mask-Free Subjective Image Segmentation via Freehand Sketchescited by 1
  14. 2021Maximize the Exploration of Congeneric Semantics for Weakly Supervised Semantic Segmentationcited by 0
  15. 2021A General Divergence Modeling Strategy for Salient Object Detectioncited by 0
  16. 2022WegFormer: Transformers for Weakly Supervised Semantic Segmentationcited by 0
  17. 2022Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxescited by 0
  18. 2023You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understandingcited by 0
  19. 2023P-NOC: adversarial training of CAM generating networks for robust weakly supervised semantic segmentation priorscited by 0
  20. 2023Learning Semantic Segmentation with Query Points Supervision on Aerial Imagescited by 0
  21. 2024Enhancing Weakly Supervised Semantic Segmentation with Multi-modal Foundation Models: An End-to-End Approachcited by 0