# Exploiting saliency for object segmentation from image level labels

arXiv: https://arxiv.org/abs/1701.08261 · HTML: https://mlsanity.com/paper/1701.08261/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jan 2017.

## Built on by (most cited first, 30 of 33)

- [Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2105.08965/) (2021)
- [Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.14581/) (2021)
- [One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation](https://mlsanity.com/paper/2104.02246/) (2021)
- [Weakly Supervised Semantic Segmentation using Out-of-Distribution Data](https://mlsanity.com/paper/2203.03860/) (2022)
- [A Closer Look at Self-training for Zero-Label Semantic Segmentation](https://mlsanity.com/paper/2104.11692/) (2021)
- [Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation](https://mlsanity.com/paper/2210.17400/) (2022)
- [Incremental Learning in Semantic Segmentation from Image Labels](https://mlsanity.com/paper/2112.01882/) (2021)
- [Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement](https://mlsanity.com/paper/2109.09477/) (2021)
- [Unsupervised Foreground Extraction via Deep Region Competition](https://mlsanity.com/paper/2110.15497/) (2021)
- [From colouring-in to pointillism: revisiting semantic segmentation supervision](https://mlsanity.com/paper/2210.14142/) (2022)
- [Salient Objects in Clutter](https://mlsanity.com/paper/2105.03053/) (2021)
- [Weakly supervised segmentation with cross-modality equivariant constraints](https://mlsanity.com/paper/2104.02488/) (2021)
- [Sketch2Saliency: Learning to Detect Salient Objects from Human Drawings](https://mlsanity.com/paper/2303.11502/) (2023)
- [Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Mining](https://mlsanity.com/paper/2111.15210/) (2021)
- [Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation](https://mlsanity.com/paper/2207.09084/) (2022)
- [Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation](https://mlsanity.com/paper/2108.07413/) (2021)
- [On Label Granularity and Object Localization](https://mlsanity.com/paper/2207.10225/) (2022)
- [Urban Scene Semantic Segmentation with Low-Cost Coarse Annotation](https://mlsanity.com/paper/2212.07911/) (2022)
- [Interaction-aware Joint Attention Estimation Using People Attributes](https://mlsanity.com/paper/2308.05382/) (2023)
- [Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2304.09059/) (2023)
- [Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization](https://mlsanity.com/paper/2305.15354/) (2023)
- [Modeling the Background for Incremental and Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2201.13338/) (2022)
- [Learning to Detect Semantic Boundaries with Image-level Class Labels](https://mlsanity.com/paper/2212.07579/) (2022)
- [Simpler Does It: Generating Semantic Labels with Objectness Guidance](https://mlsanity.com/paper/2110.10335/) (2021)
- [SketchYourSeg: Mask-Free Subjective Image Segmentation via Freehand Sketches](https://mlsanity.com/paper/2501.16022/) (2025)
- [Maximize the Exploration of Congeneric Semantics for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2110.03982/) (2021)
- [A General Divergence Modeling Strategy for Salient Object Detection](https://mlsanity.com/paper/2111.11827/) (2021)
- [WegFormer: Transformers for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.08421/) (2022)
- [Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes](https://mlsanity.com/paper/2206.01203/) (2022)
- [You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding](https://mlsanity.com/paper/2303.14727/) (2023)

## 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.