# Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation

arXiv: https://arxiv.org/abs/1707.05821 · HTML: https://mlsanity.com/paper/1707.05821/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2017.

## Built on by (most cited first, 21 of 21)

- [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)
- [Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2107.11787/) (2021)
- [Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.01795/) (2021)
- [Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.09653/) (2022)
- [Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2305.05803/) (2023)
- [Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.07246/) (2021)
- [Incremental Learning in Semantic Segmentation from Image Labels](https://mlsanity.com/paper/2112.01882/) (2021)
- [Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds](https://mlsanity.com/paper/2203.16045/) (2022)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [Saliency Guided Inter- and Intra-Class Relation Constraints for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2206.09554/) (2022)
- [Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation](https://mlsanity.com/paper/2108.07413/) (2021)
- [Towards Single Stage Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2106.10309/) (2021)
- [Learning structure-aware semantic segmentation with image-level supervision](https://mlsanity.com/paper/2104.07216/) (2021)
- [Improving Disease Classification Performance and Explainability of Deep Learning Models in Radiology with Heatmap Generators](https://mlsanity.com/paper/2207.00157/) (2022)
- [Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2304.09059/) (2023)
- [Auxiliary Tasks Enhanced Dual-affinity Learning for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2403.01156/) (2024)
- [Simpler Does It: Generating Semantic Labels with Objectness Guidance](https://mlsanity.com/paper/2110.10335/) (2021)
- [MECPformer: Multi-estimations Complementary Patch with CNN-Transformers for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2303.10689/) (2023)
- [P-NOC: adversarial training of CAM generating networks for robust weakly supervised semantic segmentation priors](https://mlsanity.com/paper/2305.12522/) (2023)
- [Dual-Augmented Transformer Network for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2310.00307/) (2023)

## Abstract (arXiv)

We propose an approach to discover class-specific pixels for the weakly-supervised semantic segmentation task. We show that properly combining saliency and attention maps allows us to obtain reliable cues capable of significantly boosting the performance. First, we propose a simple yet powerful hierarchical approach to discover the class-agnostic salient regions, obtained using a salient object detector, which otherwise would be ignored. Second, we use fully convolutional attention maps to reliably localize the class-specific regions in a given image. We combine these two cues to discover class-specific pixels which are then used as an approximate ground truth for training a CNN. While solving the weakly supervised semantic segmentation task, we ensure that the image-level classification task is also solved in order to enforce the CNN to assign at least one pixel to each object present in the image. Experimentally, on the PASCAL VOC12 val and test sets, we obtain the mIoU of 60.8% and 61.9%, achieving the performance gains of 5.1% and 5.2% compared to the published state-of-the-art results. The code is made publicly available.