# Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation

arXiv: https://arxiv.org/abs/2104.00905 · HTML: https://mlsanity.com/paper/2104.00905/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 70 references that are in the map.
- First posted on arXiv 2 Apr 2021.

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [Dynamic Few-Shot Visual Learning without Forgetting](https://mlsanity.com/paper/1804.09458/) (2018)
- [ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1604.05144/) (2016)
- [Training Deep Neural Networks on Noisy Labels with Bootstrapping](https://mlsanity.com/paper/1412.6596/) (2014)
- [Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/1803.10464/) (2018)
- [What's the Point: Semantic Segmentation with Point Supervision](https://mlsanity.com/paper/1506.02106/) (2015)
- [BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1503.01640/) (2015)
- [Simple Does It: Weakly Supervised Instance and Semantic Segmentation](https://mlsanity.com/paper/1603.07485/) (2016)
- [Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach](https://mlsanity.com/paper/1703.08448/) (2017)
- [Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation](https://mlsanity.com/paper/1603.06098/) (2016)
- [Deeply supervised salient object detection with short connections](https://mlsanity.com/paper/1611.04849/) (2016)
- [Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation](https://mlsanity.com/paper/1502.02734/) (2015)
- [Tell Me Where to Look: Guided Attention Inference Network](https://mlsanity.com/paper/1802.10171/) (2018)
- [FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference](https://mlsanity.com/paper/1902.10421/) (2019)

## Built on by (most cited first, 30 of 41)

- [Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast](https://mlsanity.com/paper/2110.07110/) (2021)
- [UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning](https://mlsanity.com/paper/2203.14542/) (2022)
- [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)
- [A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction](https://mlsanity.com/paper/2207.01223/) (2022)
- [ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2210.05944/) (2022)
- [Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2112.08996/) (2021)
- [Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching](https://mlsanity.com/paper/2112.09459/) (2021)
- [Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling](https://mlsanity.com/paper/2202.04812/) (2022)
- [Weakly-Supervised Audio-Visual Segmentation](https://mlsanity.com/paper/2311.15080/) (2023)
- [DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2403.11184/) (2024)
- [Orthogonal Annotation Benefits Barely-supervised Medical Image Segmentation](https://mlsanity.com/paper/2303.13090/) (2023)
- [Adaptive Superpixel for Active Learning in Semantic Segmentation](https://mlsanity.com/paper/2303.16817/) (2023)
- [ALEX: Towards Effective Graph Transfer Learning with Noisy Labels](https://mlsanity.com/paper/2309.14673/) (2023)
- [Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals](https://mlsanity.com/paper/2404.16818/) (2024)
- [GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation](https://mlsanity.com/paper/2112.02841/) (2021)
- [In the Picture: Medical Imaging Datasets, Artifacts, and their Living Review](https://mlsanity.com/paper/2501.10727/) (2025)
- [Uncovering the Inner Workings of STEGO for Safe Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2304.07314/) (2023)
- [3D Medical Image Segmentation with Sparse Annotation via Cross-Teaching between 3D and 2D Networks](https://mlsanity.com/paper/2307.16256/) (2023)
- [How to Efficiently Annotate Images for Best-Performing Deep Learning Based Segmentation Models: An Empirical Study with Weak and Noisy Annotations and Segment Anything Model](https://mlsanity.com/paper/2312.10600/) (2023)
- [Dynamic Feature Regularized Loss for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2108.01296/) (2021)
- [Background-aware Classification Activation Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2112.14379/) (2021)
- [Exploiting Shape Cues for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2208.04286/) (2022)
- [Weakly Supervised Semantic Segmentation for Driving Scenes](https://mlsanity.com/paper/2312.13646/) (2023)
- [Exploring Pixel-level Self-supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2112.05351/) (2021)
- [MonoBox: Tightness-free Box-supervised Polyp Segmentation using Monotonicity Constraint](https://mlsanity.com/paper/2404.01188/) (2024)
- [Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets](https://mlsanity.com/paper/2408.12489/) (2024)
- [A Language-Guided Benchmark for Weakly Supervised Open Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2302.14163/) (2023)
- [All-pairs Consistency Learning for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2308.04321/) (2023)
- [Tendency-driven Mutual Exclusivity for Weakly Supervised Incremental Semantic Segmentation](https://mlsanity.com/paper/2404.11981/) (2024)

## Abstract (arXiv)

We address the problem of weakly-supervised semantic segmentation (WSSS) using bounding box annotations. Although object bounding boxes are good indicators to segment corresponding objects, they do not specify object boundaries, making it hard to train convolutional neural networks (CNNs) for semantic segmentation. We find that background regions are perceptually consistent in part within an image, and this can be leveraged to discriminate foreground and background regions inside object bounding boxes. To implement this idea, we propose a novel pooling method, dubbed background-aware pooling (BAP), that focuses more on aggregating foreground features inside the bounding boxes using attention maps. This allows to extract high-quality pseudo segmentation labels to train CNNs for semantic segmentation, but the labels still contain noise especially at object boundaries. To address this problem, we also introduce a noise-aware loss (NAL) that makes the networks less susceptible to incorrect labels. Experimental results demonstrate that learning with our pseudo labels already outperforms state-of-the-art weakly- and semi-supervised methods on the PASCAL VOC 2012 dataset, and the NAL further boosts the performance.