# Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching

arXiv: https://arxiv.org/abs/2112.09459 · HTML: https://mlsanity.com/paper/2112.09459/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 50 of its 87 references that are in the map.
- First posted on arXiv 17 Dec 2021.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 50)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [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)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/1803.10464/) (2018)
- [Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2004.04581/) (2020)
- [What's the Point: Semantic Segmentation with Point Supervision](https://mlsanity.com/paper/1506.02106/) (2015)
- [Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations](https://mlsanity.com/paper/1904.05044/) (2019)
- [Causal Intervention for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2009.12547/) (2020)
- [Learning Deep Representations with Probabilistic Knowledge Transfer](https://mlsanity.com/paper/1803.10837/) (2018)
- [Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation](https://mlsanity.com/paper/1603.06098/) (2016)
- [Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation](https://mlsanity.com/paper/1502.02734/) (2015)
- [Wider or Deeper: Revisiting the ResNet Model for Visual Recognition](https://mlsanity.com/paper/1611.10080/) (2016)
- [Weakly-Supervised Semantic Segmentation via Sub-category Exploration](https://mlsanity.com/paper/2008.01183/) (2020)
- [Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2007.01947/) (2020)
- [Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.08896/) (2021)
- [Salient Object Detection: A Benchmark](https://mlsanity.com/paper/1501.02741/) (2015)
- [On Regularized Losses for Weakly-supervised CNN Segmentation](https://mlsanity.com/paper/1803.09569/) (2018)
- [BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation](https://mlsanity.com/paper/2103.08907/) (2021)
- [Snapshot Distillation: Teacher-Student Optimization in One Generation](https://mlsanity.com/paper/1812.00123/) (2018)
- [Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.14581/) (2021)

## Built on by (most cited first, 19 of 19)

- [GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding](https://mlsanity.com/paper/2311.11863/) (2023)
- [VDG: Vision-Only Dynamic Gaussian for Driving Simulation](https://mlsanity.com/paper/2406.18198/) (2024)
- [Image Augmentation Agent for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2412.20439/) (2024)
- [DAWN: Domain-Adaptive Weakly Supervised Nuclei Segmentation via Cross-Task Interactions](https://mlsanity.com/paper/2404.14956/) (2024)
- [Federated Momentum Contrastive Clustering](https://mlsanity.com/paper/2206.05093/) (2022)
- [SASFormer: Transformers for Sparsely Annotated Semantic Segmentation](https://mlsanity.com/paper/2212.02019/) (2022)
- [Weakly Semi-Supervised Detection in Lung Ultrasound Videos](https://mlsanity.com/paper/2308.04463/) (2023)
- [Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets](https://mlsanity.com/paper/2408.12489/) (2024)
- [Uncertainty Guided Refinement for Fine-Grained Salient Object Detection](https://mlsanity.com/paper/2504.09666/) (2025)
- [ProCNS: Progressive Prototype Calibration and Noise Suppression for Weakly-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2401.14074/) (2024)
- [Masked Collaborative Contrast for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2305.08491/) (2023)
- [Weakly-supervised Semantic Segmentation via Dual-stream Contrastive Learning of Cross-image Contextual Information](https://mlsanity.com/paper/2405.04913/) (2024)
- [A Point-Neighborhood Learning Framework for Nasal Endoscope Image Segmentation](https://mlsanity.com/paper/2405.20044/) (2024)
- [Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2408.02039/) (2024)
- [Mitigating Spurious Correlations in Weakly Supervised Semantic Segmentation via Cross-architecture Consistency Regularization](https://mlsanity.com/paper/2507.21959/) (2025)
- [Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance](https://mlsanity.com/paper/2602.10549/) (2026)
- [ARTEMIS: Agent-guided Reliability-aware Temporal Mask Evolution for Imperfectly Supervised Video Polyp Segmentation](https://mlsanity.com/paper/2606.20161/) (2026)
- [PolSAM: Polarimetric Scattering Mechanism Informed Segment Anything Model](https://mlsanity.com/paper/2412.12737/) (2024)
- [DiCLIP: Diffusion Model Enhances CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2605.04593/) (2026)

## Abstract (arXiv)

Current weakly supervised semantic segmentation (WSSS) frameworks usually contain the separated mask-refinement model and the main semantic region mining model. These approaches would contain redundant feature extraction backbones and biased learning objectives, making them computational complex yet sub-optimal to addressing the WSSS task. To solve this problem, this paper establishes a compact learning framework that embeds the classification and mask-refinement components into a unified deep model. With the shared feature extraction backbone, our model is able to facilitate knowledge sharing between the two components while preserving a low computational complexity. To encourage high-quality knowledge interaction, we propose a novel alternative self-dual teaching (ASDT) mechanism. Unlike the conventional distillation strategy, the knowledge of the two teacher branches in our model is alternatively distilled to the student branch by a Pulse Width Modulation (PWM), which generates PW wave-like selection signal to guide the knowledge distillation process. In this way, the student branch can help prevent the model from falling into local minimum solutions caused by the imperfect knowledge provided of either teacher branch. Comprehensive experiments on the PASCAL VOC 2012 and COCO-Stuff 10K demonstrate the effectiveness of the proposed alternative self-dual teaching mechanism as well as the new state-of-the-art performance of our approach.