mlsanityData to 7 Oct 2026

Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation

arXiv 2203.10739 ↗First posted 21 Mar 2022cs.CVcited by 47

Not on the map. Why?

Abstract (arXiv)

Sparsely annotated semantic segmentation (SASS) aims to train a segmentation network with coarse-grained (i.e., point-, scribble-, and block-wise) supervisions, where only a small proportion of pixels are labeled in each image. In this paper, we propose a novel tree energy loss for SASS by providing semantic guidance for unlabeled pixels. The tree energy loss represents images as minimum spanning trees to model both low-level and high-level pair-wise affinities. By sequentially applying these affinities to the network prediction, soft pseudo labels for unlabeled pixels are generated in a coarse-to-fine manner, achieving dynamic online self-training. The tree energy loss is effective and easy to be incorporated into existing frameworks by combining it with a traditional segmentation loss. Compared with previous SASS methods, our method requires no multistage training strategies, alternating optimization procedures, additional supervised data, or time-consuming post-processing while outperforming them in all SASS settings. Code is available at https://github.com/megvii-research/TreeEnergyLoss.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). Builds on 28 of its 46 references that are in the map. First posted on arXiv 21 Mar 2022.

Builds on

28 of 46 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2017Non-local Neural Networkscited by 2,290
  7. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  8. 2015Holistically-Nested Edge Detectioncited by 590
  9. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  10. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
  11. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
  12. 2019Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentationcited by 258
16 more
  1. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  2. 2019High-Resolution Representations for Labeling Pixels and Regionscited by 211
  3. 2020BoxInst: High-Performance Instance Segmentation with Box Annotationscited by 150
  4. 2018On Regularized Losses for Weakly-supervised CNN Segmentationcited by 121
  5. 2018Normalized Cut Loss for Weakly-supervised CNN Segmentationcited by 112
  6. 2018Learning random-walk label propagation for weakly-supervised semantic segmentationcited by 101
  7. 2022Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentationcited by 64
  8. 2021Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentationcited by 47
  9. 2021Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learningcited by 43
  10. 2019Gated CRF Loss for Weakly Supervised Semantic Image Segmentationcited by 40
  11. 2018Weakly Supervised Scene Parsing with Point-based Distance Metric Learningcited by 33
  12. 2019Learnable Tree Filter for Structure-preserving Feature Transformcited by 25
  13. 2021Scribble-Supervised Semantic Segmentation by Uncertainty Reduction on Neural Representation and Self-Supervision on Neural Eigenspacecited by 19
  14. 2021Seminar Learning for Click-Level Weakly Supervised Semantic Segmentationcited by 14
  15. 2020Rethinking Learnable Tree Filter for Generic Feature Transformcited by 10
  16. 2021WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotationscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 12; 2024: 13; 2025: 7; 2026: 11.

47 papers.

Sort:

By area:

  1. 2023Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Groupingcited by 92
  2. 2022Box-supervised Instance Segmentation with Level Set Evolutioncited by 41
  3. 2023Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transportcited by 23
  4. 2022Box2Mask: Box-supervised Instance Segmentation via Level-set Evolutioncited by 22
  5. 2024SAM-COD: SAM-guided Unified Framework for Weakly-Supervised Camouflaged Object Detectioncited by 22
  6. 2023LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillationcited by 18
  7. 2024Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentationcited by 14
  8. 2023Pixel Difference Convolutional Network for RGB-D Semantic Segmentationcited by 13
  9. 2024Learning Camouflaged Object Detection from Noisy Pseudo Labelcited by 12
  10. 2023Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detectioncited by 9
  11. 2024Label-efficient Semantic Scene Completion with Scribble Annotationscited by 9
  12. 2023Scribble-based 3D Multiple Abdominal Organ Segmentation via Triple-branch Multi-dilated Network with Pixel- and Class-wise Consistencycited by 7
35 more
  1. 2023Label-efficient Segmentation via Affinity Propagationcited by 7
  2. 2022SASFormer: Transformers for Sparsely Annotated Semantic Segmentationcited by 6
  3. 2024FedLPPA: Learning Personalized Prompt and Aggregation for Federated Weakly-supervised Medical Image Segmentationcited by 6
  4. 2024Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Labelcited by 6
  5. 2025SCALER: SAM-Enhanced Collaborative Learning for Label-Deficient Concealed Object Segmentationcited by 6
  6. 2023ScribbleGen: Generative Data Augmentation Improves Scribble-supervised Semantic Segmentationcited by 5
  7. 2023Unifying and Personalizing Weakly-supervised Federated Medical Image Segmentation via Adaptive Representation and Aggregationcited by 4
  8. 2024Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasetscited by 4
  9. 2025Segment Concealed Objects with Incomplete Supervisioncited by 4
  10. 2023A Language-Guided Benchmark for Weakly Supervised Open Vocabulary Semantic Segmentationcited by 3
  11. 2024ProCNS: Progressive Prototype Calibration and Noise Suppression for Weakly-Supervised Medical Image Segmentationcited by 3
  12. 2024Towards Real Zero-Shot Camouflaged Object Segmentation without Camouflaged Annotationscited by 3
  13. 2025Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentationcited by 3
  14. 2023Boosting Weakly-Supervised Image Segmentation via Representation, Transform, and Compensatorcited by 2
  15. 2025Soft Self-labeling and Potts Relaxations for Weakly-Supervised Segmentationcited by 2
  16. 2025Segment Anything Across Shots: A Method and Benchmarkcited by 2
  17. 2022RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised Semantic Segmentation across Single- and Multi-Stage Frameworkscited by 1
  18. 2023Land Cover Segmentation with Sparse Annotations from Sentinel-2 Imagerycited by 1
  19. 2024Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect Labelscited by 1
  20. 2024Global High Categorical Resolution Land Cover Mapping via Weak Supervisioncited by 1
  21. 2025Deep Learning for Crack Detection: A Review of Learning Paradigms, Generalizability, and Datasetscited by 1
  22. 2026Weakly Supervised Segmentation as Semantic-Based Regularizationcited by 1
  23. 2026Weakly Supervised Camouflaged Object Detection Based on the SAM Model and Mask Guidancecited by 1
  24. 2026ARTEMIS: Agent-guided Reliability-aware Temporal Mask Evolution for Imperfectly Supervised Video Polyp Segmentationcited by 1
  25. 2024Competing for pixels: a self-play algorithm for weakly-supervised segmentationcited by 0
  26. 2024Size Aware Cross-shape Scribble Supervision for Medical Image Segmentationcited by 0
  27. 2025LC-SLab -- An object-based deep learning framework for large-scale land cover classification from satellite imagery and sparse in-situ labelscited by 0
  28. 2026SAPNet++: Evolving Point-Prompted Instance Segmentation with Semantic and Spatial Awarenesscited by 0
  29. 2026Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentationcited by 0
  30. 2026Do Instance Priors Help Weakly Supervised Semantic Segmentation?cited by 0
  31. 2026LIE: LiDAR-only HD Map Construction with Intensity Enhancement via Online Knowledge Distillationcited by 0
  32. 2026iSAGE: A Human-in-the-Loop Framework for Remote Sensing Semantic Segmentation via Sparse Point Supervisioncited by 0
  33. 2026APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigmscited by 0
  34. 2026TACoS: Weakly Supervised Learning of Two-Dimensional Materials from Scribble Annotations to Precise Segmentationcited by 0
  35. 2026A Unified Variational Framework for Deep Weakly Supervised Image Segmentationcited by 0