mlsanityData to 7 Oct 2026

Puzzle-CAM: Improved localization via matching partial and full features

arXiv 2101.11253 ↗First posted 27 Jan 2021cs.CV cs.AIcited by 37

Not on the map. Why?

Abstract (arXiv)

Weakly-supervised semantic segmentation (WSSS) is introduced to narrow the gap for semantic segmentation performance from pixel-level supervision to image-level supervision. Most advanced approaches are based on class activation maps (CAMs) to generate pseudo-labels to train the segmentation network. The main limitation of WSSS is that the process of generating pseudo-labels from CAMs that use an image classifier is mainly focused on the most discriminative parts of the objects. To address this issue, we propose Puzzle-CAM, a process that minimizes differences between the features from separate patches and the whole image. Our method consists of a puzzle module and two regularization terms to discover the most integrated region in an object. Puzzle-CAM can activate the overall region of an object using image-level supervision without requiring extra parameters. % In experiments, Puzzle-CAM outperformed previous state-of-the-art methods using the same labels for supervision on the PASCAL VOC 2012 test dataset. In experiments, Puzzle-CAM outperformed previous state-of-the-art methods using the same labels for supervision on the PASCAL VOC 2012 dataset. Code associated with our experiments is available at https://github.com/OFRIN/PuzzleCAM.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Builds on 13 of its 18 references that are in the map. First posted on arXiv 27 Jan 2021.

Builds on

13 of 18 references.

References · 13

  1. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  2. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  3. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  4. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  5. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 552
  6. 2020ResNeSt: Split-Attention Networkscited by 445
  7. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
  8. 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
  9. 2020Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentationcited by 299
  10. 2019Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relationscited by 245
  11. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 226
  12. 2019FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inferencecited by 162
1 more
  1. 2018Self-Erasing Network for Integral Object Attentioncited by 95

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 14; 2023: 10; 2024: 5; 2025: 2; 2026: 1.

37 papers.

Sort:

By area:

  1. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 529
  2. 2021Scaling Open-Vocabulary Image Segmentation with Image-Level Labelscited by 471
  3. 2022Cross Language Image Matching for Weakly Supervised Semantic Segmentationcited by 72
  4. 2023Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentationcited by 53
  5. 2021ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenescited by 47
  6. 2022TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentationcited by 26
  7. 2022Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Poolingcited by 19
  8. 2023Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentationcited by 17
  9. 2023MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentationcited by 13
  10. 2021Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similaritycited by 11
  11. 2022Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentationcited by 7
  12. 2022Mixed-UNet: Refined Class Activation Mapping for Weakly-Supervised Semantic Segmentation with Multi-scale Inferencecited by 7
25 more
  1. 2021Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Studycited by 6
  2. 2022SESS: Saliency Enhancing with Scaling and Slidingcited by 5
  3. 2022Dual Progressive Transformations for Weakly Supervised Semantic Segmentationcited by 4
  4. 2023Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentationcited by 4
  5. 2024DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentationcited by 3
  6. 2022ISIM: Iterative Self-Improved Model for Weakly Supervised Segmentationcited by 2
  7. 2021One-shot Weakly-Supervised Segmentation in Medical Imagescited by 1
  8. 2022RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised Semantic Segmentation across Single- and Multi-Stage Frameworkscited by 1
  9. 2022Object-Aware Self-supervised Multi-Label Learningcited by 1
  10. 2022Single-cell Subcellular Protein Localisation Using Novel Ensembles of Diverse Deep Architecturescited by 1
  11. 2022ExpNet: A unified network for Expert-Level Classificationcited by 1
  12. 2023ReFit: A Framework for Refinement of Weakly Supervised Semantic Segmentation using Object Border Fitting for Medical Imagescited by 1
  13. 2023BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applicationscited by 1
  14. 2025Temporal-consistent CAMs for Weakly Supervised Video Segmentation in Waste Sortingcited by 1
  15. 2022Towards Better Guided Attention and Human Knowledge Insertion in Deep Convolutional Neural Networkscited by 0
  16. 2023SILOP: An Automated Framework for Semantic Segmentation Using Image Labels Based on Object Perimeterscited by 0
  17. 2023ISLE: A Framework for Image Level Semantic Segmentation Ensemblecited by 0
  18. 2023P-NOC: adversarial training of CAM generating networks for robust weakly supervised semantic segmentation priorscited by 0
  19. 2023Automatic coral reef fish identification and 3D measurement in the wildcited by 0
  20. 2024Not just Birds and Cars: Generic, Scalable and Explainable Models for Professional Visual Recognitioncited by 0
  21. 2024Part-based Quantitative Analysis for Heatmapscited by 0
  22. 2024Top-GAP: Integrating Size Priors in CNNs for more Interpretability, Robustness, and Bias Mitigationcited by 0
  23. 2024Text-Driven Weakly Supervised OCT Lesion Segmentation with Structural Guidancecited by 0
  24. 2025WS2: Weakly Supervised Segmentation using Before-After Supervision in Waste Sortingcited by 0
  25. 2026APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigmscited by 0