mlsanityData to 14 Oct 2026

Improving Few-Shot Part Segmentation using Coarse Supervision

arXiv 2204.05393 ↗First posted 11 Apr 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

A significant bottleneck in training deep networks for part segmentation is the cost of obtaining detailed annotations. We propose a framework to exploit coarse labels such as figure-ground masks and keypoint locations that are readily available for some categories to improve part segmentation models. A key challenge is that these annotations were collected for different tasks and with different labeling styles and cannot be readily mapped to the part labels. To this end, we propose to jointly learn the dependencies between labeling styles and the part segmentation model, allowing us to utilize supervision from diverse labels. To evaluate our approach we develop a benchmark on the Caltech-UCSD birds and OID Aircraft dataset. Our approach outperforms baselines based on multi-task learning, semi-supervised learning, and competitive methods relying on loss functions manually designed to exploit sparse-supervision.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 28 of its 39 references that are in the map. First posted on arXiv 11 Apr 2022.

Builds on

28 of 39 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2017Mask R-CNNcited by 7,277
  5. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 463
  6. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 375
  7. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 331
  8. 2020Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentationcited by 300
  9. 2021DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effortcited by 264
  10. 2019Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relationscited by 247
  11. 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 232
  12. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 227
16 more
  1. 2021Efficiently Identifying Task Groupings for Multi-Task Learningcited by 222
  2. 2020PseudoSeg: Designing Pseudo Labels for Semantic Segmentationcited by 180
  3. 2021PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clusteringcited by 163
  4. 2020BoxInst: High-Performance Instance Segmentation with Box Annotationscited by 151
  5. 2020Unsupervised Learning of Dense Visual Representationscited by 147
  6. 2015Instance-aware Semantic Segmentation via Multi-task Network Cascadescited by 121
  7. 2020Learning to Branch for Multi-Task Learningcited by 115
  8. 2019SCOPS: Self-Supervised Co-Part Segmentationcited by 100
  9. 2021Repurposing GANs for One-shot Semantic Part Segmentationcited by 88
  10. 2021Pointly-Supervised Instance Segmentationcited by 83
  11. 2018Weakly Supervised Instance Segmentation using Class Peak Responsecited by 75
  12. 2018MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Networkcited by 47
  13. 2021MultiTask-CenterNet (MCN): Efficient and Diverse Multitask Learning using an Anchor Free Approachcited by 17
  14. 2021Few-Shot Segmentation with Global and Local Contrastive Learningcited by 17
  15. 2021GANORCON: Are Generative Models Useful for Few-shot Segmentation?cited by 13
  16. 2017Pose2Instance: Harnessing Keypoints for Person Instance Segmentationcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 6; 2024: 3; 2025: 1.

10 papers.

  1. 2023Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentationcited by 29
  2. 2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
  3. 2023Towards Open-World Segmentation of Partscited by 15
  4. 2024DEAL: Disentangle and Localize Concept-level Explanations for VLMscited by 14
  5. 2024Beyond Accuracy: Ensuring Correct Predictions With Correct Rationalescited by 6
  6. 2023PARTICLE: Part Discovery and Contrastive Learning for Fine-grained Recognitioncited by 5
  7. 2023Learning Part Segmentation from Synthetic Animalscited by 4
  8. 2023CrashCar101: Procedural Generation for Damage Assessmentcited by 1
  9. 2024Learning Robust Correlation with Foundation Model for Weakly-Supervised Few-Shot Segmentationcited by 0
  10. 2025Emerging Semantic Segmentation from Positive and Negative Coarse Label Learningcited by 0