Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Budget-aware Semi-Supervised Semantic and Instance Segmentation

298 views

Published on

Methods that move towards less supervised scenarios are key for image segmentation, as dense labels demand significant human intervention. Generally, the annotation burden is mitigated by labeling datasets with weaker forms of supervision, e.g. image-level labels or bounding boxes. Another option are semi-supervised settings, that commonly leverage a few strong annotations and a huge number of unlabeled/weakly-labeled data. In this paper, we revisit semi-supervised segmentation schemes and narrow down significantly the annotation budget (in terms of total labeling time of the training set) compared to previous approaches. With a very simple pipeline, we demonstrate that at low annotation budgets, semi-supervised methods outperform by a wide margin weakly-supervised ones for both semantic and instance segmentation. Our approach also outperforms previous semi-supervised works at a much reduced labeling cost. We present results for the Pascal VOC benchmark and unify weakly and semi-supervised approaches by considering the total annotation budget, thus allowing a fairer comparison between methods.

http://openaccess.thecvf.com/content_CVPRW_2019/html/Deep_Vision_Workshop/Bellver_Budget-aware_Semi-Supervised_Semantic_and_Instance_Segmentation_CVPRW_2019_paper.html

Published in: Data & Analytics
  • Be the first to comment

  • Be the first to like this

Budget-aware Semi-Supervised Semantic and Instance Segmentation

  1. 1. Budget-aware Semi-Supervised Semantic and Instance Segmentation Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto Women In Computer Vision - CVPR 2019
  2. 2. Motivation Budget-aware Semi-Supervised Semantic and Instance Segmentation: Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto Semantic segmentation Instance segmentation Pixel-level annotations are expensive!
  3. 3. Motivation Budget-aware Semi-Supervised Semantic and Instance Segmentation: Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto Semantic segmentation Instance segmentation Solution: Weakly and Semi-supervised methods!
  4. 4. Motivation Budget-aware Semi-Supervised Semantic and Instance Segmentation: Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto Semantic segmentation Instance segmentation Solution: Weakly and Semi-supervised methods!
  5. 5. Contributions Budget-aware Semi-Supervised Semantic and Instance Segmentation: Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto 1. We unify the segmentation benchmarks regardless the training setting and the supervision signals comparing them in terms of the total annotation cost.
  6. 6. Contributions Budget-aware Semi-Supervised Semantic and Instance Segmentation: Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto 1. We unify the segmentation benchmarks regardless the training setting and the supervision signals comparing them in terms of the total annotation cost. 2. We experiment with a semi-supervised pipeline and test it in Pascal VOC for semantic and instance segmentation, outperforming previous works at low annotated budgets.
  7. 7. Contributions Budget-aware Semi-Supervised Semantic and Instance Segmentation: Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto 1. We unify the segmentation benchmarks regardless the training setting and the supervision signals comparing them in terms of the total annotation cost. 2. We experiment with a semi-supervised pipeline and test it in Pascal VOC for semantic and instance segmentation, outperforming previous works at low annotated budgets. 3. We show that for low annotation budgets, it’s more convenient having fewer but stronger-labeled data over having larger weakly-annotated sets.
  8. 8. Budget-aware Semi-Supervised Semantic and Instance Segmentation: Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto Semi-Supervised PipelineSemi-Supervised Pipeline Annotation network
  9. 9. Budget-aware Semi-Supervised Semantic and Instance Segmentation: Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto Semi-Supervised PipelineSemi-Supervised Pipeline Annotation network Segmentation network
  10. 10. Experimental validation for Pascal VOC Budget-aware Semi-Supervised Semantic and Instance Segmentation: Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto Semantic segmentation Annotation cost Segmentationquality We used DeepLab v3+ for both the annotation and segmentation network
  11. 11. Experimental validation for Pascal VOC Budget-aware Semi-Supervised Semantic and Instance Segmentation: Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto Instance segmentation Annotation cost Segmentationquality We used RSIS for both the annotation and segmentation network
  12. 12. Comparison to other works Budget-aware Semi-Supervised Semantic and Instance Segmentation: Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto Semantic segmentation Instance segmentation Annotation cost Segmentationquality
  13. 13. Visualization for semantic segmentation Budget-aware Semi-Supervised Semantic and Instance Segmentation: Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto
  14. 14. Visualization for instance segmentation Budget-aware Semi-Supervised Semantic and Instance Segmentation: Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto
  15. 15. Thanks for your attention!

×