Unsupervised Part Segmentation through Disentangling Appearance and Shape

  title={Unsupervised Part Segmentation through Disentangling Appearance and Shape},
  author={Shilong Liu and Lei Zhang and X. Yang and Hang Su and Jun Zhu},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Shilong Liu, Lei Zhang, +2 authors Jun Zhu
  • Published 26 May 2021
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
We study the problem, of unsupervised discovery and segmentation of object parts, which, as an intermediate local representation, are capable of finding intrinsic object structure and providing more explainable recognition results. Recent unsupervised methods have greatly relaxed the dependency on annotated data which are costly to obtain, but still rely on additional information such as object segmentation mask or saliency map. To remove such a dependency and further improve the part… Expand
GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation
  • Xingzhe He, Bastian Wandt, Helge Rhodin
  • Computer Science
  • 2021
Segmenting an image into its parts is a common preprocess for high-level vision tasks such as image editing. However, annotating masks for supervised training is expensive. Weakly-supervised andExpand


Unsupervised Part-Based Disentangling of Object Shape and Appearance
This work presents an unsupervised approach for disentangling appearance and shape by learning parts consistently over all instances of a category by simultaneously exploiting invariance and equivariance constraints between synthetically transformed images. Expand
SCOPS: Self-Supervised Co-Part Segmentation
This work proposes a self-supervised deep learning approach for part segmentation, where several loss functions are devised that aids in predicting part segments that are geometrically concentrated, robust to object variations and are also semantically consistent across different object instances. Expand
Unsupervised Learning of Object Landmarks through Conditional Image Generation
This work proposes a method for learning landmark detectors for visual objects (such as the eyes and the nose in a face) without any manual supervision and introduces a tight bottleneck in the geometry-extraction process that selects and distils geometry-related features. Expand
Robust Object Co-Segmentation Using Background Prior
A novel MR-SGS model is proposed, i.e., manifold ranking with the self-learned graph structure, which can infer suitable graph structures in a data-driven manner rather than building the fixed graph structure relying on the subjective design. Expand
Self-supervised Single-view 3D Reconstruction via Semantic Consistency
This work is the first to try and solve the single-view reconstruction problem without a category-specific template mesh or semantic keypoints, and demonstrates that the unsupervised method performs comparably if not better than existing category- specific reconstruction methods learned with supervision. Expand
Unsupervised learning of object frames by dense equivariant image labelling
A new approach is proposed that, given a large number of images of an object and no other supervision, can extract a dense object-centric coordinate frame that is invariant to deformations of the images and comes with a dense equivariant labelling neural network that can map image pixels to their corresponding object coordinates. Expand
Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings
This paper proposes a novel unsupervised approach that can discover and learn landmarks in object categories, thus characterizing their structure, and shows that the learned landmarks establish meaningful correspondences between different object instances in a category without having to impose this requirement explicitly. Expand
Discriminative clustering for image co-segmentation
  • Armand Joulin, F. Bach, J. Ponce
  • Mathematics, Computer Science
  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
This paper combines existing tools for bottom-up image segmentation such as normalized cuts, with kernel methods commonly used in object recognition, used within a discriminative clustering framework to obtain a combinatorial optimization problem which is relaxed to a continuous convex optimization problem that can be solved efficiently for up to dozens of images. Expand
Deep Semantic Feature Matching
  • Nikolai Ufer, B. Ommer
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
A novel method for semantic matching with pre-trained CNN features which is based on convolutional feature pyramids and activation guided feature selection and can be transformed into a dense correspondence field. Expand
Object Co-Segmentation Based on Shortest Path Algorithm and Saliency Model
This paper proposes a new model that efficiently segments common objects from multiple images by segmenting each original image into a number of local regions based on local region similarities and saliency maps and uses the dynamic programming method to solve the co-segmentation problem. Expand