Unsupervised part representation by Flow Capsules

• URL: http://arxiv.org/abs/2011.13920v2
• Date: Fri, 19 Feb 2021 18:07:46 GMT
• Title: Unsupervised part representation by Flow Capsules
• Authors: Sara Sabour, Andrea Tagliasacchi, Soroosh Yazdani, Geoffrey E. Hinton, David J. Fleet
• Abstract summary: We propose a way to learn primary capsule encoders that detect atomic parts from a single image. We exploit motion as a powerful perceptual cue for part definition, with an expressive decoder for part generation within a layered image model.
• Score: 43.2934619818695
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Capsule networks aim to parse images into a hierarchy of objects, parts and relations. While promising, they remain limited by an inability to learn effective low level part descriptions. To address this issue we propose a way to learn primary capsule encoders that detect atomic parts from a single image. During training we exploit motion as a powerful perceptual cue for part definition, with an expressive decoder for part generation within a layered image model with occlusion. Experiments demonstrate robust part discovery in the presence of multiple objects, cluttered backgrounds, and occlusion. The part decoder infers the underlying shape masks, effectively filling in occluded regions of the detected shapes. We evaluate FlowCapsules on unsupervised part segmentation and unsupervised image classification.

Related papers

• DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut [62.63481844384229]
  Foundation models have emerged as powerful tools across various domains including language, vision, and multimodal tasks. In this paper, we use a diffusion UNet encoder as a foundation vision encoder and introduce DiffCut, an unsupervised zero-shot segmentation method. Our work highlights the remarkably accurate semantic knowledge embedded within diffusion UNet encoders that could then serve as foundation vision encoders for downstream tasks.
  arXiv  Detail & Related papers  (2024-06-05T01:32:31Z)
• PDiscoNet: Semantically consistent part discovery for fine-grained recognition [62.12602920807109]
  We propose PDiscoNet to discover object parts by using only image-level class labels along with priors encouraging the parts to be. Our results on CUB, CelebA, and PartImageNet show that the proposed method provides substantially better part discovery performance than previous methods.
  arXiv  Detail & Related papers  (2023-09-06T17:19:29Z)
• Unsupervised Dense Nuclei Detection and Segmentation with Prior Self-activation Map For Histology Images [5.3882963853819845]
  We propose a self-supervised learning based approach with a Prior Self-activation Module (PSM) PSM generates self-activation maps from the input images to avoid labeling costs and further produce pseudo masks for the downstream task. Compared with other fully-supervised and weakly-supervised methods, our method can achieve competitive performance without any manual annotations.
  arXiv  Detail & Related papers  (2022-10-14T14:34:26Z)
• HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network [76.92310948325847]
  We propose a Hierarchical Parsing Capsule Network (HP-Capsule) for unsupervised face subpart-part discovery. HP-Capsule extends the application of capsule networks from digits to human faces and takes a step forward to show how the neural networks understand objects without human intervention.
  arXiv  Detail & Related papers  (2022-03-21T01:39:41Z)
• Unsupervised Part Discovery from Contrastive Reconstruction [90.88501867321573]
  The goal of self-supervised visual representation learning is to learn strong, transferable image representations. We propose an unsupervised approach to object part discovery and segmentation. Our method yields semantic parts consistent across fine-grained but visually distinct categories.
  arXiv  Detail & Related papers  (2021-11-11T17:59:42Z)
• Self-supervised Segmentation via Background Inpainting [96.10971980098196]
  We introduce a self-supervised detection and segmentation approach that can work with single images captured by a potentially moving camera. We exploit a self-supervised loss function that we exploit to train a proposal-based segmentation network. We apply our method to human detection and segmentation in images that visually depart from those of standard benchmarks and outperform existing self-supervised methods.
  arXiv  Detail & Related papers  (2020-11-11T08:34:40Z)
• Unsupervised Part Discovery by Unsupervised Disentanglement [10.664434993386525]
  Part segmentations provide information about part localizations on the level of individual pixels. Large annotation costs limit the scalability of supervised algorithms to other object categories. Our work demonstrates the feasibility to discover semantic part segmentations without supervision.
  arXiv  Detail & Related papers  (2020-09-09T12:34:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.