Unsupervised part representation by Flow Capsules
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Decoderimage-classificationImage ClassificationUnsupervised Image ClassificationSimilar Papers 제목 키워드 기반
HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network
Capsule networks are designed to present the objects by a set of parts and their relationships, which provide an insight into the procedure of visual perception. Although recent works have shown the success of capsule ne…
Sparse Unsupervised Capsules Generalize Better
We show that unsupervised training of latent capsule layers using only the reconstruction loss, without masking to select the correct output class, causes a loss of equivariances and other desirable capsule qualities. Th…
General ClassificationDPR-CAE: Capsule Autoencoder with Dynamic Part Representation for Image Parsing
Parsing an image into a hierarchy of objects, parts, and relations is important and also challenging in many computer vision tasks. This paper proposes a simple and effective capsule autoencoder to address this issue, ca…
DecoderTranslationGeometric Capsule Autoencoders for 3D Point Clouds
We propose a method to learn object representations from 3D point clouds using bundles of geometrically interpretable hidden units, which we call geometric capsules. Each geometric capsule represents a visual entity, suc…
ObjectRetrievalObject Learning and Robust 3D Reconstruction
In this thesis we discuss architectural designs and training methods for a neural network to have the ability of dissecting an image into objects of interest without supervision. The main challenge in 2D unsupervised obj…
3D ReconstructionObjectSemantic SegmentationUnsupervised Object Segmentation