PVEs: Position-Velocity Encoders for Unsupervised Learning of Structured State Representations
We propose position-velocity encoders (PVEs) which learn---without supervision---to encode images to positions and velocities of task-relevant objects. PVEs encode a single image into a low-dimensional position state and compute the velocity state from finite differences in position. In contrast to autoencoders, position-velocity encoders are not trained by image reconstruction, but by making the position-velocity representation consistent with priors about interacting with the physical world. We applied PVEs to several simulated control tasks from pixels and achieved promising preliminary results.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ReconstructionPositionSimilar Papers 제목 키워드 기반
DeepVesselNet: Vessel Segmentation, Centerline Prediction, and Bifurcation Detection in 3-D Angiographic Volumes
We present DeepVesselNet, an architecture tailored to the challenges faced when extracting vessel networks or trees and corresponding features in 3-D angiographic volumes using deep learning. We discuss the problems of l…
Transfer LearningUnsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network
The task of blood vessel segmentation in microscopy images is crucial for many diagnostic and research applications. However, vessels can look vastly different, depending on the transient imaging conditions, and collecti…
DiagnosticImage SegmentationSegmentationSemantic SegmentationNVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videos
In this paper, we aim to model 3D scene dynamics from multi-view videos. Unlike the majority of existing works which usually focus on the common task of novel view synthesis within the training time period, we propose to…
Novel View SynthesisGraph Attention Auto-Encoders
Auto-encoders have emerged as a successful framework for unsupervised learning. However, conventional auto-encoders are incapable of utilizing explicit relations in structured data. To take advantage of relations in grap…
DecoderGraph AttentionInductive LearningNode Classification+1ACSGRegNet: A Deep Learning-based Framework for Unsupervised Joint Affine and Diffeomorphic Registration of Lumbar Spine CT via Cross- and Self-Attention Fusion
Registration plays an important role in medical image analysis. Deep learning-based methods have been studied for medical image registration, which leverage convolutional neural networks (CNNs) for efficiently regressing…
DecoderImage RegistrationMedical Image AnalysisMedical Image Registration