English
Related papers

Related papers: Cross Pixel Optical Flow Similarity for Self-Super…

200 papers

Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated…

Computer Vision and Pattern Recognition · Computer Science 2018-01-18 Nikolaus Mayer , Eddy Ilg , Philip Häusser , Philipp Fischer , Daniel Cremers , Alexey Dosovitskiy , Thomas Brox

Self-supervised learning allows for better utilization of unlabelled data. The feature representation obtained by self-supervision can be used in downstream tasks such as classification, object detection, segmentation, and anomaly…

Computer Vision and Pattern Recognition · Computer Science 2020-06-18 Rabia Ali , Muhammad Umar Karim Khan , Chong Min Kyung

In this paper, we present supervision-by-registration, an unsupervised approach to improve the precision of facial landmark detectors on both images and video. Our key observation is that the detections of the same landmark in adjacent…

Computer Vision and Pattern Recognition · Computer Science 2018-07-05 Xuanyi Dong , Shoou-I Yu , Xinshuo Weng , Shih-En Wei , Yi Yang , Yaser Sheikh

Motion representation plays a vital role in human action recognition in videos. In this study, we introduce a novel compact motion representation for video action recognition, named Optical Flow guided Feature (OFF), which enables the…

Computer Vision and Pattern Recognition · Computer Science 2018-07-10 Shuyang Sun , Zhanghui Kuang , Wanli Ouyang , Lu Sheng , Wei Zhang

Event-based cameras have shown great promise in a variety of situations where frame based cameras suffer, such as high speed motions and high dynamic range scenes. However, developing algorithms for event measurements requires a new class…

Computer Vision and Pattern Recognition · Computer Science 2018-08-14 Alex Zihao Zhu , Liangzhe Yuan , Kenneth Chaney , Kostas Daniilidis

Whilst computer vision models built using self-supervised approaches are now commonplace, some important questions remain. Do self-supervised models learn highly redundant channel features? What if a self-supervised network could…

Computer Vision and Pattern Recognition · Computer Science 2022-12-19 Tarun Krishna , Ayush K. Rai , Yasser A. D. Djilali , Alan F. Smeaton , Kevin McGuinness , Noel E. O'Connor

We present an unsupervised representation learning approach that compactly encodes the motion dependencies in videos. Given a pair of images from a video clip, our framework learns to predict the long-term 3D motions. To reduce the…

Computer Vision and Pattern Recognition · Computer Science 2017-04-13 Zelun Luo , Boya Peng , De-An Huang , Alexandre Alahi , Li Fei-Fei

In this paper, we propose a recurrent framework for Joint Unsupervised LEarning (JULE) of deep representations and image clusters. In our framework, successive operations in a clustering algorithm are expressed as steps in a recurrent…

Computer Vision and Pattern Recognition · Computer Science 2016-06-21 Jianwei Yang , Devi Parikh , Dhruv Batra

Estimating the parameters of a model describing a set of observations using a neural network is in general solved in a supervised way. In cases when we do not have access to the model's true parameters this approach can not be applied.…

Astrophysics of Galaxies · Physics 2020-09-30 Miguel A. Aragon-Calvo

We present a framework to use recently introduced Capsule Networks for solving the problem of Optical Flow, one of the fundamental computer vision tasks. Most of the existing state of the art deep architectures either uses a correlation…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Rahul Chand , Rajat Arora , K Ram Prabhakar , R Venkatesh Babu

Neural networks are a powerful framework for foreground segmentation in video acquired by static cameras, segmenting moving objects from the background in a robust way in various challenging scenarios. The premier methods are those based on…

Computer Vision and Pattern Recognition · Computer Science 2021-06-22 Levi Kassel , Michael Werman

Self-supervised monocular depth estimation enables robots to learn 3D perception from raw video streams. This scalable approach leverages projective geometry and ego-motion to learn via view synthesis, assuming the world is mostly static.…

Computer Vision and Pattern Recognition · Computer Science 2022-06-14 Vitor Guizilini , Kuan-Hui Lee , Rares Ambrus , Adrien Gaidon

We propose an adversarial contextual model for detecting moving objects in images. A deep neural network is trained to predict the optical flow in a region using information from everywhere else but that region (context), while another…

Computer Vision and Pattern Recognition · Computer Science 2019-04-16 Yanchao Yang , Antonio Loquercio , Davide Scaramuzza , Stefano Soatto

A key challenge in self-supervised video representation learning is how to effectively capture motion information besides context bias. While most existing works implicitly achieve this with video-specific pretext tasks (e.g., predicting…

Computer Vision and Pattern Recognition · Computer Science 2021-04-05 Lianghua Huang , Yu Liu , Bin Wang , Pan Pan , Yinghui Xu , Rong Jin

In order to autonomously learn wide repertoires of complex skills, robots must be able to learn from their own autonomously collected data, without human supervision. One learning signal that is always available for autonomously collected…

Robotics · Computer Science 2017-10-18 Frederik Ebert , Chelsea Finn , Alex X. Lee , Sergey Levine

Estimating the correspondences between pixels in sequences of images is a critical first step for a myriad of tasks including vision-aided navigation (e.g., visual odometry (VO), visual-inertial odometry (VIO), and visual simultaneous…

Image and Video Processing · Electrical Eng. & Systems 2018-03-16 E. Jared Shamwell , William D. Nothwang , Donald Perlis

This paper presents SPeCiaL: a method for unsupervised pretraining of representations tailored for continual learning. Our approach devises a meta-learning objective that differentiates through a sequential learning process. Specifically,…

Computer Vision and Pattern Recognition · Computer Science 2021-06-18 Lucas Caccia , Joelle Pineau

We propose a novel unsupervised image segmentation algorithm, which aims to segment an image into several coherent parts. It requires no user input, no supervised learning phase and assumes an unknown number of segments. It achieves this by…

Computer Vision and Pattern Recognition · Computer Science 2016-03-09 Aleksandar Dimitriev , Matej Kristan

Self-training is a simple semi-supervised learning approach: Unlabelled examples that attract high-confidence predictions are labelled with their predictions and added to the training set, with this process being repeated multiple times.…

Computer Vision and Pattern Recognition · Computer Science 2021-09-13 Attaullah Sahito , Eibe Frank , Bernhard Pfahringer

We present a novel approach to object classification and detection which requires minimal supervision and which combines visual texture cues and shape information learned from freely available unlabeled web search results. The explosion of…

Computer Vision and Pattern Recognition · Computer Science 2016-09-15 Xingchao Peng , Kate Saenko