English
Related papers

Related papers: Learning Successor Features the Simple Way

200 papers

A key question in Reinforcement Learning is which representation an agent can learn to efficiently reuse knowledge between different tasks. Recently the Successor Representation was shown to have empirical benefits for transferring…

Machine Learning · Computer Science 2018-07-06 Lucas Lehnert , Michael L. Littman

This paper introduces a novel method for self-supervised video representation learning via feature prediction. In contrast to the previous methods that focus on future feature prediction, we argue that a supervisory signal arising from…

Computer Vision and Pattern Recognition · Computer Science 2020-11-13 Nadine Behrmann , Juergen Gall , Mehdi Noroozi

The methods of extracting image features are the key to many image processing tasks. At present, the most popular method is the deep neural network which can automatically extract robust features through end-to-end training instead of…

Computer Vision and Pattern Recognition · Computer Science 2023-03-20 Xiang Ma , Liangzhe Chen , Zhaohong Deng , Peng Xu , Qisheng Yan , Kup-Sze Choi , Shitong Wang

Few-shot learning (FSL) techniques seek to learn the underlying patterns in data using fewer samples, analogous to how humans learn from limited experience. In this limited-data scenario, the challenges associated with deep neural networks,…

Computer Vision and Pattern Recognition · Computer Science 2023-04-14 Deepan Chakravarthi Padmanabhan , Shruthi Gowda , Elahe Arani , Bahram Zonooz

Learning to predict future images from a video sequence involves the construction of an internal representation that models the image evolution accurately, and therefore, to some degree, its content and dynamics. This is why pixel-space…

Machine Learning · Computer Science 2016-03-01 Michael Mathieu , Camille Couprie , Yann LeCun

Federated learning (FL) based magnetic resonance (MR) image reconstruction can facilitate learning valuable priors from multi-site institutions without violating patient's privacy for accelerating MR imaging. However, existing methods rely…

Image and Video Processing · Electrical Eng. & Systems 2023-05-11 Juan Zou , Cheng Li , Ruoyou Wu , Tingrui Pei , Hairong Zheng , Shanshan Wang

Most image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs that are constructed by a predetermined operation, e.g., bicubic downsampling. As existing methods typically learn…

Image and Video Processing · Electrical Eng. & Systems 2021-09-09 Sanghyun Son , Jaeha Kim , Wei-Sheng Lai , Ming-Husan Yang , Kyoung Mu Lee

Catastrophic forgetting has been a major challenge in continual learning, where the model needs to learn new tasks with limited or no access to data from previously seen tasks. To tackle this challenge, methods based on knowledge…

Machine Learning · Computer Science 2023-06-29 Qiao Gu , Dongsub Shim , Florian Shkurti

Many approximations were suggested to circumvent the cubic complexity of kernel-based algorithms, allowing their application to large-scale datasets. One strategy is to consider the primal formulation of the learning problem by mapping the…

Machine Learning · Computer Science 2025-12-03 Albert Saiapin , Kim Batselier

Recently, there is a vast interest in developing image feature learning methods that are independent of the training data, such as deep image prior, InGAN, SinGAN, and DCIL. These methods are unsupervised and are used to perform low-level…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Indra Deep Mastan , Shanmuganathan Raman

Sample efficiency and risk-awareness are central to the development of practical reinforcement learning (RL) for complex decision-making. The former can be addressed by transfer learning and the latter by optimizing some utility function of…

Machine Learning · Computer Science 2021-06-01 Michael Gimelfarb , André Barreto , Scott Sanner , Chi-Guhn Lee

Purpose: To improve reconstruction fidelity of fine structures and textures in deep learning (DL) based reconstructions. Methods: A novel patch-based Unsupervised Feature Loss (UFLoss) is proposed and incorporated into the training of…

Image and Video Processing · Electrical Eng. & Systems 2021-08-31 Ke Wang , Jonathan I Tamir , Alfredo De Goyeneche , Uri Wollner , Rafi Brada , Stella Yu , Michael Lustig

In order to encode the class correlation and class specific information in image representation, we propose a new local feature learning approach named Deep Discriminative and Shareable Feature Learning (DDSFL). DDSFL aims to hierarchically…

Computer Vision and Pattern Recognition · Computer Science 2015-08-24 Zhen Zuo , Gang Wang , Bing Shuai , Lifan Zhao , Qingxiong Yang

Feature point detection and description is the backbone for various computer vision applications, such as Structure-from-Motion, visual SLAM, and visual place recognition. While learning-based methods have surpassed traditional handcrafted…

Computer Vision and Pattern Recognition · Computer Science 2024-09-23 Ali Youssef , Francisco Vasconcelos

Based on the predictive map theory of spatial learning in animals, this study delves into the dynamics of Successor Feature (SF) and Predecessor Feature (PF) algorithms within noisy environments. Utilizing Q-learning and Q($\lambda$)…

Neural and Evolutionary Computing · Computer Science 2024-02-08 Hyunsu Lee

Video analysis tasks rely heavily on identifying the pixels from different frames that correspond to the same visual target. To tackle this problem, recent studies have advocated feature learning methods that aim to learn distinctive…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Rui Li , Shenglong Zhou , Dong Liu

The success of Reinforcement Learning (RL) heavily relies on the ability to learn robust representations from the observations of the environment. In most cases, the representations learned purely by the reinforcement learning loss can…

Machine Learning · Computer Science 2024-02-12 Somjit Nath , Rushiv Arora , Samira Ebrahimi Kahou

Many self-supervised learning (SSL) methods have been successful in learning semantically meaningful visual representations by solving pretext tasks. However, prior work in SSL focuses on tasks like object recognition or detection, which…

Computer Vision and Pattern Recognition · Computer Science 2021-08-13 Donghyun Kim , Kuniaki Saito , Samarth Mishra , Stan Sclaroff , Kate Saenko , Bryan A Plummer

Deep learning approaches to generic (non-semantic) segmentation have so far been indirect and relied on edge detection. This is in contrast to semantic segmentation, where DNNs are applied directly. We propose an alternative approach called…

Computer Vision and Pattern Recognition · Computer Science 2019-09-27 Oran Shayer , Michael Lindenbaum

Language models are typically trained to predict the next token in a sequence. Here, we explore an alternative predictive principle from reinforcement learning: Successor Representations (SRs), which model the expected discounted…

Computation and Language · Computer Science 2026-05-26 Mathis Immertreu , Achim Schilling , Thomas Kinfe , Patrick Krauss