English
Related papers

Related papers: Online Prototype Alignment for Few-shot Policy Tra…

200 papers

In recent years, significant progress has been made in multi-objective reinforcement learning (RL) research, which aims to balance multiple objectives by incorporating preferences for each objective. In most existing studies, specific…

Machine Learning · Computer Science 2024-09-17 Qian Lin , Zongkai Liu , Danying Mo , Chao Yu

Domain adaptation is an essential task in transfer learning to leverage data in one domain to bolster learning in another domain. In this paper, we present a new semi-supervised manifold alignment technique based on a two-step approach of…

Machine Learning · Computer Science 2020-11-12 Stefan Dernbach , Don Towsley

Applying the knowledge of an object detector trained on a specific domain directly onto a new domain is risky, as the gap between two domains can severely degrade model's performance. Furthermore, since different instances commonly embody…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Minghao Xu , Hang Wang , Bingbing Ni , Qi Tian , Wenjun Zhang

Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem. To mitigate this issue, a typical solution…

Machine Learning · Computer Science 2023-09-06 Qisen Yang , Shenzhi Wang , Qihang Zhang , Gao Huang , Shiji Song

In this work, we tackle the problem of online adaptation for stereo depth estimation, that consists in continuously adapting a deep network to a target video recordedin an environment different from that of the source training set. To…

Computer Vision and Pattern Recognition · Computer Science 2019-04-19 Zhenyu Zhang , Stéphane Lathuilière , Andrea Pilzer , Nicu Sebe , Elisa Ricci , Jian Yang

This article reviews the recent advances on the statistical foundation of reinforcement learning (RL) in the offline and low-adaptive settings. We will start by arguing why offline RL is the appropriate model for almost any real-life ML…

Machine Learning · Computer Science 2025-01-07 Ming Yin , Mengdi Wang , Yu-Xiang Wang

We try to address the problem of document layout understanding using a simple algorithm which generalizes across multiple domains while training on just few examples per domain. We approach this problem via supervised object detection…

Computer Vision and Pattern Recognition · Computer Science 2018-08-23 Pranaydeep Singh , Srikrishna Varadarajan , Ankit Narayan Singh , Muktabh Mayank Srivastava

Deep networks are prone to performance degradation when there is a domain shift between the source (training) data and target (test) data. Recent test-time adaptation methods update batch normalization layers of pre-trained source models…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Wenyu Zhang , Li Shen , Wanyue Zhang , Chuan-Sheng Foo

Cross-domain offline reinforcement learning (RL) aims to learn a policy in the target domain with a limited target domain dataset and a source domain dataset that exhibits a dynamics shift. Training directly on the original source dataset…

Machine Learning · Computer Science 2026-05-26 Zhongjian Qiao , Jiafei Lyu , Chenjia Bai , Peisong Wang , Siyang Gao , Shuang Qiu

Machine learning algorithms typically assume that the training and test samples come from the same distributions, i.e., in-distribution. However, in open-world scenarios, streaming big data can be Out-Of-Distribution (OOD), rendering these…

Machine Learning · Computer Science 2022-11-10 Anique Tahir , Lu Cheng , Ruocheng Guo , Huan Liu

With the ability to learn from static datasets, Offline Reinforcement Learning (RL) emerges as a compelling avenue for real-world applications. However, state-of-the-art offline RL algorithms perform sub-optimally when confronted with…

Machine Learning · Computer Science 2024-06-12 Briti Gangopadhyay , Zhao Wang , Jia-Fong Yeh , Shingo Takamatsu

Deep reinforcement learning agents have recently been successful across a variety of discrete and continuous control tasks; however, they can be slow to train and require a large number of interactions with the environment to learn a…

Machine Learning · Computer Science 2018-12-19 Thomas Carr , Maria Chli , George Vogiatzis

Domain adaptation is the supervised learning setting in which the training and test data are sampled from different distributions: training data is sampled from a source domain, whilst test data is sampled from a target domain. This paper…

Machine Learning · Statistics 2016-10-21 Wouter M. Kouw , Jesse H. Krijthe , Marco Loog , Laurens J. P. van der Maaten

Existing few-shot learning (FSL) methods make the implicit assumption that the few target class samples are from the same domain as the source class samples. However, in practice this assumption is often invalid -- the target classes could…

Computer Vision and Pattern Recognition · Computer Science 2020-03-20 An Zhao , Mingyu Ding , Zhiwu Lu , Tao Xiang , Yulei Niu , Jiechao Guan , Ji-Rong Wen , Ping Luo

Offline reinforcement learning (RL) aims to learn a policy that maximizes the expected return using a given static dataset of transitions. However, offline RL faces the distribution shift problem. The policy constraint offline RL method is…

Machine Learning · Computer Science 2025-12-24 Yuanhao Chen , Qi Liu , Pengbin Chen , Zhongjian Qiao , Yanjie Li

Recent progress in the few-shot adaptation of Vision-Language Models (VLMs) has further pushed their generalization capabilities, at the expense of just a few labeled samples within the target downstream task. However, this promising,…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Maxime Zanella , Ismail Ben Ayed

Target-driven visual navigation is a challenging problem that requires a robot to find the goal using only visual inputs. Many researchers have demonstrated promising results using deep reinforcement learning (deep RL) on various robotic…

Robotics · Computer Science 2021-06-08 Qian Luo , Maks Sorokin , Sehoon Ha

We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is directly inspired by the theory on domain adaptation…

Few-shot relation extraction aims to recognize novel relations with few labeled sentences in each relation. Previous metric-based few-shot relation extraction algorithms identify relationships by comparing the prototypes generated by the…

Computation and Language · Computer Science 2023-05-12 Zhongju Yuan , Zhenkun Wang , Genghui Li

This paper investigates the application of Low-Rank Adaptation (LoRA) to small models for cross-domain few-shot object detection in aerial images. Originally designed for large-scale models, LoRA helps mitigate overfitting, making it a…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Hicham Talaoubrid , Anissa Mokraoui , Ismail Ben Ayed , Axel Prouvost , Sonimith Hang , Monit Korn , Rémi Harvey