Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay

• URL: http://arxiv.org/abs/2003.04382v1
• Date: Mon, 9 Mar 2020 19:50:24 GMT
• Title: Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay
• Authors: Qicheng Lao, Xiang Jiang, Mohammad Havaei, Yoshua Bengio
• Abstract summary: Learning in non-stationary environments is one of the biggest challenges in machine learning. Non-stationarity can be caused by either task drift, or the domain drift. We propose variational domain-agnostic feature replay, an approach that is composed of three components.
• Score: 78.7472257594881
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning in non-stationary environments is one of the biggest challenges in machine learning. Non-stationarity can be caused by either task drift, i.e., the drift in the conditional distribution of labels given the input data, or the domain drift, i.e., the drift in the marginal distribution of the input data. This paper aims to tackle this challenge in the context of continuous domain adaptation, where the model is required to learn new tasks adapted to new domains in a non-stationary environment while maintaining previously learned knowledge. To deal with both drifts, we propose variational domain-agnostic feature replay, an approach that is composed of three components: an inference module that filters the input data into domain-agnostic representations, a generative module that facilitates knowledge transfer, and a solver module that applies the filtered and transferable knowledge to solve the queries. We address the two fundamental scenarios in continuous domain adaptation, demonstrating the effectiveness of our proposed approach for practical usage.

Related papers

• xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing [21.37585797507323]
  Cross-domain policy transfer methods mostly aim at learning domain correspondences or corrections to facilitate policy learning. We propose the Cross-Domain Trajectory EDiting framework that employs a specially designed diffusion model for cross-domain trajectory adaptation. Our proposed model architecture effectively captures the intricate dependencies among states, actions, and rewards, as well as the dynamics patterns within target data.
  arXiv  Detail & Related papers  (2024-09-13T10:07:28Z)
• Adapting to Distribution Shift by Visual Domain Prompt Generation [34.19066857066073]
  We adapt a model at test-time using a few unlabeled data to address distribution shifts. We build a knowledge bank to learn the transferable knowledge from source domains. The proposed method outperforms previous work on 5 large-scale benchmarks including WILDS and DomainNet.
  arXiv  Detail & Related papers  (2024-05-05T02:44:04Z)
• SIDE: Self-supervised Intermediate Domain Exploration for Source-free Domain Adaptation [36.470026809824674]
  Domain adaptation aims to alleviate the domain shift when transferring the knowledge learned from the source domain to the target domain. Due to privacy issues, source-free domain adaptation (SFDA) has recently become very demanding yet challenging. This paper proposes self-supervised intermediate domain exploration (SIDE) that effectively bridges the domain gap with an intermediate domain.
  arXiv  Detail & Related papers  (2023-10-13T07:50:37Z)
• Transfer RL via the Undo Maps Formalism [29.798971172941627]
  Transferring knowledge across domains is one of the most fundamental problems in machine learning. We propose TvD: transfer via distribution matching, a framework to transfer knowledge across interactive domains. We show this objective leads to a policy update scheme reminiscent of imitation learning, and derive an efficient algorithm to implement it.
  arXiv  Detail & Related papers  (2022-11-26T03:44:28Z)
• Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images [93.50240389540252]
  Road segmentation from remote sensing images is a challenging task with wide ranges of application potentials. We propose a novel stagewise domain adaptation model called RoadDA to address the domain shift (DS) issue in this field. Experiment results on two benchmarks demonstrate that RoadDA can efficiently reduce the domain gap and outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-08-28T09:29:14Z)
• Cross-domain Imitation from Observations [50.669343548588294]
  Imitation learning seeks to circumvent the difficulty in designing proper reward functions for training agents by utilizing expert behavior. In this paper, we study the problem of how to imitate tasks when there exist discrepancies between the expert and agent MDP. We present a novel framework to learn correspondences across such domains.
  arXiv  Detail & Related papers  (2021-05-20T21:08:25Z)
• Select, Label, and Mix: Learning Discriminative Invariant Feature Representations for Partial Domain Adaptation [55.73722120043086]
  We develop a "Select, Label, and Mix" (SLM) framework to learn discriminative invariant feature representations for partial domain adaptation. First, we present a simple yet efficient "select" module that automatically filters out outlier source samples to avoid negative transfer. Second, the "label" module iteratively trains the classifier using both the labeled source domain data and the generated pseudo-labels for the target domain to enhance the discriminability of the latent space.
  arXiv  Detail & Related papers  (2020-12-06T19:29:32Z)
• Domain Adaptation with Incomplete Target Domains [61.68950959231601]
  We propose an Incomplete Data Imputation based Adversarial Network (IDIAN) model to address this new domain adaptation challenge. In the proposed model, we design a data imputation module to fill the missing feature values based on the partial observations in the target domain. We conduct experiments on both cross-domain benchmark tasks and a real world adaptation task with imperfect target domains.
  arXiv  Detail & Related papers  (2020-12-03T00:07:40Z)
• Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation [165.61511788237485]
  Unsupervised domain adaptation (UDA) aims to address the domain-shift problem between a labeled source domain and an unlabeled target domain. We propose a dynamic task-oriented disentangling network (DTDN) to learn disentangled representations in an end-to-end fashion for UDA.
  arXiv  Detail & Related papers  (2020-07-27T01:21:18Z)
• Discriminative Active Learning for Domain Adaptation [16.004653151961303]
  We introduce a discriminative active learning approach for domain adaptation to reduce the efforts of data annotation. Specifically, we propose three-stage active adversarial training of neural networks. Empirical comparisons with existing domain adaptation methods using four benchmark datasets demonstrate the effectiveness of the proposed approach.
  arXiv  Detail & Related papers  (2020-05-24T04:20:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.