Stochastic Adversarial Gradient Embedding for Active Domain Adaptation

• URL: http://arxiv.org/abs/2012.01843v1
• Date: Thu, 3 Dec 2020 11:28:32 GMT
• Title: Stochastic Adversarial Gradient Embedding for Active Domain Adaptation
• Authors: Victor Bouvier, Philippe Very, Cl\'ement Chastagnol, Myriam Tami, C\'eline Hudelot
• Abstract summary: Unlabelled Domain Adaptation (UDA) aims to bridge the gap between a source domain, where labelled data are available, and a target domain only represented with unsupervised data. This paper addresses this problem by using active learning to annotate a small budget of target data. We introduce textitStochastic Adversarial Gradient Embedding (SAGE), a framework that makes a triple contribution to ADA.
• Score: 4.514832807541817
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unsupervised Domain Adaptation (UDA) aims to bridge the gap between a source domain, where labelled data are available, and a target domain only represented with unlabelled data. If domain invariant representations have dramatically improved the adaptability of models, to guarantee their good transferability remains a challenging problem. This paper addresses this problem by using active learning to annotate a small budget of target data. Although this setup, called Active Domain Adaptation (ADA), deviates from UDA's standard setup, a wide range of practical applications are faced with this situation. To this purpose, we introduce \textit{Stochastic Adversarial Gradient Embedding} (SAGE), a framework that makes a triple contribution to ADA. First, we select for annotation target samples that are likely to improve the representations' transferability by measuring the variation, before and after annotation, of the transferability loss gradient. Second, we increase sampling diversity by promoting different gradient directions. Third, we introduce a novel training procedure for actively incorporating target samples when learning invariant representations. SAGE is based on solid theoretical ground and validated on various UDA benchmarks against several baselines. Our empirical investigation demonstrates that SAGE takes the best of uncertainty \textit{vs} diversity samplings and improves representations transferability substantially.

Related papers

• Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence [60.37934652213881]
  Domain Adaptation (DA) facilitates knowledge transfer from a source domain to a related target domain. This paper investigates a practical DA paradigm, namely Source data-Free Active Domain Adaptation (SFADA), where source data becomes inaccessible during adaptation. We present learn from the learnt (LFTL), a novel paradigm for SFADA to leverage the learnt knowledge from the source pretrained model and actively iterated models without extra overhead.
  arXiv  Detail & Related papers  (2024-07-26T17:51:58Z)
• Overcoming Negative Transfer by Online Selection: Distant Domain Adaptation for Fault Diagnosis [42.85741244467877]
  The term distant domain adaptation problem' describes the challenge of adapting from a labeled source domain to a significantly disparate unlabeled target domain. This problem exhibits the risk of negative transfer, where extraneous knowledge from the source domain adversely affects the target domain performance. In response to this challenge, we propose a novel Online Selective Adversarial Alignment (OSAA) approach.
  arXiv  Detail & Related papers  (2024-05-25T07:17:47Z)
• Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer [69.82229895838577]
  Active Domain Adaptation (ADA) aims to maximally boost model adaptation in a new target domain by actively selecting a limited number of target data to annotate. This setting neglects the more practical scenario where training data are collected from multiple sources. This motivates us to target a new and challenging setting of knowledge transfer that extends ADA from a single source domain to multiple source domains.
  arXiv  Detail & Related papers  (2023-11-21T13:12:21Z)
• Divide and Adapt: Active Domain Adaptation via Customized Learning [56.79144758380419]
  We present Divide-and-Adapt (DiaNA), a new ADA framework that partitions the target instances into four categories with stratified transferable properties. With a novel data subdivision protocol based on uncertainty and domainness, DiaNA can accurately recognize the most gainful samples. Thanks to the "divideand-adapt" spirit, DiaNA can handle data with large variations of domain gap.
  arXiv  Detail & Related papers  (2023-07-21T14:37:17Z)
• Diffusion-based Target Sampler for Unsupervised Domain Adaptation [5.025971841729201]
  Large domain shifts and the sample scarcity in the target domain make existing UDA methods achieve suboptimal performance. We propose a plug-and-play Diffusion-based Target Sampler (DTS) to generate high fidelity and diversity pseudo target samples. The generated samples can well simulate the data distribution of the target domain and help existing UDA methods transfer from the source domain to the target domain more easily.
  arXiv  Detail & Related papers  (2023-03-17T02:07:43Z)
• ADAS: A Simple Active-and-Adaptive Baseline for Cross-Domain 3D Semantic Segmentation [38.66509154973051]
  We propose an Active-and-Adaptive (ADAS) baseline to enhance the weak cross-domain generalization ability of a well-trained 3D segmentation model. ADAS performs an active sampling operation to select a maximally-informative subset from both source and target domains for effective adaptation. ADAS is verified to be effective in many cross-domain settings including: 1) Unsupervised Domain Adaptation (UDA), which means that all samples from target domain are unlabeled; 2) Unsupervised Few-shot Domain Adaptation (UFDA), which means that only a few unlabeled samples are available in the unlabeled target domain.
  arXiv  Detail & Related papers  (2022-12-20T16:17:40Z)
• Cyclically Disentangled Feature Translation for Face Anti-spoofing [61.70377630461084]
  We propose a novel domain adaptation method called cyclically disentangled feature translation network (CDFTN) CDFTN generates pseudo-labeled samples that possess: 1) source domain-invariant liveness features and 2) target domain-specific content features, which are disentangled through domain adversarial training. A robust classifier is trained based on the synthetic pseudo-labeled images under the supervision of source domain labels.
  arXiv  Detail & Related papers  (2022-12-07T14:12:34Z)
• Semi-Supervised Domain Adaptation with Prototypical Alignment and Consistency Learning [86.6929930921905]
  This paper studies how much it can help address domain shifts if we further have a few target samples labeled. To explore the full potential of landmarks, we incorporate a prototypical alignment (PA) module which calculates a target prototype for each class from the landmarks. Specifically, we severely perturb the labeled images, making PA non-trivial to achieve and thus promoting model generalizability.
  arXiv  Detail & Related papers  (2021-04-19T08:46:08Z)
• A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation [142.31610972922067]
  This work addresses the unsupervised domain adaptation problem, especially in the case of class labels in the target domain being only a subset of those in the source domain. We build on domain adversarial learning and propose a novel domain adaptation method BA$3$US with two new techniques termed Balanced Adversarial Alignment (BAA) and Adaptive Uncertainty Suppression (AUS) Experimental results on multiple benchmarks demonstrate our BA$3$US surpasses state-of-the-arts for partial domain adaptation tasks.
  arXiv  Detail & Related papers  (2020-03-05T11:37:06Z)

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.