Subsidiary Prototype Alignment for Universal Domain Adaptation

• URL: http://arxiv.org/abs/2210.15909v1
• Date: Fri, 28 Oct 2022 05:32:14 GMT
• Title: Subsidiary Prototype Alignment for Universal Domain Adaptation
• Authors: Jogendra Nath Kundu, Suvaansh Bhambri, Akshay Kulkarni, Hiran Sarkar, Varun Jampani, R. Venkatesh Babu
• Abstract summary: A major problem in Universal Domain Adaptation (UniDA) is misalignment of "known" and "unknown" classes. We propose a novel word-histogram-related pretext task to enable closed-set SPA, operating in conjunction with goal task UniDA. We demonstrate the efficacy of our approach on top of existing UniDA techniques, yielding state-of-the-art performance across three standard UniDA and Open-Set DA object recognition benchmarks.
• Score: 58.431124236254
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Universal Domain Adaptation (UniDA) deals with the problem of knowledge transfer between two datasets with domain-shift as well as category-shift. The goal is to categorize unlabeled target samples, either into one of the "known" categories or into a single "unknown" category. A major problem in UniDA is negative transfer, i.e. misalignment of "known" and "unknown" classes. To this end, we first uncover an intriguing tradeoff between negative-transfer-risk and domain-invariance exhibited at different layers of a deep network. It turns out we can strike a balance between these two metrics at a mid-level layer. Towards designing an effective framework based on this insight, we draw motivation from Bag-of-visual-Words (BoW). Word-prototypes in a BoW-like representation of a mid-level layer would represent lower-level visual primitives that are likely to be unaffected by the category-shift in the high-level features. We develop modifications that encourage learning of word-prototypes followed by word-histogram based classification. Following this, subsidiary prototype-space alignment (SPA) can be seen as a closed-set alignment problem, thereby avoiding negative transfer. We realize this with a novel word-histogram-related pretext task to enable closed-set SPA, operating in conjunction with goal task UniDA. We demonstrate the efficacy of our approach on top of existing UniDA techniques, yielding state-of-the-art performance across three standard UniDA and Open-Set DA object recognition benchmarks.

Related papers

• Reducing Source-Private Bias in Extreme Universal Domain Adaptation [11.875619863954238]
  Universal Domain Adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. We show that state-of-the-art methods struggle when the source domain has significantly more non-overlapping classes than overlapping ones. We propose using self-supervised learning to preserve the structure of the target data.
  arXiv  Detail & Related papers  (2024-10-15T04:51:37Z)
• EIANet: A Novel Domain Adaptation Approach to Maximize Class Distinction with Neural Collapse Principles [15.19374752514876]
  Source-free domain adaptation (SFDA) aims to transfer knowledge from a labelled source domain to an unlabelled target domain. A major challenge in SFDA is deriving accurate categorical information for the target domain. We introduce a novel ETF-Informed Attention Network (EIANet) to separate class prototypes.
  arXiv  Detail & Related papers  (2024-07-23T05:31:05Z)
• Upcycling Models under Domain and Category Shift [95.22147885947732]
  We introduce an innovative global and local clustering learning technique (GLC) We design a novel, adaptive one-vs-all global clustering algorithm to achieve the distinction across different target classes. Remarkably, in the most challenging open-partial-set DA scenario, GLC outperforms UMAD by 14.8% on the VisDA benchmark.
  arXiv  Detail & Related papers  (2023-03-13T13:44:04Z)
• Imbalanced Open Set Domain Adaptation via Moving-threshold Estimation and Gradual Alignment [58.56087979262192]
  Open Set Domain Adaptation (OSDA) aims to transfer knowledge from a well-labeled source domain to an unlabeled target domain. The performance of OSDA methods degrades drastically under intra-domain class imbalance and inter-domain label shift. We propose Open-set Moving-threshold Estimation and Gradual Alignment (OMEGA) to alleviate the negative effects raised by label shift.
  arXiv  Detail & Related papers  (2023-03-08T05:55:02Z)
• CDA: Contrastive-adversarial Domain Adaptation [11.354043674822451]
  We propose a two-stage model for domain adaptation called textbfContrastive-adversarial textbfDomain textbfAdaptation textbf(CDA). While the adversarial component facilitates domain-level alignment, two-stage contrastive learning exploits class information to achieve higher intra-class compactness across domains.
  arXiv  Detail & Related papers  (2023-01-10T07:43:21Z)
• UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation [84.16372642822495]
  We propose an unsupervised domain adaptation (UDA) for category-level object pose estimation, called textbfUDA-COPE. Inspired by the recent multi-modal UDA techniques, the proposed method exploits a teacher-student self-supervised learning scheme to train a pose estimation network without using target domain labels.
  arXiv  Detail & Related papers  (2021-11-24T16:00:48Z)
• Multi-Level Features Contrastive Networks for Unsupervised Domain Adaptation [6.934905764152813]
  Unsupervised domain adaptation aims to train a model from the labeled source domain to make predictions on the unlabeled target domain. Existing methods tend to align the two domains directly at the domain-level, or perform class-level domain alignment based on deep feature. In this paper, we develop this work on the method of class-level alignment.
  arXiv  Detail & Related papers  (2021-09-14T09:23:27Z)
• 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)
• Domain Adaptive Semantic Segmentation Using Weak Labels [115.16029641181669]
  We propose a novel framework for domain adaptation in semantic segmentation with image-level weak labels in the target domain. We develop a weak-label classification module to enforce the network to attend to certain categories. In experiments, we show considerable improvements with respect to the existing state-of-the-arts in UDA and present a new benchmark in the WDA setting.
  arXiv  Detail & Related papers  (2020-07-30T01:33:57Z)

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.