A2XP: Towards Private Domain Generalization

• URL: http://arxiv.org/abs/2311.10339v2
• Date: Wed, 17 Apr 2024 09:50:25 GMT
• Title: A2XP: Towards Private Domain Generalization
• Authors: Geunhyeok Yu, Hyoseok Hwang,
• Abstract summary: eXpert Prompts (A2XP) is a novel approach for domain generalization that preserves the privacy and integrity of the network architecture. Our experiments demonstrate that A2XP achieves state-of-the-art results over existing non-private domain generalization methods.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep Neural Networks (DNNs) have become pivotal in various fields, especially in computer vision, outperforming previous methodologies. A critical challenge in their deployment is the bias inherent in data across different domains, such as image style and environmental conditions, leading to domain gaps. This necessitates techniques for learning general representations from biased training data, known as domain generalization. This paper presents Attend to eXpert Prompts (A2XP), a novel approach for domain generalization that preserves the privacy and integrity of the network architecture. A2XP consists of two phases: Expert Adaptation and Domain Generalization. In the first phase, prompts for each source domain are optimized to guide the model towards the optimal direction. In the second phase, two embedder networks are trained to effectively amalgamate these expert prompts, aiming for an optimal output. Our extensive experiments demonstrate that A2XP achieves state-of-the-art results over existing non-private domain generalization methods. The experimental results validate that the proposed approach not only tackles the domain generalization challenge in DNNs but also offers a privacy-preserving, efficient solution to the broader field of computer vision.

Related papers

• Uncertainty-guided Contrastive Learning for Single Source Domain Generalisation [15.907643838530655]
  In this paper, we introduce a novel model referred to as Contrastive Uncertainty Domain Generalisation Network (CUDGNet) The key idea is to augment the source capacity in both input and label spaces through the fictitious domain generator. Our method also provides efficient uncertainty estimation at inference time from a single forward pass through the generator subnetwork.
  arXiv  Detail & Related papers  (2024-03-12T10:47:45Z)
• Beyond Finite Data: Towards Data-free Out-of-distribution Generalization via Extrapolation [19.944946262284123]
  Humans can easily extrapolate novel domains, thus, an intriguing question arises: How can neural networks extrapolate like humans and achieve OOD generalization? We introduce a novel approach to domain extrapolation that leverages reasoning ability and the extensive knowledge encapsulated within large language models (LLMs) to synthesize entirely new domains. Our methods exhibit commendable performance in this setting, even surpassing the supervised setting by approximately 1-2% on datasets such as VLCS.
  arXiv  Detail & Related papers  (2024-03-08T18:44:23Z)
• Single Domain Dynamic Generalization for Iris Presentation Attack Detection [41.126916126040655]
  Iris presentation generalization has achieved great success under intra-domain settings but easily degrades on unseen domains. We propose a Single Domain Dynamic Generalization (SDDG) framework, which exploits domain-invariant and domain-specific features on a per-sample basis. The proposed method is effective and outperforms the state-of-the-art on LivDet-Iris 2017 dataset.
  arXiv  Detail & Related papers  (2023-05-22T07:54:13Z)
• Modality-Agnostic Debiasing for Single Domain Generalization [105.60451710436735]
  We introduce a versatile Modality-Agnostic Debiasing (MAD) framework for single-DG. We show that MAD improves DSU by 2.82% and 1.5% in accuracy and mIOU. More remarkably, for recognition on 3D point clouds and semantic segmentation on 2D images, MAD improves DSU by 1.5% in accuracy and mIOU.
  arXiv  Detail & Related papers  (2023-03-13T13:56:11Z)
• Localized Adversarial Domain Generalization [83.4195658745378]
  Adversarial domain generalization is a popular approach to domain generalization. We propose localized adversarial domain generalization with space compactness maintenance(LADG) We conduct comprehensive experiments on the Wilds DG benchmark to validate our approach.
  arXiv  Detail & Related papers  (2022-05-09T08:30:31Z)
• Compound Domain Generalization via Meta-Knowledge Encoding [55.22920476224671]
  We introduce Style-induced Domain-specific Normalization (SDNorm) to re-normalize the multi-modal underlying distributions. We harness the prototype representations, the centroids of classes, to perform relational modeling in the embedding space. Experiments on four standard Domain Generalization benchmarks reveal that COMEN exceeds the state-of-the-art performance without the need of domain supervision.
  arXiv  Detail & Related papers  (2022-03-24T11:54:59Z)
• TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification [115.31432027711202]
  We argue that both domain-specific and domain-invariant features are crucial for improving the generalization ability of re-id models. We name two-stream adaptive learning (TAL) to simultaneously model these two kinds of information. Our framework can be applied to both single-source and multi-source domain generalization tasks.
  arXiv  Detail & Related papers  (2021-11-29T01:27:42Z)
• Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition [15.545769463854915]
  First person action recognition is becoming an increasingly researched area thanks to the rising popularity of wearable cameras. This is bringing to light cross-domain issues that are yet to be addressed in this context. We introduce the first domain generalization approach for egocentric activity recognition, by proposing a new audio-visual loss.
  arXiv  Detail & Related papers  (2021-10-19T16:52:39Z)
• Gradient Matching for Domain Generalization [93.04545793814486]
  A critical requirement of machine learning systems is their ability to generalize to unseen domains. We propose an inter-domain gradient matching objective that targets domain generalization. We derive a simpler first-order algorithm named Fish that approximates its optimization.
  arXiv  Detail & Related papers  (2021-04-20T12:55:37Z)
• Domain Conditioned Adaptation Network [90.63261870610211]
  We propose a Domain Conditioned Adaptation Network (DCAN) to excite distinct convolutional channels with a domain conditioned channel attention mechanism. This is the first work to explore the domain-wise convolutional channel activation for deep DA networks.
  arXiv  Detail & Related papers  (2020-05-14T04:23:24Z)

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.