Semantic Feature Learning for Universal Unsupervised Cross-Domain Retrieval

• URL: http://arxiv.org/abs/2403.05690v1
• Date: Fri, 8 Mar 2024 21:56:00 GMT
• Title: Semantic Feature Learning for Universal Unsupervised Cross-Domain Retrieval
• Authors: Lixu Wang, Xinyu Du, Qi Zhu
• Abstract summary: We introduce the problem of Universal Unsupervised Cross-Domain Retrieval (U2CDR) for the first time. In the first stage, a cross-domain unified structure is established under the guidance of an instance-prototype-mixed contrastive loss. In the second stage, through a modified adversarial training mechanism, we ensure minimal changes for the established prototypical structure during domain alignment.
• Score: 10.270998709614538
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cross-domain retrieval (CDR), as a crucial tool for numerous technologies, is finding increasingly broad applications. However, existing efforts face several major issues, with the most critical being the need for accurate supervision, which often demands costly resources and efforts. Cutting-edge studies focus on achieving unsupervised CDR but typically assume that the category spaces across domains are identical, an assumption that is often unrealistic in real-world scenarios. This is because only through dedicated and comprehensive analysis can the category spaces of different domains be confirmed as identical, which contradicts the premise of unsupervised scenarios. Therefore, in this work, we introduce the problem of Universal Unsupervised Cross-Domain Retrieval (U^2CDR) for the first time and design a two-stage semantic feature learning framework to address it. In the first stage, a cross-domain unified prototypical structure is established under the guidance of an instance-prototype-mixed contrastive loss and a semantic-enhanced loss, to counteract category space differences. In the second stage, through a modified adversarial training mechanism, we ensure minimal changes for the established prototypical structure during domain alignment, enabling more accurate nearest-neighbor searching. Extensive experiments across multiple datasets and scenarios, including closet, partial, and open-set CDR, demonstrate that our approach significantly outperforms existing state-of-the-art CDR works and some potentially effective studies from other topics in solving U^2CDR challenges.

Related papers

• A Unified Framework for Cross-Domain Recommendation [15.987800946057343]
  Cross-Domain Recommendation emerges as a promising methodology. We extend the former SOTA model UniCDR in five different aspects, named as UniCDR+. Our work was successfully deployed on the Kuaishou Living-Room RecSys.
  arXiv  Detail & Related papers  (2024-09-06T18:10:42Z)
• Understanding the Cross-Domain Capabilities of Video-Based Few-Shot Action Recognition Models [3.072340427031969]
  Few-shot action recognition (FSAR) aims to learn a model capable of identifying novel actions in videos using only a few examples. In assuming the base dataset seen during meta-training and novel dataset used for evaluation can come from different domains, cross-domain few-shot learning alleviates data collection and annotation costs. We systematically evaluate existing state-of-the-art single-domain, transfer-based, and cross-domain FSAR methods on new cross-domain tasks.
  arXiv  Detail & Related papers  (2024-06-03T07:48:18Z)
• DIGIC: Domain Generalizable Imitation Learning by Causal Discovery [69.13526582209165]
  Causality has been combined with machine learning to produce robust representations for domain generalization. We make a different attempt by leveraging the demonstration data distribution to discover causal features for a domain generalizable policy. We design a novel framework, called DIGIC, to identify the causal features by finding the direct cause of the expert action from the demonstration data distribution.
  arXiv  Detail & Related papers  (2024-02-29T07:09:01Z)
• Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining [81.09446228688559]
  Cross-Domain Few-Shots (CD-FSS) poses the challenge of segmenting novel categories from a distinct domain using only limited exemplars. We propose a novel cross-domain fine-tuning strategy that addresses the challenging CD-FSS tasks.
  arXiv  Detail & Related papers  (2024-01-16T14:45:41Z)
• Unified Domain Adaptive Semantic Segmentation [96.74199626935294]
  Unsupervised Adaptive Domain Semantic (UDA-SS) aims to transfer the supervision from a labeled source domain to an unlabeled target domain. We propose a Quad-directional Mixup (QuadMix) method, characterized by tackling distinct point attributes and feature inconsistencies. Our method outperforms the state-of-the-art works by large margins on four challenging UDA-SS benchmarks.
  arXiv  Detail & Related papers  (2023-11-22T09:18:49Z)
• Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency [90.71745178767203]
  Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets. Existing 3D domain adaptive detection methods often assume prior access to the target domain annotations, which is rarely feasible in the real world. We study a more realistic setting, unsupervised 3D domain adaptive detection, which only utilizes source domain annotations.
  arXiv  Detail & Related papers  (2021-07-23T17:19:23Z)
• Unsupervised Domain Adaptation Network with Category-Centric Prototype Aligner for Biomedical Image Segmentation [1.1799563040751586]
  We present a novel unsupervised domain adaptation network for generalizing models learned from the labeled source domain to the unlabeled target domain. Specifically, our approach consists of two key modules, a conditional domain discriminator(CDD) and a category-centric prototype aligner(CCPA)
  arXiv  Detail & Related papers  (2021-03-03T07:07:38Z)
• 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)
• Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learning [109.42987031347582]
  Face presentation attack detection (PAD) has been an urgent problem to be solved in the face recognition systems. We propose an efficient disentangled representation learning for cross-domain face PAD. Our approach consists of disentangled representation learning (DR-Net) and multi-domain learning (MD-Net)
  arXiv  Detail & Related papers  (2020-04-04T15:45:14Z)
• Unsupervised Domain Adaptation via Discriminative Manifold Embedding and Alignment [23.72562139715191]
  Unsupervised domain adaptation is effective in leveraging the rich information from the source domain to the unsupervised target domain. The hard-assigned pseudo labels on the target domain are risky to the intrinsic data structure. A consistent manifold learning framework is proposed to achieve transferability and discriminability consistently.
  arXiv  Detail & Related papers  (2020-02-20T11:06:41Z)

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.