paper-with-me

Papers

Instance-level Heterogeneous Domain Adaptation for Limited-labeled Sketch-to-Photo Retrieval

2022-11-26 · IEEE Transactions on Multimedia 2020 7 · Fan Yang, Yang Wu, Zheng Wang, Xiang Li, Sakriani Sakti, Satoshi Nakamura

Although sketch-to-photo retrieval has a wide range of applications, it is costly to obtain paired and rich-labeled ground truth. Differently, photo retrieval data is easier to acquire. Therefore, previous works pre-train their models on rich-labeled photo retrieval data (i.e., source domain) and then fine-tune them on the limited-labeled sketch-to-photo retrieval data (i.e., target domain). However, without co-training source and target data, source domain knowledge might be forgotten during the fine-tuning process, while simply co-training them may cause negative transfer due to domain gaps. Moreover, identity label spaces of source data and target data are generally disjoint and therefore conventional category-level Domain Adaptation (DA) is not directly applicable. To address these issues, we propose an Instance-level Heterogeneous Domain Adaptation (IHDA) framework. We apply the fine-tuning strategy for identity label learning, aiming to transfer the instance-level knowledge in an inductive transfer manner. Meanwhile, labeled attributes from the source data are selected to form a shared label space for source and target domains. Guided by shared attributes, DA is utilized to bridge cross-dataset domain gaps and heterogeneous domain gaps, which transfers instance-level knowledge in a transductive transfer manner. Experiments show that our method has set a new state of the art on three sketch-to-photo image retrieval benchmarks without extra annotations, which opens the door to train more effective models on limited-labeled heterogeneous image retrieval tasks. Related codes are available at https://github.com/fandulu/IHDA.

📄 PDF Abstract BibTeX arXiv:2211.14515

Code (1)

fandulu/IHDA 공식 구현 pytorch

Tasks

Domain AdaptationImage RetrievalRetrieval

Similar Papers 제목 키워드 기반

Locality Preserving Joint Transfer for Domain Adaptation

2019-06-18 · Li Jingjing, Jing Mengmeng, Lu Ke, Zhu Lei 외

Domain adaptation aims to leverage knowledge from a well-labeled source domain to a poorly-labeled target domain. A majority of existing works transfer the knowledge at either feature level or sample level. Recent resear…

Domain AdaptationTransfer Learning

BEACON: Cross-Domain Co-Training of Generative Robot Policies via Best-Effort Adaptation

2026-05-09 · Antong Zhang, Han Qi, Heng Yang arxiv

We introduce BEACON--Best-Effort Adaptation for Cross-Domain Co-Training--a theory-driven framework for training generative robot policies with abundant source demonstrations and limited target demonstrations. BEACON cas…

Domain Generalization

MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection

2023-09-03 · Onkar Krishna, Hiroki Ohashi, Saptarshi Sinha

Cross-domain object detection is challenging, and it involves aligning labeled source and unlabeled target domains. Previous approaches have used adversarial training to align features at both image-level and instance-le…

Domain Adaptationobject-detectionObject DetectionUnsupervised Domain Adaptation

MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection

2023-11-20 · Onkar Krishna; Hiroki Ohashi; Saptarshi Sinha

Cross-domain object detection is challenging, and it involves aligning labeled source and unlabeled target domains. Previous approaches have used adversarial training to align features at both image-level and instance-le…

Domain Adaptationobject-detectionObject Detection

Prototype and Instance Contrastive Learning for Unsupervised Domain Adaptation in Speaker Verification

2024-10-22 · Wen Huang, Bing Han, Zhengyang Chen, Shuai Wang 외

Speaker verification system trained on one domain usually suffers performance degradation when applied to another domain. To address this challenge, researchers commonly use feature distribution matching-based methods in…

Contrastive LearningDomain AdaptationSpeaker VerificationUnsupervised Domain Adaptation