Filters








57,033 Hits in 7.0 sec

An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection [article]

Jia Liu, Wenjie Xuan, Yuhang Gan, Juhua Liu, Bo Du
2022 arXiv   pre-print
In this paper, we propose an end-to-end Supervised Domain Adaptation framework for cross-domain Change Detection, namely SDACD, to effectively alleviate the domain shift between bi-temporal images for  ...  As to feature adaptation, we extract domain-invariant features to align different feature distributions in the feature space, which could further reduce the domain gap of cross-domain images.  ...  Our contributions can be summarized as follows:  We propose a novel supervised domain adaptation framework SDACD for cross-domain change detection.  ... 
arXiv:2204.00154v2 fatcat:fhm2xzzierhilhwpal35nxkuau

Place recognition survey: An update on deep learning approaches [article]

Tiago Barros, Ricardo Pereira, Luís Garrote, Cristiano Premebida, Urbano J. Nunes
2022 arXiv   pre-print
Some lessons learned from this survey include: the importance of NetVLAD for supervised end-to-end learning; the advantages of unsupervised approaches in place recognition, namely for cross-domain applications  ...  This survey proceeds by elaborating on the various DL-based works, presenting summaries for each framework.  ...  To learn domain-invariant features for cross-domain visual place recognition, Wang et al. [160] propose an approach that combines weakly supervised learning with unsupervised learning.  ... 
arXiv:2106.10458v3 fatcat:bbfv4qympffaphojhxkc4og4am

Progressive Domain Adaptation for Change Detection Using Season-Varying Remote Sensing Images

Rong Kou, Bo Fang, Gang Chen, Lizhe Wang
2020 Remote Sensing  
All these problems pose great challenges for season-varying change detection because the real and seasonal variation-induced changes are technically difficult to separate by a single end-to-end model.  ...  (PDA), for change detection using season-varying remote sensing images.  ...  Figure 2 . 2 Framework of our proposed progressive domain adaptation method for change detection using season-varying remote sensing images.  ... 
doi:10.3390/rs12223815 fatcat:zdtczfjhsfet5cv4bxx6gvsyii

Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning [article]

Fuxun Yu, Di Wang, Yinpeng Chen, Nikolaos Karianakis, Tong Shen, Pei Yu, Dimitrios Lymberopoulos, Sidi Lu, Weisong Shi, Xiang Chen
2021 arXiv   pre-print
To overcome this limitation, we propose the Cross-Domain Semi-Supervised Learning (CDSSL) framework by leveraging high-quality pseudo labels to learn better representations from the target domain directly  ...  To enable SSL for cross-domain object detection, we propose fine-grained domain transfer, progressive-confidence-based label sharpening and imbalanced sampling strategy to address two challenges: (i) non-identical  ...  Conclusion In this work, we propose CDSSL: a cross-domain semisupervised learning framework to address the unsupervised domain adaptation for object detection.  ... 
arXiv:1911.07158v5 fatcat:avo3zydua5dalo7e6ggnik3wuy

Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training [article]

Zhenyu Li, Zehui Chen, Ang Li, Liangji Fang, Qinhong Jiang, Xianming Liu, Junjun Jiang
2022 arXiv   pre-print
Then, we propose STMono3D, a new self-teaching framework for unsupervised domain adaptation on Mono3D.  ...  However, drastic performance degradation remains an unwell-studied challenge for practical cross-domain deployment as the lack of labels on the target domain.  ...  Hence, some methods propose to design the framework in an end-to-end manner like 2D detection.  ... 
arXiv:2204.11590v2 fatcat:oho5oi4go5fxtavavfkqeoiqme

Sim-to-Real Domain Adaptation for Lane Detection and Classification in Autonomous Driving [article]

Chuqing Hu, Sinclair Hudson, Martin Ethier, Mohammad Al-Sharman, Derek Rayside, William Melek
2022 arXiv   pre-print
While supervised detection and classification frameworks in autonomous driving require large labelled datasets to converge, Unsupervised Domain Adaptation (UDA) approaches, facilitated by synthetic data  ...  The proposed UDA frameworks take the synthesized dataset with labels as the source domain, whereas the target domain is the unlabelled real-world data.  ...  Lane Detection Model As we apply the proposed sim-to-real algorithm for lane detection, we adopt an end-to-end approach and use Ultra-Fast-Lane-Detection (UFLD) [30] as our base network.  ... 
arXiv:2202.07133v2 fatcat:s2fvrdppprf65pp2i7dtb2q5da

Multi-Level Alignment Network for Cross-Domain Ship Detection

Chujie Xu, Xiangtao Zheng, Xiaoqiang Lu
2022 Remote Sensing  
The entire multi-level alignment network is trained end-to-end and its effectiveness is proved on multiple cross-domain ship detection datasets.  ...  To address the above limitations, this paper explores a cross-domain ship detection task, which adapts the detector from labeled optical images to unlabeled SAR images.  ...  The cross-domain ship detection task. Full supervision is given in the optical domain while no supervision is available in the SAR domain.  ... 
doi:10.3390/rs14102389 fatcat:7kpa4oprojcdnkmwuzffsxtebq

Cycle and Self-Supervised Consistency Training for Adapting Semantic Segmentation of Aerial Images

Han Gao, Yang Zhao, Peng Guo, Zihao Sun, Xiuwan Chen, Yunwei Tang
2022 Remote Sensing  
To this end, we proposed an unsupervised domain adaptation framework for RS image semantic segmentation that is both practical and effective.  ...  We enforce consistency of model predictions across target image transformations in order to provide self-supervision for the unlabeled target data.  ...  Acknowledgments: Our sincere gratitude goes to the anonymous reviewers for the constructive comments and suggestions that have helped improve this paper substantially.  ... 
doi:10.3390/rs14071527 doaj:3e371156360c450ea7b23f242d99e34f fatcat:offdwang4va2hbolpbcwu2mp44

Deep Learning for Face Anti-Spoofing: A Survey [article]

Zitong Yu, Yunxiao Qin, Xiaobai Li, Chenxu Zhao, Zhen Lei, Guoying Zhao
2022 arXiv   pre-print
It covers several novel and insightful components: 1) besides supervision with binary label (e.g., '0' for bonafide vs. '1' for PAs), we also investigate recent methods with pixel-wise supervision (e.g  ...  ., pseudo depth map); 2) in addition to traditional intra-dataset evaluation, we collect and analyze the latest methods specially designed for domain generalization and open-set FAS; and 3) besides commercial  ...  Fig. 8 : 8 Fig. 8: Traditional end-to-end deep learning frameworks for FAS. (a) Direct supervision with binary cross entropy loss. (b) Pixel-wise supervision with auxiliary tasks.  ... 
arXiv:2106.14948v2 fatcat:wsheo7hbwvewhjoe6ykwjuqfii

Self-Adversarial Disentangling for Specific Domain Adaptation [article]

Qianyu Zhou, Qiqi Gu, Jiangmiao Pang, Zhengyang Feng, Guangliang Cheng, Xuequan Lu, Jianping Shi, Lizhuang Ma
2021 arXiv   pre-print
Domain adaptation aims to bridge the domain shifts between the source and target domains. These shifts may span different dimensions such as fog, rainfall, etc.  ...  To address the problem, we propose a novel Self-Adversarial Disentangling (SAD) framework.  ...  End-to-End Training and Inference In this section, we will briefly introduce the inter-domain adaptation, the task loss and formulate an overall loss function for end-to-end training.  ... 
arXiv:2108.03553v2 fatcat:ce4hubfkf5ga7ee2xdxhojhwiq

Unsupervised Domain Adaptation of Object Detectors: A Survey [article]

Poojan Oza, Vishwanath A. Sindagi, Vibashan VS, Vishal M. Patel
2021 arXiv   pre-print
Here, we describe in detail the domain adaptation problem for detection and present an extensive survey of the various methods.  ...  There is a plethora of works to adapt classification and segmentation models to label-scarce target datasets through unsupervised domain adaptation.  ...  [121] Adversarial feature learning Image-to-image translation Domain randomization Roychowdhury et al. [61] Khodabandeh et al. [62] Kim et al. [97] D'Innocente et al.  ... 
arXiv:2105.13502v2 fatcat:ozzbbvoflfdvjdewjnjmfajlpa

A Survey on Label-efficient Deep Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction [article]

Wei Shen, Zelin Peng, Xuehui Wang, Huayu Wang, Jiazhong Cen, Dongsheng Jiang, Lingxi Xie, Xiaokang Yang, Qi Tian
2022 arXiv   pre-print
To this end, we first develop a taxonomy to organize these methods according to the supervision provided by different types of weak labels (including no supervision, coarse supervision, incomplete supervision  ...  Next, we summarize the existing label-efficient segmentation methods from a unified perspective that discusses an important question: how to bridge the gap between weak supervision and dense prediction  ...  [138] firstly brought the framework of selftraining to domain adaptive semantic segmentation.  ... 
arXiv:2207.01223v1 fatcat:i7rgpxrfkrdbfm4effjdcjjr24

Joint Distribution Alignment via Adversarial Learning for Domain Adaptive Object Detection [article]

Bo Zhang, Tao Chen, Bin Wang, Ruoyao Li
2022 arXiv   pre-print
First, an end-to-end joint adversarial adaptation framework for object detection is proposed, which aligns both marginal and conditional distributions between domains without introducing any extra hyperparameter  ...  In this paper, we propose a joint adaptive detection framework (JADF) to address the above challenges.  ...  and conditional adaptation approach to construct an end-to-end joint domain adaptive detection framework. 1) Detection Module: Given images s x from the source domain and the feature extractor (backbone  ... 
arXiv:2109.09033v2 fatcat:rsvajbh3vfecdd6v4raenm7zym

2020 Index IEEE/ACM Transactions on Audio, Speech, and Language Processing Vol. 28

2020 IEEE/ACM Transactions on Audio Speech and Language Processing  
Zhang, M., +, TASLP 2020 785-797 Modular End-to-End Automatic Speech Recognition Framework for Acous- tic-to-Word Model.  ...  Weis, C., +, TASLP 2020 2919-2932 Modular End-to-End Automatic Speech Recognition Framework for Acous- tic-to-Word Model.  ...  T Target tracking Multi-Hypothesis Square-Root Cubature Kalman Particle Filter for Speaker Tracking in Noisy and Reverberant Environments. Zhang, Q., +, TASLP 2020 1183 -1197  ... 
doi:10.1109/taslp.2021.3055391 fatcat:7vmstynfqvaprgz6qy3ekinkt4

OA-FSUI2IT: A Novel Few-Shot Cross Domain Object Detection Framework with Object-Aware Few-Shot Unsupervised Image-to-Image Translation

Lifan Zhao, Yunlong Meng, Lin Xu
2022 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Day-to-Night, and Cross-scene adaptation.  ...  In this paper, we propose an Object-Aware Few-Shot UI2I Translation (OA-FSUI2IT) framework to address the few-shot cross domain (FSCD) object detection task with limited unlabeled images in the target  ...  We assume that applying an augment transform pair, (T G , T −1 G ), on the input end and output end, respectively, should not change the synthesized result, i.e., G s→t (x s ) = T −1 G (G s→t (T G (x s  ... 
doi:10.1609/aaai.v36i3.20253 fatcat:wgqmie7zrvgdlazamy7ze6fmoq
« Previous Showing results 1 — 15 out of 57,033 results