Adaptive pedestrian detection by predicting classifier

Tang, Song; Ye, Mao; Xu, Pei; Li, Xudong

doi:10.1007/s00521-017-3152-z

Cited by 9 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second focuses on mining transferable factors that are suitable for both domains. [25] supposed that a sample and its exemplar classifier (SVM) satisfy a certain mapping relationship. Following this idea, this method learned the mapping on the source domain and predicted the classifier for each target sample to perform an individual classification.…”

Section: B Source Data-absent Unsupervised Domain Adaptationmentioning

confidence: 99%

Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation

Tang,

Yang,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In the classic setting of unsupervised domain adaptation (UDA), the labeled source data are available in the training phase. However, in many real-world scenarios, owing to some reasons such as privacy protection and information security, the source data is inaccessible, and only a model trained on the source domain is available. This paper proposes a novel deep clustering method for this challenging task. Aiming at the dynamical clustering at feature-level, we introduce extra constraints hidden in the geometric structure between data to assist the process. Concretely, we propose a geometry-based constraint, named semantic consistency on the nearest neighborhood (SCNNH), and use it to encourage robust clustering. To reach this goal, we construct the nearest neighborhood for every target data and take it as the fundamental clustering unit by building our objective on the geometry. Also, we develop a more SCNNH-compliant structure with an additional semantic credibility constraint, named semantic hyper-nearest neighborhood (SHNNH). After that, we extend our method to this new geometry. Extensive experiments on three challenging UDA datasets indicate that our

show abstract

Section: B Source Data-absent Unsupervised Domain Adaptationmentioning

confidence: 99%

Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation

Tang,

Yang,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this case, there exist two subcategories. The first subcategory does not have source samples, such as some meta learning methods [15], [16]. While the other subcategories have source domain data.…”

Section: Introductionmentioning

confidence: 99%

Cycle-Consistent Domain Adaptive Faster RCNN

Zhang

Xiong

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

Traditional object detection methods always assume both of the training and test data follow the same distribution, but this cannot always be guaranteed in the real world. Domain adaptive methods are proposed to handle this situation. However, existing methods generally ignore the semantic alignment at feature level when they try to align data distributions between source and target domains. In this paper, we propose a novel unsupervised cross-domain object detection method, named Cycle-consistent domain Adaptive Faster RCNN (CA-FRCNN). A couple of Generative Adversarial Nets (GAN) are used to make the features from two domains consistent at both data distribution level and semantic level. Specifically, features from source domain are transformed to the target domain. Then they are aligned with features from target domain. At the same time, target features are handled with similar operations. Furthermore, a cycleconsistent loss is optimized to guarantee that the semantic information is preserved before and after the style translations. In the end, identity module is used to make the feature in source domain equivalent to the reconstructed feature output by the source generator, whose input is from the source domain. For the feature in the target domain, similar identity is required. Experiments on multiple datasets show that our method performs better than previous state-of-the-art methods. INDEX TERMS Domain adaptive object detection, generative adversarial net, semantic information.

show abstract