Domain Adaptation of Deformable Part-Based Models

By Jiaolong Xu, Sebastian Ramos, David Vázquez, A. L. Peña. 2014

153 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Recognition in Terra Incognita (2018, methodology): “[48,49,50,51,52] look at methods for adapting detectors from one data source to another, such as from synthetic to real data or from images to video.”
LSDA: Large Scale Detection through Adaptation (2014, methodology): “Each of these steps adds between 1-2mAP at high computation cost and using the SVMs removes the adaptation capacity of the system.”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “26 Domain Adaptation of DPM based on SA-SSVM [251] (Image courtesy J.”
Domain Adaptive Faster R-CNN for Object Detection in the Wild (2018, methodology): “For the task of detection, [58] proposed to mitigate the domain shift problem of the deformable part-based model (DPM) by introducing an adaptive SVM.”
Heterogeneous Graph Attention Network for Unsupervised Multiple-Target Domain Adaptation (2020, background): “ing model for label-deficient domains (target domains) by feat of available labeled data from the other domains (source domains) to alleviate such insufficiency, which is the basic definition in domain adaptation (DA) [2].”
Subspace Alignment Based Domain Adaptation for RCNN Detector (2015, methodology): “applicable to object detection has been the adaptation of Deformable Part Models for object detection [9].”
The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes (2016, background): “On the other hand, it is known that classifiers trained only with virtual images may require domain adaptation to work on real images [42] [44] [37] [25] [45]; however, it has been shown that this is just because virtual and real world cameras are different sensors, i.e. domain adaptation is also…”
From Virtual to Reality: Fast Adaptation of Virtual Object Detectors to Real Domains (2014, methodology): “LDA was shown in [10] to have competitive performance to SVM, and can be implemented both as an exemplar-based [16] or as deformable parts model (DPM) [5] .”
Few-Shot Adaptive Faster R-CNN (2019, background): “[45] proposed a framework to mitigate the domain shift problem of deformable part-based model (DPM).”
Recognizing Actions Through Action-Specific Person Detection (2015, methodology): “Domain adaptation techniques are designed to tackle these situations [20], [22], [34], [41], [42].”
DOCK: Detecting Objects by Transferring Common-Sense Knowledge (2018, background): “Existing transfer learning approaches can be roughly divided into two groups: one that learns using bounding box annotations for both source and target categories [36,3,21,11,43,40], and another that learns using bounding box annotations for source categories but only image-level annotations for tar”
Pedestrian Detection at Day/Night Time with Visible and FIR Cameras: A Comparison (2016, background): “and even alternative approaches like generative classifiers [28], active learning [29], and domain adaptation [30,31].”