Domain Generalization and Adaptation Using Low Rank Exemplar SVMs

Wen, Li; Xu, Zheng; Xu, Dong; Dai, Dengxin; Gool, Luc Van

doi:10.1109/tpami.2017.2704624

Cited by 126 publications

(63 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, we compared our DAESVM with unsupervised domain adaptation methods, such as TCA or GFK, implemented to use the same dimension reduction with the parameter in our model. At last, we also compared DAESVM with newly transfer learning models, like low-rank ESVMs [18]. Overall, in a usual transfer learning way, we run datasets across different pairs of source and target domain.…”

Section: Experiments Resultsmentioning

confidence: 99%

“…(1) Transfer Component Analysis (TCA) [40] (2) Support Vector Machine (SVM) [43] (3) Geodesic Flow Kernel (GFK) [28] (4) Landmarks Selection-based Subspace Alignment (LSSA) [23] (5) Kernel Mean Maximum (KMM) [20] (6) Subspace Alignment (SA) [44] (7) Joint Matching Transfer (TJM) [45] (8) Low-Rank Exemplar-SVMs (LRESVMs) [18] TCA, GFK, and KMM are the classical transfer learning methods. We compare our model with these methods.…”

Section: Experiments Setupmentioning

confidence: 99%

“…Each exemplar-SVMs classifier is trained on a high weight positive sample and other negative samples; it can represent the positive sample well in the same distribution. Recently, [18] extends exemplar-SVMs into a transfer learning form which uses loss function reweighting and adds a low-rank regularization item for classifiers.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Unsupervised Domain Adaptation Using Exemplar‐SVMs with Adaptation Regularization

Tian

Tang

et al. 2018

Complexity

View full text Add to dashboard Cite

Domain adaptation has recently attracted attention for visual recognition. It assumes that source and target domain data are drawn from the same feature space but different margin distributions and its motivation is to utilize the source domain instances to assist in training a robust classifier for target domain tasks. Previous studies always focus on reducing the distribution mismatch across domains. However, in many real-world applications, there also exist problems of sample selection bias among instances in a domain; this would reduce the generalization performance of learners. To address this issue, we propose a novel model named Domain Adaptation Exemplar Support Vector Machines (DAESVMs) based on exemplar support vector machines (exemplar-SVMs). Our approach aims to address the problems of sample selection bias and domain adaptation simultaneously. Comparing with usual domain adaptation problems, we go a step further in slacking the assumption of i.i.d. First, we formulate the DAESVMs training classifiers with reducing Maximum Mean Discrepancy (MMD) among domains by mapping data into a latent space and preserving properties of original data, and then, we integrate classifiers to make a prediction for target domain instances. Our experiments were conducted on Office and Caltech10 datasets and verify the effectiveness of the model we proposed.

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

Section: Experiments Setupmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Domain Adaptation Using Exemplar‐SVMs with Adaptation Regularization

Tian

Tang

et al. 2018

Complexity

View full text Add to dashboard Cite

show abstract

“…Consequently, we base our improvements on Faster R-CNN, a slower, but accurate detector. 1 Domain Adaptation: was initially studied for image classification and the majority of the domain adaptation literature focuses on this problem [10,9,29,21,20,12,48,32,33,14,13,17,1,37,30]. Some of the methods developed in this context include cross-domain kernel learning methods such as adaptive multiple kernel learning (A-MKL) [10], domain transfer multiple kernel learning (DTMKL) [9], and geodesic flow kernel (GFK) [20].…”

Section: Previous Workmentioning

confidence: 99%

A Robust Learning Approach to Domain Adaptive Object Detection

Khodabandeh

Vahdat

Ranjbar³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

252

160

View full text Add to dashboard Cite

Domain shift is unavoidable in real-world applications of object detection. For example, in self-driving cars, the target domain consists of unconstrained road environments which cannot all possibly be observed in training data. Similarly, in surveillance applications sufficiently representative training data may be lacking due to privacy regulations. In this paper, we address the domain adaptation problem from the perspective of robust learning and show that the problem may be formulated as training with noisy labels. We propose a robust object detection framework that is resilient to noise in bounding box class labels, locations and size annotations. To adapt to the domain shift, the model is trained on the target domain using a set of noisy object bounding boxes that are obtained by a detection model trained only in the source domain. We evaluate the accuracy of our approach in various source/target domain pairs and demonstrate that the model significantly improves the state-of-the-art on multiple domain adaptation scenarios on the SIM10K, Cityscapes and KITTI datasets.

show abstract

“…However, in real world, it is impossible to guarantee that assumption. Hence, in visual recognition tasks, classifier or model usually does not work well because of data bias between the distributions of the training and test data [1], [2] [3], [4], [5], [6], [7]. The domain discrepancy constitutes a major obstacle in training the predictive models across domains.…”

mentioning

confidence: 99%

Manifold Criterion Guided Transfer Learning via Intermediate Domain Generation

Zhang

Wang

Huang

et al. 2019

IEEE Trans. Neural Netw. Learning Syst.

103

View full text Add to dashboard Cite

In many practical transfer learning scenarios, the feature distribution is different across the source and target domains (i.e. non-i.i.d.). Maximum mean discrepancy (MMD), as a domain discrepancy metric, has achieved promising performance in unsupervised domain adaptation (DA). We argue that MMD-based DA methods ignore the data locality structure, which, to some extent, would cause the negative transfer effect. The locality plays an important role in minimizing the nonlinear local domain discrepancy underlying the marginal distributions. For better exploiting the domain locality, a novel local generative discrepancy metric (LGDM) based intermediate domain generation learning called Manifold Criterion guided Transfer Learning (MCTL) is proposed in this paper. The merits of the proposed MCTL are four-fold: 1) the concept of manifold criterion (MC) is first proposed as a measure validating the distribution matching across domains, and domain adaptation is achieved if the MC is satisfied; 2) the proposed MC can well guide the generation of the intermediate domain sharing similar distribution with the target domain, by minimizing the local domain discrepancy; 3) a global generative discrepancy metric (GGDM) is presented, such that both the global and local discrepancy can be effectively and positively reduced; 4) a simplified version of MCTL called MCTL-S is presented under a perfect domain generation assumption for more generic learning scenario. Experiments on a number of benchmark visual transfer tasks demonstrate the superiority of the proposed manifold criterion guided generative transfer method, by comparing with other state-of-the-art methods. The source code is available in https://github.com/wangshanshanCQU/MCTL.

show abstract

Domain Generalization and Adaptation Using Low Rank Exemplar SVMs

Cited by 126 publications

References 32 publications

Unsupervised Domain Adaptation Using Exemplar‐SVMs with Adaptation Regularization

Unsupervised Domain Adaptation Using Exemplar‐SVMs with Adaptation Regularization

A Robust Learning Approach to Domain Adaptive Object Detection

Manifold Criterion Guided Transfer Learning via Intermediate Domain Generation

Contact Info

Product

Resources

About