Proceedings ArticleDOI
Open Set Domain Adaptation
Pau Panareda Busto,Juergen Gall +1 more
- pp 754-763
Reads0
Chats0
TLDR
This work learns a mapping from the source to the target domain by jointly solving an assignment problem that labels those target instances that potentially belong to the categories of interest present in the source dataset.Abstract:
When the training and the test data belong to different domains, the accuracy of an object classifier is significantly reduced. Therefore, several algorithms have been proposed in the last years to diminish the so called domain shift between datasets. However, all available evaluation protocols for domain adaptation describe a closed set recognition task, where both domains, namely source and target, contain exactly the same object classes. In this work, we also explore the field of domain adaptation in open sets, which is a more realistic scenario where only a few categories of interest are shared between source and target data. Therefore, we propose a method that fits in both closed and open set scenarios. The approach learns a mapping from the source to the target domain by jointly solving an assignment problem that labels those target instances that potentially belong to the categories of interest present in the source dataset. A thorough evaluation shows that our approach outperforms the state-of-the-art.read more
Citations
More filters
Posted Content
Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation
TL;DR: In this paper, the authors propose a novel loss function, i.e., Conservative Loss, which penalizes the extreme good and bad cases while encouraging the moderate examples and enables the network to learn features that are discriminative by gradient descent and are invariant to the change of domains via gradient ascend method.
Journal ArticleDOI
CDTD: A Large-Scale Cross-Domain Benchmark for Instance-Level Image-to-Image Translation and Domain Adaptive Object Detection
Zhiqiang Shen,Mingyang Huang,Jianping Shi,Zechun Liu,Harsh Maheshwari,Yutong Zheng,Xiangyang Xue,Marios Savvides,Thomas S. Huang +8 more
TL;DR: A large-scale cross-domain benchmark CDTD is introduced and a novel instance-level image-to-image translation approach called INIT and a gradient detach method for the domain adaptive object detection to harvest and exert dataset’s function of the instance level annotations across different domains is proposed.
Posted Content
Unsupervised Domain Adaptation for 3D Keypoint Prediction from a Single Depth Scan.
TL;DR: A novel unsupervised domain adaptation technique for the task of 3D keypoint prediction from a single depth scan/image based on the fact that predictions from different views of the same or similar objects should be consistent with each other is introduced.
Proceedings ArticleDOI
Domain-robust VQA with diverse datasets and methods but no target labels
TL;DR: In this paper, the authors quantify domain shifts between popular VQA datasets, in both visual and textual space, and test the robustness of different families of visual question answering methods (two-stream, transformer and neuro-symbolic) to these shifts.
Posted Content
Strong-Weak Distribution Alignment for Adaptive Object Detection
TL;DR: In this article, the authors propose an approach for unsupervised adaptation of object detectors from label-rich to label-poor domains, which can significantly reduce annotation costs associated with detection.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal ArticleDOI
LIBSVM: A library for support vector machines
Chih-Chung Chang,Chih-Jen Lin +1 more
TL;DR: Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.
Proceedings Article
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
TL;DR: DeCAF as discussed by the authors is an open-source implementation of these deep convolutional activation features, along with all associated network parameters, to enable vision researchers to conduct experimentation with deep representations across a range of visual concept learning paradigms.
Posted Content
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
TL;DR: DeCAF, an open-source implementation of deep convolutional activation features, along with all associated network parameters, are released to enable vision researchers to be able to conduct experimentation with deep representations across a range of visual concept learning paradigms.
Posted Content
Learning Transferable Features with Deep Adaptation Networks
TL;DR: A new Deep Adaptation Network (DAN) architecture is proposed, which generalizes deep convolutional neural network to the domain adaptation scenario and can learn transferable features with statistical guarantees, and can scale linearly by unbiased estimate of kernel embedding.