scholarly journals Domain Conditioned Adaptation Network

2020 ◽  
Vol 34 (07) ◽  
pp. 11386-11393 ◽  
Author(s):  
Shuang Li ◽  
Chi Liu ◽  
Qiuxia Lin ◽  
Binhui Xie ◽  
Zhengming Ding ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
Feature Learning ◽  
Feature Representations ◽  
Domain Specific ◽  
Cross Domain ◽  
Learning Tasks ◽  
Domain Learning ◽  
High Level ◽  
High Level Feature ◽  
Target Data

Tremendous research efforts have been made to thrive deep domain adaptation (DA) by seeking domain-invariant features. Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while integrating a totally shared convolutional architecture for source and target. However, we argue that such strongly-shared convolutional layers might be harmful for domain-specific feature learning when source and target data distribution differs to a large extent. In this paper, we relax a shared-convnets assumption made by previous DA methods and propose a Domain Conditioned Adaptation Network (DCAN), which aims to excite distinct convolutional channels with a domain conditioned channel attention mechanism. As a result, the critical low-level domain-dependent knowledge could be explored appropriately. As far as we know, this is the first work to explore the domain-wise convolutional channel activation for deep DA networks. Moreover, to effectively align high-level feature distributions across two domains, we further deploy domain conditioned feature correction blocks after task-specific layers, which will explicitly correct the domain discrepancy. Extensive experiments on three cross-domain benchmarks demonstrate the proposed approach outperforms existing methods by a large margin, especially on very tough cross-domain learning tasks.

Learning Efficient Binary Codes From High-Level Feature Representations for Multilabel Image Retrieval

2017 ◽  
Vol 19 (11) ◽  
pp. 2545-2560 ◽  
Author(s):  
Lei Ma ◽  
Hongliang Li ◽  
Fanman Meng ◽  
Qingbo Wu ◽  
King Ngi Ngan
Keyword(s):  
Image Retrieval ◽  
Binary Codes ◽  
Feature Representations ◽  
High Level ◽  
High Level Feature

Chapter 4. Graph Reasoning Networks and Applications

2021 ◽  
Author(s):  
Qingxing Cao ◽  
Wentao Wan ◽  
Xiaodan Liang ◽  
Liang Lin
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Domain Knowledge ◽  
Feature Learning ◽  
External Information ◽  
Feature Representations ◽  
Domain Specific ◽  
The Neural Network ◽  
Structured Knowledge ◽  
Knowledge Graphs

Despite the significant success in various domains, the data-driven deep neural networks compromise the feature interpretability, lack the global reasoning capability, and can’t incorporate external information crucial for complicated real-world tasks. Since the structured knowledge can provide rich cues to record human observations and commonsense, it is thus desirable to bridge symbolic semantics with learned local feature representations. In this chapter, we review works that incorporate different domain knowledge into the intermediate feature representation.These methods firstly construct a domain-specific graph that represents related human knowledge. Then, they characterize node representations with neural network features and perform graph convolution to enhance these symbolic nodes via the graph neural network(GNN).Lastly, they map the enhanced node feature back into the neural network for further propagation or prediction. Through integrating knowledge graphs into neural networks, one can collaborate feature learning and graph reasoning with the same supervised loss function and achieve a more effective and interpretable way to introduce structure constraints.

Joint deep feature learning and unsupervised visual domain adaptation for cross-domain 3D object retrieval

2020 ◽  
Vol 57 (5) ◽  
pp. 102275 ◽  
Author(s):  
Wen-Hui Li ◽  
Shu Xiang ◽  
Wei-Zhi Nie ◽  
Dan Song ◽  
An-An Liu ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
Feature Learning ◽  
3D Object Retrieval ◽  
Object Retrieval ◽  
3D Object ◽  
Cross Domain ◽  
Deep Feature ◽  
Deep Feature Learning ◽  
Visual Domain

scholarly journals Exploring the Cross-Domain Action Recognition Problem by Deep Feature Learning and Cross-Domain Learning

IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 68989-69008 ◽  
Author(s):  
Zan Gao ◽  
T. T. Han ◽  
Lei Zhu ◽  
Hua Zhang ◽  
Yinglong Wang
Keyword(s):  
Action Recognition ◽  
Feature Learning ◽  
Recognition Problem ◽  
Cross Domain ◽  
Deep Feature ◽  
Domain Learning ◽  
Deep Feature Learning ◽  
The Cross

scholarly journals Domain Adaptation for Semantic Parsing

2020 ◽  
Author(s):  
Zechang Li ◽  
Yuxuan Lai ◽  
Yansong Feng ◽  
Dongyan Zhao
Keyword(s):  
Domain Adaptation ◽  
Specific Information ◽  
Semantic Parsing ◽  
Target Domain ◽  
Source Domain ◽  
Domain Specific ◽  
The Difference ◽  
Two Stages ◽  
Coarse To Fine ◽  
Target Data

Recently, semantic parsing has attracted much attention in the community. Although many neural modeling efforts have greatly improved the performance, it still suffers from the data scarcity issue. In this paper, we propose a novel semantic parser for domain adaptation, where we have much fewer annotated data in the target domain compared to the source domain. Our semantic parser benefits from a two-stage coarse-to-fine framework, thus can provide different and accurate treatments for the two stages, i.e., focusing on domain invariant and domain specific information, respectively. In the coarse stage, our novel domain discrimination component and domain relevance attention encourage the model to learn transferable domain general structures. In the fine stage, the model is guided to concentrate on domain related details. Experiments on a benchmark dataset show that our method consistently outperforms several popular domain adaptation strategies. Additionally, we show that our model can well exploit limited target data to capture the difference between the source and target domain, even when the target domain has far fewer training instances.

scholarly journals Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction

2021 ◽  
Author(s):  
G. Bellitto ◽  
F. Proietto Salanitri ◽  
S. Palazzo ◽  
F. Rundo ◽  
D. Giordano ◽  
...  
Keyword(s):  
Multiple Scales ◽  
Domain Adaptation ◽  
State Of The Art ◽  
Feature Learning ◽  
Hierarchical Learning ◽  
Domain Specific ◽  
Proposed Model ◽  
Saliency Prediction ◽  
Video Saliency ◽  
Abstraction Levels

AbstractIn this work, we propose a 3D fully convolutional architecture for video saliency prediction that employs hierarchical supervision on intermediate maps (referred to as conspicuity maps) generated using features extracted at different abstraction levels. We provide the base hierarchical learning mechanism with two techniques for domain adaptation and domain-specific learning. For the former, we encourage the model to unsupervisedly learn hierarchical general features using gradient reversal at multiple scales, to enhance generalization capabilities on datasets for which no annotations are provided during training. As for domain specialization, we employ domain-specific operations (namely, priors, smoothing and batch normalization) by specializing the learned features on individual datasets in order to maximize performance. The results of our experiments show that the proposed model yields state-of-the-art accuracy on supervised saliency prediction. When the base hierarchical model is empowered with domain-specific modules, performance improves, outperforming state-of-the-art models on three out of five metrics on the DHF1K benchmark and reaching the second-best results on the other two. When, instead, we test it in an unsupervised domain adaptation setting, by enabling hierarchical gradient reversal layers, we obtain performance comparable to supervised state-of-the-art. Source code, trained models and example outputs are publicly available at https://github.com/perceivelab/hd2s.

scholarly journals Cross-Domain 3D Model Retrieval via Visual Domain Adaption

2018 ◽  
Author(s):  
Anan Liu ◽  
Shu Xiang ◽  
Wenhui Li ◽  
Weizhi Nie ◽  
Yuting Su
Keyword(s):  
Large Scale ◽  
3D Model ◽  
Domain Adaptation ◽  
3D Model Retrieval ◽  
Learning To Learn ◽  
Domain Specific ◽  
Cross Domain ◽  
Model Retrieval ◽  
Modeling Software ◽  
Visual Domain

Recent advances in 3D capturing devices and 3D modeling software have led to extensive and diverse 3D datasets, which usually have different distributions. Cross-domain 3D model retrieval is becoming an important but challenging task. However, existing works mainly focus on 3D model retrieval in a closed dataset, which seriously constrain their implementation for real applications. To address this problem, we propose a novel crossdomain 3D model retrieval method by visual domain adaptation. This method can inherit the advantage of deep learning to learn multi-view visual features in the data-driven manner for 3D model representation. Moreover, it can reduce the domain divergence by exploiting both domainshared and domain-specific features of different domains. Consequently, it can augment the discrimination of visual descriptors for cross-domain similarity measure. Extensive experiments on two popular datasets, under three designed cross-domain scenarios, demonstrate the superiority and effectiveness of the proposed method by comparing against the state-of-the-art methods. Especially, the proposed method can significantly outperform the most recent method for cross-domain 3D model retrieval and the champion of Shrec’16 Large-Scale 3D Shape Retrieval from ShapeNet Core55.

scholarly journals Learning to Track Aircraft in Infrared Imagery

2020 ◽  
Vol 12 (23) ◽  
pp. 3995
Author(s):  
Sijie Wu ◽  
Kai Zhang ◽  
Shaoyi Li ◽  
Jie Yan
Keyword(s):  
Target Tracking ◽  
Signal To Noise Ratio ◽  
Feature Learning ◽  
Tracking Algorithm ◽  
Correlation Filters ◽  
Infrared Imagery ◽  
Feature Representations ◽  
Domain Specific ◽  
Tightly Coupled ◽  
Airborne Target

Airborne target tracking in infrared imagery remains a challenging task. The airborne target usually has a low signal-to-noise ratio and shows different visual patterns. The features adopted in the visual tracking algorithm are usually deep features pre-trained on ImageNet, which are not tightly coupled with the current video domain and therefore might not be optimal for infrared target tracking. To this end, we propose a new approach to learn the domain-specific features, which can be adapted to the current video online without pre-training on a large datasets. Considering that only a few samples of the initial frame can be used for online training, general feature representations are encoded to the network for a better initialization. The feature learning module is flexible and can be integrated into tracking frameworks based on correlation filters to improve the baseline method. Experiments on airborne infrared imagery are conducted to demonstrate the effectiveness of our tracking algorithm.

Supervised High-Level Feature Learning With Label Consistencies for Object Recognition

2020 ◽  
Vol 58 (7) ◽  
pp. 4501-4516 ◽  
Author(s):  
Yuebin Wang ◽  
Xun Zhou ◽  
Honglei Yang ◽  
Liqiang Zhang ◽  
Suhong Liu ◽  
...  
Keyword(s):  
Object Recognition ◽  
Feature Learning ◽  
High Level ◽  
High Level Feature
Sign in / Sign up

Export Citation Format

Share Document