Beyond classical domain-specific adversarial training, a recently proposed task-specific framework has achieved a great success in single source domain adaptation by utilizing task-specific decision boundaries. Howeve...
Beyond classical domain-specific adversarial training, a recently proposed task-specific framework has achieved a great success in single source domain adaptation by utilizing task-specific decision boundaries. However, compared to single-source-single-target setting, multi-source domain adaptation (MDA) shows more powerful capability to handle with most real-life cases. To align target domain with diverse multi-source domains using task-specific decision boundaries, we provide a deep insight of task-specific framework on MDA for the first time. Accordingly, we propose a novel task-specific multi-source domain adaptation method (TMDA) with a clustering embedded adversarial training process. Specifically, the proposed TMDA detects and refines less discriminative target representations through a max-min optimization over two adversarial task-specific classifiers. Moreover, our analysis implies that scattered multi-source representations disturb the adversarial training under the task-specific framework. To tight up the dispersed source representations, we embeds a relationship-based domain clustering into TMDA. Empirical results demonstrate that our TMDA outperforms state-of-the-art methods on toy dataset, sentiment analysis and digit classification.
The aim of multi-agent reinforcement learning systems is to provide interacting agents with the ability to collaboratively learn and adapt to the behavior of other agents. In many real-world applications, the agents c...
详细信息
Deduplication is a data redundancy elimination technique, designed to save system storage resources by reducing redundant data in cloud storage systems. With the development of cloud computing technology, deduplicatio...
详细信息
ISBN:
(数字)9781728190747
ISBN:
(纸本)9781728183824
Deduplication is a data redundancy elimination technique, designed to save system storage resources by reducing redundant data in cloud storage systems. With the development of cloud computing technology, deduplication has been increasingly applied to cloud data centers. However, traditional technologies face great challenges in big data deduplication to properly weigh the two conflicting goals of deduplication throughput and high duplicate elimination ratio. This paper proposes a similarity clustering-based deduplication strategy (named SCDS), which aims to delete more duplicate data without significantly increasing system overhead. The main idea of SCDS is to narrow the query range of fingerprint index by data partitioning and similarity clustering algorithms. In the data preprocessing stage, SCDS uses data partitioning algorithm to classify similar data together. In the data deletion stage, the similarity clustering algorithm is used to divide the similar data fingerprint superblock into the same cluster. Repetitive fingerprints are detected in the same cluster to speed up the retrieval of duplicate fingerprints. Experiments show that the deduplication ratio of SCDS is better than some existing similarity deduplication algorithms, but the overhead is only slightly higher than some high throughput but low deduplication ratio methods.
MOOCs have attracted a large number of learners with different education background all over the world. Despite its increasing popularity, MOOCs still suffer from the problem of high drop-out rate. One important reaso...
详细信息
The deep neural named entity recognition model automatically learns and extracts the features of entities and solves the problem of the traditional model relying heavily on complex feature engineering and obscure prof...
详细信息
With the popularity of the open source, the open source community has accumulated a large number of open source project. While these massive projects provide developers with rich reusable resource, they also bring dif...
详细信息
ISBN:
(纸本)9781538665664;9781538665657
With the popularity of the open source, the open source community has accumulated a large number of open source project. While these massive projects provide developers with rich reusable resource, they also bring difficulties for users to choose the appropriate software. Therefore, it is very meaningful to rank the software and tell users which is better. In this paper, we propose a novel approach that ranks software based on a global perspective different from traditional software evaluation and ranking methods. We evaluate the software from four dimensions, namely community popularity, development activity, software health and team health. Each dimension contains some metrics. We demonstrate the effectiveness of our method through comparative experiments. This method has been integrated into to the OSSEAN platform to form a software leaderboard.
Mobile devices play an important role in our everyday lives, but they also bring great security threats. Deep packet inspection (DPI) is one of the most efficient methods to detect the malicious information hidden in ...
详细信息
In crowd counting, regression-based method shows better performance in extreme density scenes by introduces a density map. However, the regression-based method fails to locate the positions of each head, which signifi...
详细信息
ISBN:
(数字)9781728146447
ISBN:
(纸本)9781728146454
In crowd counting, regression-based method shows better performance in extreme density scenes by introduces a density map. However, the regression-based method fails to locate the positions of each head, which significantly restricts its applications. Detection-based method counts each head with their accurate locations but works only in middle or low-level density scenes. In this paper, a joint learning method, named Density-attentive Head Detector (DAHD) is developed to overcome their respective shortcomings via a multi-task training procedure. Specifically, to guarantee the sensitivity of the detector to small or partially occluded heads, we carefully equip the detector with a density map which learned from regression module. Moreover, a novel Dilated Feature Pyramid Network (DFPN) is introduced to our method to enlarge the receptive field of convolutional kernel, bringing confirmative additional benefits to identify small heads. Experiments on the popular ShanghaiTech and Mall datasets confirm the improved performance of DAHD compared with the current detection-based approaches, and a comparable performance to regression-based approaches in term of counting.
Recently correlation filter based trackers have attracted considerable attention for their high computational efficiency. However, they cannot handle occlusion and scale variation well enough. This paper aims at preve...
详细信息
Recently correlation filter based trackers have attracted considerable attention for their high computational efficiency. However, they cannot handle occlusion and scale variation well enough. This paper aims at preventing the tracker from failure in these two situations by integrating the depth information into a correlation filter based tracker. By using RGB-D data, we construct a depth context model to reveal the spatial correlation between the target and its surrounding regions. Furthermore, we adopt a region growing method to make our tracker robust to occlusion and scale variation. Additional optimizations such as a model updating scheme are applied to improve the performance for longer video sequences. Both qualitative and quantitative evaluations on challenging benchmark image sequences demonstrate that the proposed tracker performs favourably against state-of-the-art algorithms.
Multi-view shape descriptors obtained from various 2D images are commonly adopted in 3D shape retrieval. One major challenge is that significant shape information are discarded during 2D view rendering through project...
详细信息
ISBN:
(数字)9781728148038
ISBN:
(纸本)9781728148045
Multi-view shape descriptors obtained from various 2D images are commonly adopted in 3D shape retrieval. One major challenge is that significant shape information are discarded during 2D view rendering through projection. In this paper, we propose a convolutional neural network based method, CenterNet, to enhance each individual 2D view using its neighboring ones. By exploiting cross-view correlations, CenterNet learns how adjacent views can be maximally incorporated for an enhanced 2D representation to effectively describe shapes. We observe that a very small amount of, e.g., six, enhanced 2D views, are already sufficient for a panoramic shape description. Thus, by simply aggregating features from six enhanced 2D views, we arrive at a highly compact yet discriminative shape descriptor. The proposed shape descriptor significantly outperforms state-of-the-art 3D shape retrieval methods on the ModelNet and ShapeNetCore55 benchmarks, and also exhibits robustness against object occlusion.
暂无评论