arXiv subjects

Juan Wen

Publications and source records attributed to Juan Wen.

24 records · Page 2Linked to original sources

arXiv2023

When Super-Resolution Meets Camouflaged Object Detection: A Comparison Study

Super Resolution (SR) and Camouflaged Object Detection (COD) are two hot topics in computer vision with various joint applications. For instance, low-resolution surveillance images can be successively processed by super-resolution techniques and camouflaged object detection. However, in previous work, these two areas are always studied in isolation. In this paper, we, for the first time, conduct an integrated comparative evaluation for both. Specifically, we benchmark different super-resolution methods on commonly used COD datasets, and meanwhile, we evaluate the robustness of different COD models by using COD data processed by SR methods. Our goal is to bridge these two domains, discover novel experimental phenomena, summarize new experim.

cs.CV↗

arXiv2019

Varifocal-Net: A Chromosome Classification Approach using Deep Convolutional Networks

Chromosome classification is critical for karyotyping in abnormality diagnosis. To expedite the diagnosis, we present a novel method named Varifocal-Net for simultaneous classification of chromosome's type and polarity using deep convolutional networks. The approach consists of one global-scale network (G-Net) and one local-scale network (L-Net). It follows three stages. The first stage is to learn both global and local features. We extract global features and detect finer local regions via the G-Net. By proposing a varifocal mechanism, we zoom into local parts and extract local features via the L-Net. Residual learning and multi-task learning strategies are utilized to promote high-level feature extraction. The detection of discriminative local parts is fulfilled by a localization subnet of the G-Net, whose training process involves both supervised and weakly-supervised learning. The second stage is to build two multi-layer perceptron classifiers that exploit features of both two scales to boost classification performance. The third stage is to introduce a dispatch strategy of assigning each chromosome to a type within each patient case, by utilizing the domain knowledge of karyotyping. Evaluation results from 1909 karyotyping cases showed that the proposed Varifocal-Net achieved the highest accuracy per patient case (%) 99.2 for both type and polarity tasks. It outperformed state-of-the-art methods, demonstrating the effectiveness of our varifocal mechanism, multi-scale feature ensemble, and dispatch strategy. The proposed method has been applied to assist practical karyotype diagnosis.

cs.CV↗

arXiv2017

Cache-Enabled Heterogeneous Cellular Networks: Optimal Tier-Level Content Placement

Caching popular contents at base stations (BSs) of a heterogeneous cellular network (HCN) avoids frequent information passage from content providers to the network edge, thereby reducing latency and alleviating traffic congestion in backhaul links. In general, the optimal strategies for content placement in HCNs remain largely unknown and deriving them forms the theme of this paper. To this end, we adopt the popular random HCN model where $K$ tiers of BSs are modelled as independent Poisson point processes distributed in the plane with different densities. Further, the random caching scheme is considered where each of a given set of $M$ files with corresponding popularity measures is placed at each BS of a particular tier with a corresponding probability, called placement probability. The probabilities are identical for all BSs in the same tier but vary over tiers, giving the name tier-level content placement. We consider the network performance metric, hit probability, defined as the probability that a file requested by the typical user is delivered successfully to the user. We maximize the hit probability over content placement probabilities, which yields the optimal tier-level placement policies. For the case of uniform received signal-to-interference thresholds for successful transmissions for BSs in different tiers, the policy is in closed-form where the placement probability for a particular file is proportional to the square-root of the corresponding popularity measure with an offset depending on BS caching capacities. For the general case of non-uniform SIR thresholds, the optimization problem is non-convex and a sub-optimal placement policy is designed by approximation, which has a similar structure as in the case of uniform SIR thresholds and shown by simulation to be close-to-optimal.

cs.IT↗

arXiv2017

Effects of Base-Station Spatial Interdependence on Interference Correlation and Network Performance

The spatial-and-temporal correlation of interference has been well studied in Poisson networks where the interfering base stations (BSs) are independent of each other. However, there exists spatial interdependence including attraction and repulsion among the BSs in practical wireless networks, affecting the interference distribution and hence the network performance. In view of this, by modeling the network as a Poisson clustered process, we quantify the effects of spatial interdependence among BSs on the interference correlation and analytically prove that BS clustering increases the level of interference correlation. In particular, it is shown that the level increases as the attraction between the BSs increases. Furthermore, we study the effects of spatial interdependence among BSs on network performance with a retransmission scheme via considering heterogeneous cellular networks in which small-cell BSs exhibit a clustered topology in practice. It is shown that the interference correlation degrades the network performance and the degradation increases as the attraction between BSs increases. Finally, a correlation-aware retransmission scheme is proposed to improve the network performance by taking advantage of the interference correlation and avoiding the blind retransmissions.

cs.IT↗

arXiv2016

Analysis of Interference Correlation in Non-Poisson Networks

The correlation of interference has been well quantified in Poisson networks where the interferers are independent of each other. However, there exists dependence among the base stations (BSs) in wireless networks. In view of this, we quantify the interference correlation in non-Poisson networks where the interferers are distributed as a Matern cluster process (MCP) and a second-order cluster process (SOCP). Interestingly, it is found that the correlation coefficient of interference for the Matern cluster networks, $ζ_{MCP}$, is equal to that for second-order cluster networks, $ζ_{SOCP}$. Furthermore, they are greater than their counterpart for the Poisson networks. This shows that clustering in interferers enhances the interference correlation. In addition, we show that the correlation coefficients $ζ_{MCP}$ and $ζ_{SOCP}$ increase as the average number of points in each cluster, $c$, grows, but decrease with the increase in the cluster radius, $R$. More importantly, we point that the effects of clustering on interference correlation can be neglected as $\frac{c}{π^{2}R^{2}}\rightarrow0$. Finally, the analytical results are validated by simulations.

cs.IT↗

arXiv2014

Correlations of Interference and Link Successes in Heterogeneous Cellular Networks

In heterogeneous cellular networks (HCNs), the interference received at a user is correlated over time slots since it comes from the same set of randomly located BSs. This results in the correlations of link successes, thus affecting network performance. Under the assumptions of a K-tier Poisson network, strongest-candidate based BS association, and independent Rayleigh fading, we first quantify the correlation coefficients of interference. We observe that the interference correlation is independent of the number of tiers, BS density, SIR threshold, and transmit power. Then, we study the correlations of link successes in terms of the joint success probability over multiple time slots. We show that the joint success probability is decided by the success probability in a single time slot and a diversity polynomial, which represents the temporal interference correlation. Moreover, the parameters of HCNs have an important influence on the joint success probability by affecting the success probability in a single time slot. Particularly, we obtain the condition under which the joint success probability increases with the BS density and transmit power. We further show that the conditional success probability given prior successes only depends on the path loss exponent and the number of time slots.

cs.IT↗