Aerodynamic heating effect caused by high speed flight of optical guidance system will lead to optical dome fracture failure or thermal barrier effect, which results in the inefficiency of the optical
Aerodynamic heating effect caused by high speed flight of optical guidance system will lead to optical dome fracture failure or thermal barrier effect, which results in the inefficiency of the optical
作者：
Zongyan HanZhenyong FuGuangyu LiJian YangPCA Lab
Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu 210094 China
Generalized zero-shot learning suffers from an extreme data imbalance problem, that is, the training data only come from seen classes while no unseen class data are available. Recently, a number of feature generation ...
详细信息
Generalized zero-shot learning suffers from an extreme data imbalance problem, that is, the training data only come from seen classes while no unseen class data are available. Recently, a number of feature generation methods based on generative adversarial networks (GAN) have been proposed to address this problem. Existing feature generation methods, however, have never considered the under-constrained problem, and thus could generate an unrestricted visual feature corresponding to no meaningful object class. In this paper, we propose to equip the feature generation framework with a parallel inference network that projects visual feature to the semantic descriptor space, constraining to avoid the generation of unrestricted visual features. The two-parallel-stream framework (1) enables our method, termed inference guided feature generation (Inf-FG), to mitigate the under-constrained problem and (2) makes our Inf-FG applicable to transductive ZSL. Our Inf-FG learns the feature generator and the inference network simultaneously by aligning the joint distribution of visual features and semantic descriptors from the feature generator and the joint distribution from the inference network. We evaluate our approach on four benchmark ZSL datasets, including AWA, CUB, SUN, and FLO, on which our method improves our baselines on generalized zero-shot learning.
Optical guidance system start infrared guided mode by throwing away the fairing in the terminal guidance phase. After throwing away the fairing, the infrared dome will be suddenly exposed to the aerod
Optical guidance system start infrared guided mode by throwing away the fairing in the terminal guidance phase. After throwing away the fairing, the infrared dome will be suddenly exposed to the aerod
When images compressed by traditional transformation-based compression algorithms are transmitted over wireless channels, if the gaussian random interference causes the loss of the crucial transformation coefficients,...
详细信息
When images compressed by traditional transformation-based compression algorithms are transmitted over wireless channels, if the gaussian random interference causes the loss of the crucial transformation coefficients, the contents of the reconstructed images will be lost obviously and this will reduce the accuracy of the subsequent detection and recognition results greatly. In order to solve this problem, this paper proposed an antiinterfering image reconstruction algorithm based on compressed sensing. This algorithm first confirmed the new compressed sensing signals and the new reconstruction matrix based on the locations of the compressed sensing signal components corresponding to the gaussian-interfered bit stream, and then reconstructed the original images employing the iterative threshold algorithm. The simulation results demonstrated that the new algorithm reconstructed exact images at low bit error rates, and reconstructed inexact images whose qualities were slightly lowered without loss of local contents at high bit error rates. As a result, our algorithm is able to overcome the deficiencies of compression algorithms based on diverse transformations and the iterative threshold algorithm, thus proposes a feasible solution scheme for the anti-interfering problem that arises in wireless image transmission.
Small vehicle detection in aerial images is a challenge in computervision because small vehicles occupy less pixels and the environment around the small vehicles is complex. To improve the detection performance for t...
详细信息
Small vehicle detection in aerial images is a challenge in computervision because small vehicles occupy less pixels and the environment around the small vehicles is complex. To improve the detection performance for the vehicles in aerial images, we propose an improved YOLO V3. The main contributions of our work include:(1)We redesign the backbone of YOLO V3 to select suitable scales for small vehicle detection in aerial images;(2) To make the improved YOLO V3 much stronger, we redesign the loss function of original YOLO V3 by GIOU loss and Focal loss;(3) To verify the performance of improved YOLO V3, we do the comparative experiments on VEDAI dataset. The experimental results show that the proposed method has obtained better performance than original YOLO V3 for small vehicle detection in aerial image.
In this paper, a multi-agent social evolutionary algorithm is proposed for multiobjective optimization problems. It completes the search process by the agent evolution. MOMASEA (multi-agent social evolutionary algorit...
详细信息
Landmark/pose estimation in single monocular images has received much effort in computervision due to its important applications. It remains a challenging task when input images come with severe occlusions caused by,...
详细信息
We present a novel method to modulate influence of diffuse scattering in fluid cavity and reflection at boundary of pulse-echo ultrasound image. A simplified formation of ultrasound model is used to delineate it, and ...
详细信息
This work presents a novel fundamental algorithm for for defining and training Neural Networks in Quantum Information based on time evolution and the Hamiltonian. Classical Neural Network algorithms (ANN) are computat...
详细信息
Dense crowd counting is a challenging task that demands millions of head annotations for training models. Though existing self-supervised approaches could learn good representations, they require some labeled data to ...
详细信息
暂无评论