In this article, we address the problem of clutter covariance matrix estimation for radar adaptive detection. Traditional estimation methods are usually based on specific models. However, performance will experience degradation in the presence of model mismatch, which occurs commonly in reality. Therefore, we resort to the data-driven deep learning method and construct a network based on the convolutional neural network (CNN) to estimate the clutter covariance matrix. Besides, due to the unavailable ground truth of the covariance matrix of measured data, simulated data are usually applied for training as a compromise. We design a loss function according to the whitening metric, which makes it possible to train the network directly by measured data. Compared with traditional covariance matrix estimators, the proposed network estimator has higher whitening ability. Moreover, we exploit the obtained covariance matrix estimations to an adaptive detector to evaluate the detection performance. Results with the Intelligent Pixel (IPIX) datasets show that the detector applying the network covariance matrix estimator gains a higher probability of detection (PD).

Federated learning is a distributed machine learning system that uses participants’ data to train an improved global model. In federated learning, participants collaboratively train a global model, and after the training is completed, each participant receives that global model along with an incentive. Rational participants try to maximize their individual utility, and they will not input their high-quality data truthfully unless they are provided with satisfactory payments based on their contributions. Furthermore, federated learning benefits from the cooperation of participants. Accordingly, how to establish an incentive mechanism that both incentivizes inputting data truthfully and promotes cooperative contributions has become an important issue to consider. In this article, we introduce a data sharing game model for federated learning and employ game-theoretic approaches to design a core-selecting incentive mechanism by utilizing a popular concept in cooperative games, the core. In federated learning, the core can be empty, resulting in the core-selecting mechanism becoming infeasible. To address this issue, our core-selecting mechanism employs a relaxation method and simultaneously minimizes the benefits of inputting false data for all participants. Meanwhile, to reduce the computational complexity of the core-selecting mechanism, we propose an efficient core-selecting mechanism based on sampling approximation that only aggregates models on sampled coalitions to approximate the exact result. Extensive experiments demonstrate that the efficient core-selecting mechanism can incentivize truthful input of high-quality data and promote cooperation effectively, while it reduces computational overhead compared to the core-selecting mechanism.

We present an effective and efficient method that explores the properties of Transformers in the frequency domain for high-quality image deblurring. Our method is motivated by the convolution theorem that the correlation or convolution of two signals in the spatial domain is equivalent to an element-wise product of them in the frequency domain. This inspires us to develop an efficient frequency domain-based self-attention solver (FSAS) to estimate the scaled dot-product attention by an element-wise product operation instead of the matrix multiplication in the spatial domain. In addition, we note that simply using the naive feed-forward network (FFN) in Transformers does not generate good deblurred results. To overcome this problem, we propose a simple yet effective discriminative frequency domain-based FFN (DFFN), where we introduce a gated mechanism in the FFN based on the Joint Photographic Experts Group (JPEG) compression algorithm to discriminatively determine which low- and high-frequency information of the features should be preserved for latent clear image restoration. We formulate the proposed FSAS and DFFN into an asymmetrical network based on an encoder and decoder architecture, where the FSAS is only used in the decoder module for better image deblurring. Experimental results show that the proposed method performs favorably against the state-of-the-art approaches.

How to effectively explore spatial and temporal information is important for video deblurring. In contrast to existing methods that directly align adjacent frames without discrimination, we develop a deep discriminative spatial and temporal network to facilitate the spatial and temporal feature exploration for better video deblurring. We first develop a channel-wise gated dynamic network to adaptively explore the spatial information. As adjacent frames usually contain different contents, directly stacking features of adjacent frames without discrimination may affect the latent clear frame restoration. Therefore, we develop a simple yet effective discriminative temporal feature fusion module to obtain useful temporal features for latent frame restoration. Moreover, to utilize the information from long-range frames, we develop a wavelet-based feature propagation method that takes the discriminative temporal feature fusion module as the basic unit to effectively propagate main structures from long-range frames for better video deblurring. We show that the proposed method does not require additional alignment methods and performs favorably against state-of-the-art ones on benchmark datasets in terms of accuracy and model complexity.

We aim to significantly reduce the computational cost for classification of temporally untrimmed videos while retaining similar accuracy. Existing video classification methods sample frames with a predefined frequency over entire video. Differently, we propose an end-to-end deep reinforcement approach which enables an agent to classify videos by watching a very small portion of frames like what we do. We make two main contributions. First, information is not equally distributed in video frames along time. An agent needs to watch more carefully when a clip is informative and skip the frames if they are redundant or irrelevant. The proposed approach enables the agent to adapt sampling rate to video content and skip most of the frames without the loss of information. Second, in order to have a confident decision, the number of frames that should be watched by an agent varies greatly from one video to another. We incorporate an adaptive stop network to measure confidence score and generate timely trigger to stop the agent watching videos, which improves efficiency without loss of accuracy. Our approach reduces the computational cost significantly for the large-scale YouTube-8M dataset, while the accuracy remains the same.

Image correction and preliminary analysis of a field measurement by a C band 6-channel airborne microwave synthetic aperture radiometer is presented. This measurement was carried out along the Yellow River banks, Shaan'Xi, China, during 25/sup th/ to 30/sup th/ April, 2002. The CSSAR one dimensional C-band (6.6 GHz) 6-channel synthetic aperture radiometer was used as the airborne sensor. On board of the helicopter, a GPS receiver is also used to record the geographical positions of the flight pass. The scan was carried in over a square area across the experiment fields covering about 8/spl times/8 km/sup 2/. Ground truth observation also took place at the same time. The ground measurement parameters include: temperature of water body, air temperature, soil temperature, soil moisture at varied depth, soil surface roughness, etc. Geometric correction and registration were done before the analysis of the imagery. Some preliminary results are given.

A joint field experiment was carried out using microwave and visible sensors for bare soil and vegetation in Shunyi of Beijing in May 2001. The sensors include a microwave radiometer, microwave scatterometer and visible and infrared spectrometer. The microwave radiometer operates in the L, C and K band with H and V polarizations. The microwave scatterometer operates in the C band with HH, HV, VH, VV polarizations. The microwave brightness temperature, backscatter coefficients and reflectivity of bare soil, winter wheat and alfalfa were measured at various incidence angles. Meanwhile, ground surface parameters such as soil surface roughness, soil moisture and temperature of various depths, LAI of winter wheat and alfalfa were measured at the same time. The measured data were analyzed and an algorithm based on synergistic use of all these data is put forward to estimate soil moisture.