Zero-shot domain adaptation (ZDA) methods aim to transfer knowledge about a task learned in a source domain to a target domain, while data from target domain are not available. In this work, we address learning feature representations which are invar
iant to and shared among different domains considering task characteristics for ZDA. To this end, we propose a method for task-guided ZDA (TG-ZDA) which employs multi-branch deep neural networks to learn feature representations exploiting their domain invariance and shareability properties. The proposed TG-ZDA models can be trained end-to-end without requiring synthetic tasks and data generated from estimated representations of target domains. The proposed TG-ZDA has been examined using benchmark ZDA tasks on image classification datasets. Experimental results show that our proposed TG-ZDA outperforms state-of-the-art ZDA methods for different domains and tasks.
Massive connectivity is a critical challenge of Internet of Things (IoT) networks. In this paper, we consider the grant-free uplink transmission of an IoT network with a multi-antenna base station (BS) and a large number of single-antenna IoT devices
. Due to the sporadic nature of IoT devices, we formulate the joint activity detection and channel estimation (JADCE) problem as a group-sparse matrix estimation problem. Although many algorithms have been proposed to solve the JADCE problem, most of them are developed based on compressive sensing technique, yielding suboptimal solutions. In this paper, we first develop an efficient weighted $l_1$-norm minimization algorithm to better approximate the group sparsity than the existing mixed $l_1/l_2$-norm minimization. Although an enhanced estimation performance in terms of the mean squared error (MSE) can be achieved, the weighted $l_1$-norm minimization algorithm is still a convex relaxation of the original group-sparse matrix estimation problem, yielding a suboptimal solution. To this end, we further reformulate the JADCE problem as a mixed integer programming (MIP) problem, which can be solved by using the branch-and-bound method. As a result, we are able to obtain an optimal solution of the JADCE problem, which can be adopted as an upper bound to evaluate the effectiveness of the existing algorithms. Moreover, we also derive the minimum pilot sequence length required to fully recover the estimated matrix in the noiseless scenario. Simulation results show the performance gains of the proposed optimal algorithm over the proposed weighted $l_1$-norm algorithm and the conventional mixed $l_1/l_2$-norm algorithm. Results also show that the proposed algorithms require a short pilot sequence than the conventional algorithm to achieve the same estimation performance.
Domain adaptation (DA) paves the way for label annotation and dataset bias issues by the knowledge transfer from a label-rich source domain to a related but unlabeled target domain. A mainstream of DA methods is to align the feature distributions of
the two domains. However, the majority of them focus on the entire image features where irrelevant semantic information, e.g., the messy background, is inevitably embedded. Enforcing feature alignments in such case will negatively influence the correct matching of objects and consequently lead to the semantically negative transfer due to the confusion of irrelevant semantics. To tackle this issue, we propose Semantic Concentration for Domain Adaptation (SCDA), which encourages the model to concentrate on the most principal features via the pair-wise adversarial alignment of prediction distributions. Specifically, we train the classifier to class-wisely maximize the prediction distribution divergence of each sample pair, which enables the model to find the region with large differences among the same class of samples. Meanwhile, the feature extractor attempts to minimize that discrepancy, which suppresses the features of dissimilar regions among the same class of samples and accentuates the features of principal parts. As a general method, SCDA can be easily integrated into various DA methods as a regularizer to further boost their performance. Extensive experiments on the cross-domain benchmarks show the efficacy of SCDA.
Human vision is often adversely affected by complex environmental factors, especially in night vision scenarios. Thus, infrared cameras are often leveraged to help enhance the visual effects via detecting infrared radiation in the surrounding environ
ment, but the infrared videos are undesirable due to the lack of detailed semantic information. In such a case, an effective video-to-video translation method from the infrared domain to the visible light counterpart is strongly needed by overcoming the intrinsic huge gap between infrared and visible fields. To address this challenging problem, we propose an infrared-to-visible (I2V) video translation method I2V-GAN to generate fine-grained and spatial-temporal consistent visible light videos by given unpaired infrared videos. Technically, our model capitalizes on three types of constraints: 1)adversarial constraint to generate synthetic frames that are similar to the real ones, 2)cyclic consistency with the introduced perceptual loss for effective content conversion as well as style preservation, and 3)similarity constraints across and within domains to enhance the content and motion consistency in both spatial and temporal spaces at a fine-grained level. Furthermore, the current public available infrared and visible light datasets are mainly used for object detection or tracking, and some are composed of discontinuous images which are not suitable for video tasks. Thus, we provide a new dataset for I2V video translation, which is named IRVI. Specifically, it has 12 consecutive video clips of vehicle and monitoring scenes, and both infrared and visible light videos could be apart into 24352 frames. Comprehensive experiments validate that I2V-GAN is superior to the compared SOTA methods in the translation of I2V videos with higher fluency and finer semantic details. The code and IRVI dataset are available at https://github.com/BIT-DA/I2V-GAN.
Many scenarios of physics beyond the standard model predict new light, weakly coupled degrees of freedom, populated in the early universe and remaining as cosmic relics today. Due to their high abundances, these relics can significantly affect the ev
olution of the universe. For instance, massless relics produce a shift $Delta N_{rm eff}$ to the cosmic expectation of the effective number of active neutrinos. Massive relics, on the other hand, additionally become part of the cosmological dark matter in the later universe, though their light nature allows them to freely stream out of potential wells. This produces novel signatures in the large-scale structure (LSS) of the universe, suppressing matter fluctuations at small scales. We present the first general search for such light (but massive) relics (LiMRs) with cosmic microwave background (CMB) and LSS data, scanning the 2D parameter space of their masses $m_X$ and temperatures $T_X^{(0)}$ today. In the conservative minimum-temperature ($T_X^{(0)}=0.91$ K) scenario, we rule out Weyl (and higher-spin) fermions -- such as the gravitino -- with $m_Xgeq 2.26$ eV at 95% C.L., and set analogous limits of $m_Xleq 11.2, 1.06, 1.56$ eV for scalar, vector, and Dirac-fermion relics. This is the first search for LiMRs with joint CMB, weak-lensing, and full-shape galaxy data; we demonstrate that weak-lensing data is critical for breaking parameter degeneracies, while full-shape information presents a significant boost in constraining power relative to analyses with only baryon acoustic oscillation parameters. Under the combined strength of these datasets, our constraints are the tightest and most comprehensive to date.
In this work, we focus on improving the robots dexterous capability by exploiting visual sensing and adaptive force control. TeachNet, a vision-based teleoperation learning framework, is exploited to map human hand postures to a multi-fingered robot
hand. We augment TeachNet, which is originally based on an imprecise kinematic mapping and position-only servoing, with a biomimetic learning-based compliance control algorithm for dexterous manipulation tasks. This compliance controller takes the mapped robotic joint angles from TeachNet as the desired goal, computes the desired joint torques. It is derived from a computational model of the biomimetic control strategy in human motor learning, which allows adapting the control variables (impedance and feedforward force) online during the execution of the reference joint angle trajectories. The simultaneous adaptation of the impedance and feedforward profiles enables the robot to interact with the environment in a compliant manner. Our approach has been verified in multiple tasks in physics simulation, i.e., grasping, opening-a-door, turning-a-cap, and touching-a-mouse, and has shown more reliable performances than the existing position control and the fixed-gain-based force control approaches.
In this paper, we present a hybrid deep learning framework named CTNet which combines convolutional neural network and transformer together for the detection of COVID-19 via 3D chest CT images. It consists of a CNN feature extractor module with SE at
tention to extract sufficient features from CT scans, together with a transformer model to model the discriminative features of the 3D CT scans. Compared to previous works, CTNet provides an effective and efficient method to perform COVID-19 diagnosis via 3D CT scans with data resampling strategy. Advanced results on a large and public benchmarks, COV19-CT-DB database was achieved by the proposed CTNet, over the state-of-the-art baseline approachproposed together with the dataset.
Quantum Hall interferometers have been used to probe fractional charge, and more recently, fractional statistics of quasiparticles. Theoretical predictions have been made regarding the effect of electrostatic coupling on interferometer behavior and o
bservation of anyonic phases. Here we present measurements of a small Fabry-Perot interferometer in which these electrostatic coupling constants can be determined experimentally, facilitating quantitative comparison with theory. At the $ u = 1/3$ fractional quantum Hall state, this device exhibits Aharonov-Bohm interference near the center of the conductance plateau interrupted by a few discrete phase jumps, and $Phi_0$ oscillations at higher and lower magnetic fields, consistent with theoretical predictions for detection of anyonic statistics. We estimate the electrostatic parameters $K_I$ and $K_{IL}$ by two methods: by the ratio of oscillation periods in compressible versus incompressible regions, and from finite-bias conductance measurements, and these two methods yield consistent results. We find that the extracted $K_I$ and $K_{IL}$ can account for the deviation of the values of the discrete phase jumps from the theoretically predicted anyonic phase $theta _a = 2pi /3$. In the integer quantum Hall regime, we find that the experimental values of $K_I$ and $K_{IL}$ can account for the the observed Aharonov-Bohm and Coulomb dominated behavior of different edge states.
Since the first coronavirus case was identified in the U.S. on Jan. 21, more than 1 million people in the U.S. have confirmed cases of COVID-19. This infectious respiratory disease has spread rapidly across more than 3000 counties and 50 states in th
e U.S. and have exhibited evolutionary clustering and complex triggering patterns. It is essential to understand the complex spacetime intertwined propagation of this disease so that accurate prediction or smart external intervention can be carried out. In this paper, we model the propagation of the COVID-19 as spatio-temporal point processes and propose a generative and intensity-free model to track the spread of the disease. We further adopt a generative adversarial imitation learning framework to learn the model parameters. In comparison with the traditional likelihood-based learning methods, this imitation learning framework does not need to prespecify an intensity function, which alleviates the model-misspecification. Moreover, the adversarial learning procedure bypasses the difficult-to-evaluate integral involved in the likelihood evaluation, which makes the model inference more scalable with the data and variables. We showcase the dynamic learning performance on the COVID-19 confirmed cases in the U.S. and evaluate the social distancing policy based on the learned generative model.
Pairwise comparison matrices have received substantial attention in a variety of applications, especially in rank aggregation, the task of flattening items into a one-dimensional (and thus transitive) ranking. However, non-transitive preference cycle
s can arise in practice due to the fact that making a decision often requires a complex evaluation of multiple factors. In some applications, it may be important to identify and preserve information about the inherent non-transitivity, either in the pairwise comparison data itself or in the latent feature space. In this work, we develop structured models for non-transitive pairwise comparison matrices that can be exploited to recover such matrices from incomplete noisy data and thus allow the detection of non-transitivity. Considering that individuals tastes and items latent features may change over time, we formulate time-varying pairwise comparison matrix recovery as a dynamic skew-symmetric matrix recovery problem by modeling changes in the low-rank factors of the pairwise comparison matrix. We provide theoretical guarantees for the recovery and numerically test the proposed theory with both synthetic and real-world data.
