The growth of connected intelligent devices in the Internet of Things has created a pressing need for real-time processing and understanding of large volumes of analogue data. The difficulty in boosting the computing speed renders digital computing unable to meet the demand for processing analogue information that is intrinsically continuous in magnitude and time. By utilizing a continuous data representation in a nanoscale crossbar array, parallel computing can be implemented for the direct processing of analogue information in real time. Here, we propose a scalable massively parallel computing scheme by exploiting a continuous-time data representation and frequency multiplexing in a nanoscale crossbar array. This computing scheme enables the parallel reading of stored data and the one-shot operation of matrix-matrix multiplications in the crossbar array. Furthermore, we achieve the one-shot recognition of 16 letter images based on two physically interconnected crossbar arrays and demonstrate that the processing and modulation of analogue information can be simultaneously performed in a memristive crossbar array.
We present a novel self-supervised algorithm named MotionHint for monocular visual odometry (VO) that takes motion constraints into account. A key aspect of our approach is to use an appropriate motion model that can help existing self-supervised monocular VO (SSM-VO) algorithms to overcome issues related to the local minima within their self-supervised loss functions. The motion model is expressed with a neural network named PPnet. It is trained to coarsely predict the next pose of the camera and the uncertainty of this prediction. Our self-supervised approach combines the original loss and the motion loss, which is the weighted difference between the prediction and the generated ego-motion. Taking two existing SSM-VO systems as our baseline, we evaluate our MotionHint algorithm on the standard KITTI benchmark. Experimental results show that our MotionHint algorithm can be easily applied to existing open-sourced state-of-the-art SSM-VO systems to greatly improve the performance by reducing the resulting ATE by up to 28.73%.
In recent years, single image dehazing models (SIDM) based on atmospheric scattering model (ASM) have achieved remarkable results. However, it is noted that ASM-based SIDM degrades its performance in dehazing real world hazy images due to the limited modelling ability of ASM where the atmospheric light factor (ALF) and the angular scattering coefficient (ASC) are assumed as constants for one image. Obviously, the hazy images taken in real world cannot always satisfy this assumption. Such generating modelling mismatch between the real-world images and ASM sets up the upper bound of trained ASM-based SIDM for dehazing. Bearing this in mind, in this study, a new fully non-homogeneous atmospheric scattering model (FNH-ASM) is proposed for well modeling the hazy images under complex conditions where ALF and ASC are pixel dependent. However, FNH-ASM brings difficulty in practical application. In FNH-ASM based SIDM, the estimation bias of parameters at different positions lead to different distortion of dehazing result. Hence, in order to reduce the influence of parameter estimation bias on dehazing results, two new cost sensitive loss functions, beta-Loss and D-Loss, are innovatively developed for limiting the parameter bias of sensitive positions that have a greater impact on the dehazing result. In the end, based on FNH-ASM, an end-to-end CNN-based dehazing network, FNHD-Net, is developed, which applies beta-Loss and D-Loss. Experimental results demonstrate the effectiveness and superiority of our proposed FNHD-Net for dehazing on both synthetic and real-world images. And the performance improvement of our method increases more obviously in dense and heterogeneous haze scenes.
Explanation of AI, as well as fairness of algorithms decisions and the transparency of the decision model, are becoming more and more important. And it is crucial to design effective and human-friendly techniques when opening the black-box model. Counterfactual conforms to the human way of thinking and provides a human-friendly explanation, and its corresponding explanation algorithm refers to a strategic alternation of a given data point so that its model output is counter-facted, i.e. the prediction is reverted. In this paper, we adapt counterfactual explanation over fine-grained image classification problem. We demonstrated an adaptive method that could give a counterfactual explanation by showing the composed counterfactual feature map using top-down layer searching algorithm (TDLS). We have proved that our TDLS algorithm could provide more flexible counterfactual visual explanation in an efficient way using VGG-16 model on Caltech-UCSD Birds 200 dataset. At the end, we discussed several applicable scenarios of counterfactual visual explanations.
Deformable image registration, aiming to find spatial correspondence between a given image pair, is one of the most critical problems in the domain of medical image analysis. In this paper, we present a generic, fast, and accurate diffeomorphic image registration framework that leverages neural ordinary differential equations (NODEs). We model each voxel as a moving particle and consider the set of all voxels in a 3D image as a high-dimensional dynamical system whose trajectory determines the targeted deformation field. Compared with traditional optimization-based methods, our framework reduces the running time from tens of minutes to tens of seconds. Compared with recent data-driven deep learning methods, our framework is more accessible since it does not require large amounts of training data. Our experiments show that the registration results of our method outperform state-of-the-arts under various metrics, indicating that our modeling approach is well fitted for the task of deformable image registration.
Transfer learning has become a common solution to address training data scarcity in practice. It trains a specified student model by reusing or fine-tuning early layers of a well-trained teacher model that is usually publicly available. However, besides utility improvement, the transferred public knowledge also brings potential threats to model confidentiality, and even further raises other security and privacy issues. In this paper, we present the first comprehensive investigation of the teacher model exposure threat in the transfer learning context, aiming to gain a deeper insight into the tension between public knowledge and model confidentiality. To this end, we propose a teacher model fingerprinting attack to infer the origin of a student model, i.e., the teacher model it transfers from. Specifically, we propose a novel optimization-based method to carefully generate queries to probe the student model to realize our attack. Unlike existing model reverse engineering approaches, our proposed fingerprinting method neither relies on fine-grained model outputs, e.g., posteriors, nor auxiliary information of the model architecture or training dataset. We systematically evaluate the effectiveness of our proposed attack. The empirical results demonstrate that our attack can accurately identify the model origin with few probing queries. Moreover, we show that the proposed attack can serve as a stepping stone to facilitating other attacks against machine learning models, such as model stealing.
Video salient object detection (VSOD) aims to locate and segment the most attractive object by exploiting both spatial cues and temporal cues hidden in video sequences. However, spatial and temporal cues are often unreliable in real-world scenarios, such as low-contrast foreground, fast motion, and multiple moving objects. To address these problems, we propose a new framework to adaptively capture available information from spatial and temporal cues, which contains Confidence-guided Adaptive Gate (CAG) modules and Dual Differential Enhancement (DDE) modules. For both RGB features and optical flow features, CAG estimates confidence scores supervised by the IoU between predictions and the ground truths to re-calibrate the information with a gate mechanism. DDE captures the differential feature representation to enrich the spatial and temporal information and generate the fused features. Experimental results on four widely used datasets demonstrate the effectiveness of the proposed method against thirteen state-of-the-art methods.
Based on some elementary estimates for the space-time derivatives of the heat kernel, we use a bootstrapping approach to establish the optimal decay rates for the $L^q(mathbb{R}^d)$ ($1leq qleqinfty$, $dinmathbb{N}$) norm of the space-time derivatives of solutions to the (modified) Patlak-Keller-Segel equations with initial data in $L^1(mathbb{R}^d)$, which implies the joint space-time analyticity of solutions. When the $L^1(mathbb{R}^d)$ norm of the initial datum is small, the upper bound for the decay estimates is global in time, which yields a lower bound on the growth rate of the radius of space-time analyticity in time. As a byproduct, the space analyticity is obtained for any initial data in $L^1(mathbb{R}^d)$. The decay estimates and space-time analyticity are also established for solutions bounded in both space and time variables. The results can be extended to a more general class of equations, including the Navier-Stokes equations.
Self-supervised learning (especially contrastive learning) has attracted great interest due to its tremendous potentials in learning discriminative representations in an unsupervised manner. Despite the acknowledged successes, existing contrastive learning methods suffer from very low learning efficiency, e.g., taking about ten times more training epochs than supervised learning for comparable recognition accuracy. In this paper, we discover two contradictory phenomena in contrastive learning that we call under-clustering and over-clustering problems, which are major obstacles to learning efficiency. Under-clustering means that the model cannot efficiently learn to discover the dissimilarity between inter-class samples when the negative sample pairs for contrastive learning are insufficient to differentiate all the actual object categories. Over-clustering implies that the model cannot efficiently learn the feature representation from excessive negative sample pairs, which enforces the model to over-cluster samples of the same actual categories into different clusters. To simultaneously overcome these two problems, we propose a novel self-supervised learning framework using a median triplet loss. Precisely, we employ a triplet loss tending to maximize the relative distance between the positive pair and negative pairs to address the under-clustering problem; and we construct the negative pair by selecting the negative sample of a median similarity score from all negative samples to avoid the over-clustering problem, guaranteed by the Bernoulli Distribution model. We extensively evaluate our proposed framework in several large-scale benchmarks (e.g., ImageNet, SYSU-30k, and COCO). The results demonstrate the superior performance (e.g., the learning efficiency) of our model over the latest state-of-the-art methods by a clear margin. Codes available at: https://github.com/wanggrun/triplet.
Acoustic matching layers are widely employed in high-frequency transducers which are excited by different signal types depending on applications. In this study, a theoretical method has been proposed to investigate the dependence of functional mechanism of matching layer on excitation signal types, i.e., short pulse and long pulse. The results indicate that the matching layer acts as a bandpass frequency filter under the two excitation signal types. In the short pulse excitation case, the matching layer can improve bandwidth and transmitting voltage response simultaneously, whereas for the case of long pulse excitation, the increased bandwidth is at the expense of transmitting voltage response. To verify our theoretical results, underwater acoustic transducers with and without matching layer were fabricated and tested. The thickness design principle of matching layer was modified due to the frequency-dependent acoustic radiation impedance. The experimental results verified the theoretical prediction. Our results provide a deep insight into the fundamental principle of matching layer design according to practical applications.
