The scarcity of high quality medical image annotations hinders the implementation of accurate clinical applications for detecting and segmenting abnormal lesions. To mitigate this issue, the scientific community is working on the development of unsup
ervised anomaly detection (UAD) systems that learn from a training set containing only normal (i.e., healthy) images, where abnormal samples (i.e., unhealthy) are detected and segmented based on how much they deviate from the learned distribution of normal samples. One significant challenge faced by UAD methods is how to learn effective low-dimensional image representations that are sensitive enough to detect and segment abnormal lesions of varying size, appearance and shape. To address this challenge, we propose a novel self-supervised UAD pre-training algorithm, named Multi-centred Strong Augmentation via Contrastive Learning (MSACL). MSACL learns representations by separating several types of strong and weak augmentations of normal image samples, where the weak augmentations represent normal images and strong augmentations denote synthetic abnormal images. To produce such strong augmentations, we introduce MedMix, a novel data augmentation strategy that creates new training images with realistic looking lesions (i.e., anomalies) in normal images. The pre-trained representations from MSACL are generic and can be used to improve the efficacy of different types of off-the-shelf state-of-the-art (SOTA) UAD models. Comprehensive experimental results show that the use of MSACL largely improves these SOTA UAD models on four medical imaging datasets from diverse organs, namely colonoscopy, fundus screening and covid-19 chest-ray datasets.
We provide a proof of the necessary and sufficient condition on the profile of the temperature, chemical potential, and angular velocity for a charged perfect fluid in dynamic equilibrium to be in thermodynamic equilibrium not only in fixed but also
in dynamical electromagnetic and gravitational fields. In passing, we also present the corresponding expression for the first law of thermodynamics for such a charged star.
Most existing video tasks related to human focus on the segmentation of salient humans, ignoring the unspecified others in the video. Few studies have focused on segmenting and tracking all humans in a complex video, including pedestrians and humans
of other states (e.g., seated, riding, or occluded). In this paper, we propose a novel framework, abbreviated as HVISNet, that segments and tracks all presented people in given videos based on a one-stage detector. To better evaluate complex scenes, we offer a new benchmark called HVIS (Human Video Instance Segmentation), which comprises 1447 human instance masks in 805 high-resolution videos in diverse scenes. Extensive experiments show that our proposed HVISNet outperforms the state-of-the-art methods in terms of accuracy at a real-time inference speed (30 FPS), especially on complex video scenes. We also notice that using the center of the bounding box to distinguish different individuals severely deteriorates the segmentation accuracy, especially in heavily occluded conditions. This common phenomenon is referred to as the ambiguous positive samples problem. To alleviate this problem, we propose a mechanism named Inner Center Sampling to improve the accuracy of instance segmentation. Such a plug-and-play inner center sampling mechanism can be incorporated in any instance segmentation models based on a one-stage detector to improve the performance. In particular, it gains 4.1 mAP improvement on the state-of-the-art method in the case of occluded humans. Code and data are available at https://github.com/IIGROUP/HVISNet.
Current methods of multi-person pose estimation typically treat the localization and the association of body joints separately. It is convenient but inefficient, leading to additional computation and a waste of time. This paper, however, presents a n
ovel framework PoseDet (Estimating Pose by Detection) to localize and associate body joints simultaneously at higher inference speed. Moreover, we propose the keypoint-aware pose embedding to represent an object in terms of the locations of its keypoints. The proposed pose embedding contains semantic and geometric information, allowing us to access discriminative and informative features efficiently. It is utilized for candidate classification and body joint localization in PoseDet, leading to robust predictions of various poses. This simple framework achieves an unprecedented speed and a competitive accuracy on the COCO benchmark compared with state-of-the-art methods. Extensive experiments on the CrowdPose benchmark show the robustness in the crowd scenes. Source code is available.
Interfacial thermal transport between electrodes and polymer electrolytes can play a crucial role in the thermal management of solid-state lithium-ion batteries (SLIBs). Modifying the electrode surface with functional molecules can effectively increa
se the interfacial thermal conductance (ITC) between electrodes and polymers (e.g., electrolytes, separators); however, how they influence the interfacial thermal transport in SLIBs during charge/discharge remains unknown. In this work, we conduct molecular dynamics (MD) simulations to investigate the ITC between charged electrodes and solid-state polymer electrolytes (SPEs) mixed with ionic liquids (ILs). We find that ILs could self assemble at the electrode surface and act as non-covalent functional molecules that could significantly enhance the interfacial thermal transport during charge/discharge because of the formation of a densely packed cationic or anionic layer at the interface. While the electrostatic interactions between the charged electrode and the IL ions are responsible for forming these dense interfacial layers, the enhancement of ITC is mainly contributed by the increased Lennard-Jones (LJ) interactions between the charged electrodes and ILs. This work may provide useful insights into the understanding of interfacial thermal transport between electrodes and electrolytes of SLIBs during charge/discharge.
Multilingual transformers (XLM, mT5) have been shown to have remarkable transfer skills in zero-shot settings. Most transfer studies, however, rely on automatically translated resources (XNLI, XQuAD), making it hard to discern the particular linguist
ic knowledge that is being transferred, and the role of expert annotated monolingual datasets when developing task-specific models. We investigate the cross-lingual transfer abilities of XLM-R for Chinese and English natural language inference (NLI), with a focus on the recent large-scale Chinese dataset OCNLI. To better understand linguistic transfer, we created 4 categories of challenge and adversarial tasks (totaling 17 new datasets) for Chinese that build on several well-known resources for English (e.g., HANS, NLI stress-tests). We find that cross-lingual models trained on English NLI do transfer well across our Chinese tasks (e.g., in 3/4 of our challenge categories, they perform as well/better than the best monolingual models, even on 3/5 uniquely Chinese linguistic phenomena such as idioms, pro drop). These results, however, come with important caveats: cross-lingual models often perform best when trained on a mixture of English and high-quality monolingual NLI data (OCNLI), and are often hindered by automatically translated resources (XNLI-zh). For many phenomena, all models continue to struggle, highlighting the need for our new diagnostics to help benchmark Chinese and cross-lingual models. All new datasets/code are released at https://github.com/huhailinguist/ChineseNLIProbing.
Model protection is vital when deploying Convolutional Neural Networks (CNNs) for commercial services, due to the massive costs of training them. In this work, we propose a selective encryption (SE) algorithm to protect CNN models from unauthorized a
ccess, with a unique feature of providing hierarchical services to users. Our algorithm firstly selects important model parameters via the proposed Probabilistic Selection Strategy (PSS). It then encrypts the most important parameters with the designed encryption method called Distribution Preserving Random Mask (DPRM), so as to maximize the performance degradation by encrypting only a very small portion of model parameters. We also design a set of access permissions, using which different amounts of the most important model parameters can be decrypted. Hence, different levels of model performance can be naturally provided for users. Experimental results demonstrate that the proposed scheme could effectively protect the classification model VGG19 by merely encrypting 8% parameters of convolutional layers. We also implement the proposed model protection scheme in the denoising model DnCNN, showcasing the hierarchical denoising services
Radio Map Prediction (RMP), aiming at estimating coverage of radio wave, has been widely recognized as an enabling technology for improving radio spectrum efficiency. However, fast and reliable radio map prediction can be very challenging due to the
complicated interaction between radio waves and the environment. In this paper, a novel Transformer based deep learning model termed as RadioNet is proposed for radio map prediction in urban scenarios. In addition, a novel Grid Embedding technique is proposed to substitute the original Position Embedding in Transformer to better anchor the relative position of the radiation source, destination and environment. The effectiveness of proposed method is verified on an urban radio wave propagation dataset. Compared with the SOTA model on RMP task, RadioNet reduces the validation loss by 27.3%, improves the prediction reliability from 90.9% to 98.9%. The prediction speed is increased by 4 orders of magnitude, when compared with ray-tracing based method. We believe that the proposed method will be beneficial to high-efficiency wireless communication, real-time radio visualization, and even high-speed image rendering.
Vignetting is an inherited imaging phenomenon within almost all optical systems, showing as a radial intensity darkening toward the corners of an image. Since it is a common effect for photography and usually appears as a slight intensity variation,
people usually regard it as a part of a photo and would not even want to post-process it. Due to this natural advantage, in this work, we study vignetting from a new viewpoint, i.e., adversarial vignetting attack (AVA), which aims to embed intentionally misleading information into vignetting and produce a natural adversarial example without noise patterns. This example can fool the state-of-the-art deep convolutional neural networks (CNNs) but is imperceptible to humans. To this end, we first propose the radial-isotropic adversarial vignetting attack (RI-AVA) based on the physical model of vignetting, where the physical parameters (e.g., illumination factor and focal length) are tuned through the guidance of target CNN models. To achieve higher transferability across different CNNs, we further propose radial-anisotropic adversarial vignetting attack (RA-AVA) by allowing the effective regions of vignetting to be radial-anisotropic and shape-free. Moreover, we propose the geometry-aware level-set optimization method to solve the adversarial vignetting regions and physical parameters jointly. We validate the proposed methods on three popular datasets, i.e., DEV, CIFAR10, and Tiny ImageNet, by attacking four CNNs, e.g., ResNet50, EfficientNet-B0, DenseNet121, and MobileNet-V2, demonstrating the advantages of our methods over baseline methods on both transferability and image quality.
In recent years, the immiscible polymer blend system has attracted much attention as the matrix of nanocomposites. Herein, from the perspective of dynamics, the control of the carbon nanotubes (CNTs) migration aided with the interface of polystyrene
(PS) and poly(methyl methacrylate) (PMMA) blends was achieved through a facile melt mixing method. Thus, we revealed a comprehensive relationship between several typical CNTs migrating scenarios and the microwave dielectric properties of their nanocomposites. Based on the unique morphologies and phase domain structures of the immiscible matrix, we further investigated the multiple microwave dielectric relaxation processes and shed new light on the relation between relaxation peak position and the phase domain size distribution. Moreover, by integrating the CNTs interface localization control with the matrix co-continuous structure construction, we found that the interface promotes double percolation effect to achieve conductive percolation at low CNTs loading (~1.06 vol%). Overall, the present study provides a unique nanocomposite material design symphonizing both functional fillers dispersion and location as well as the matrix architecture optimization for microwave applications.
