Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning

Medical imaging technologies, including computed tomography (CT) or chest X-Ray (CXR), are largely employed to facilitate the diagnosis of the COVID-19. Since manual report writing is usually too time-consuming, a more intelligent auxiliary medical system that could generate medical reports automatically and immediately is urgently needed. In this article, we propose to use the medical visual language BERT (Medical-VLBERT) model to identify the abnormality on the COVID-19 scans and generate the medical report automatically based on the detected lesion regions. To produce more accurate medical reports and minimize the visual-and-linguistic differences, this model adopts an alternate learning strategy with two procedures that are knowledge pretraining and transferring. To be more precise, the knowledge pretraining procedure is to memorize the knowledge from medical texts, while the transferring procedure is to utilize the acquired knowledge for professional medical sentences generations through observations of medical images. In practice, for automatic medical report generation on the COVID-19 cases, we constructed a dataset of 368 medical findings in Chinese and 1104 chest CT scans from The First Affiliated Hospital of Jinan University, Guangzhou, China, and The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China. Besides, to alleviate the insufficiency of the COVID-19 training samples, our model was first trained on the large-scale Chinese CX-CHR dataset and then transferred to the COVID-19 CT dataset for further fine-tuning. The experimental results showed that Medical-VLBERT achieved state-of-the-art performances on terminology prediction and report generation with the Chinese COVID-19 CT dataset and the CX-CHR dataset. The Chinese COVID-19 CT dataset is available at https://covid19ct.github.io/.

SIDE: I Infer the State I Want to Learn

As one of the solutions to the Dec-POMDP problem, the value decomposition method has achieved good results recently. However, most value decomposition methods require the global state during training, but this is not feasible in some scenarios where the global state cannot be obtained. Therefore, we propose a novel value decomposition framework, named State Inference for value DEcomposition (SIDE), which eliminates the need to know the true state by simultaneously seeking solutions to the two problems of optimal control and state inference. SIDE can be extended to any value decomposition method, as well as other types of multi-agent algorithms in the case of Dec-POMDP. Based on the performance results of different algorithms in Starcraft II micromanagement tasks, we verified that SIDE can construct the current state that contributes to the reinforcement learning process based on past local observations.

Learning the Superpixel in a Non-iterative and Lifelong Manner

Superpixel is generated by automatically clustering pixels in an image into hundreds of compact partitions, which is widely used to perceive the object contours for its excellent contour adherence. Although some works use the Convolution Neural Network (CNN) to generate high-quality superpixel, we challenge the design principles of these networks, specifically for their dependence on manual labels and excess computation resources, which limits their flexibility compared with the traditional unsupervised segmentation methods. We target at redefining the CNN-based superpixel segmentation as a lifelong clustering task and propose an unsupervised CNN-based method called LNS-Net. The LNS-Net can learn superpixel in a non-iterative and lifelong manner without any manual labels. Specifically, a lightweight feature embedder is proposed for LNS-Net to efficiently generate the cluster-friendly features. With those features, seed nodes can be automatically assigned to cluster pixels in a non-iterative way. Additionally, our LNS-Net can adapt the sequentially lifelong learning by rescaling the gradient of weight based on both channel and spatial context to avoid overfitting. Experiments show that the proposed LNS-Net achieves significantly better performance on three benchmarks with nearly ten times lower complexity compared with other state-of-the-art methods.

Self-supervised Low Light Image Enhancement and Denoising

This paper proposes a self-supervised low light image enhancement method based on deep learning, which can improve the image contrast and reduce noise at the same time to avoid the blur caused by pre-/post-denoising. The method contains two deep sub-networks, an Image Contrast Enhancement Network (ICE-Net) and a Re-Enhancement and Denoising Network (RED-Net). The ICE-Net takes the low light image as input and produces a contrast enhanced image. The RED-Net takes the result of ICE-Net and the low light image as input, and can re-enhance the low light image and denoise at the same time. Both of the networks can be trained with low light images only, which is achieved by a Maximum Entropy based Retinex (ME-Retinex) model and an assumption that noises are independently distributed. In the ME-Retinex model, a new constraint on the reflectance image is introduced that the maximum channel of the reflectance image conforms to the maximum channel of the low light image and its entropy should be the largest, which converts the decomposition of reflectance and illumination in Retinex model to a non-ill-conditioned problem and allows the ICE-Net to be trained with a self-supervised way. The loss functions of RED-Net are carefully formulated to separate the noises and details during training, and they are based on the idea that, if noises are independently distributed, after the processing of smoothing filters (\eg mean filter), the gradient of the noise part should be smaller than the gradient of the detail part. It can be proved qualitatively and quantitatively through experiments that the proposed method is efficient.

Dimensions of Commonsense Knowledge

Commonsense knowledge is essential for many AI applications, including those in natural language processing, visual processing, and planning. Consequently, many sources that include commonsense knowledge have been designed and constructed over the past decades. Recently, the focus has been on large text-based sources, which facilitate easier integration with neural (language) models and application on textual tasks, typically at the expense of the semantics of the sources. Such practice prevents the harmonization of these sources, understanding their coverage and gaps, and may hinder the semantic alignment of their knowledge with downstream tasks. Efforts to consolidate commonsense knowledge have yielded partial success, but provide no clear path towards a comprehensive consolidation of existing commonsense knowledge. The ambition of this paper is to organize these sources around a common set of dimensions of commonsense knowledge. For this purpose, we survey a wide range of popular commonsense sources with a special focus on their relations. We consolidate these relations into 13 knowledge dimensions, each abstracting over more specific relations found in sources. This consolidation allows us to unify the separate sources and to compute indications of their coverage, overlap, and gaps with respect to the knowledge dimensions. Moreover, we analyze the impact of each dimension on downstream reasoning tasks that require commonsense knowledge, observing that the temporal and desire/goal dimensions are very beneficial for reasoning on current downstream tasks, while distinctness and lexical knowledge have little impact. These results reveal focus towards some dimensions in current evaluation, and potential neglect of others.

CSKG: The CommonSense Knowledge Graph

Sources of commonsense knowledge aim to support applications in natural language understanding, computer vision, and knowledge graphs. These sources contain complementary knowledge to each other, which makes their integration desired. Yet, such integration is not trivial because of their different foci, modeling approaches, and sparse overlap. In this paper, we propose to consolidate commonsense knowledge by following five principles. We apply these principles to combine seven key sources into a first integrated CommonSense Knowledge Graph (CSKG). We perform analysis of CSKG and its various text and graph embeddings, showing that CSKG is a well-connected graph and that its embeddings provide a useful entry point to the graph. Moreover, we show the impact of CSKG as a source for reasoning evidence retrieval, and for pre-training language models for generalizable downstream reasoning. CSKG and all its embeddings are made publicly available to support further research on commonsense knowledge integration and reasoning.

Robust Two-Stream Multi-Feature Network for Driver Drowsiness Detection

Drowsiness driving is a major cause of traffic accidents and thus numerous previous researches have focused on driver drowsiness detection. Many drive relevant factors have been taken into consideration for fatigue detection and can lead to high precision, but there are still several serious constraints, such as most existing models are environmentally susceptible. In this paper, fatigue detection is considered as temporal action detection problem instead of image classification. The proposed detection system can be divided into four parts: (1) Localize the key patches of the detected driver picture which are critical for fatigue detection and calculate the corresponding optical flow. (2) Contrast Limited Adaptive Histogram Equalization (CLAHE) is used in our system to reduce the impact of different light conditions. (3) Three individual two-stream networks combined with attention mechanism are designed for each feature to extract temporal information. (4) The outputs of the three sub-networks will be concatenated and sent to the fully-connected network, which judges the status of the driver. The drowsiness detection system is trained and evaluated on the famous Nation Tsing Hua University Driver Drowsiness Detection (NTHU-DDD) dataset and we obtain an accuracy of 94.46%, which outperforms most existing fatigue detection models.

The 1st Tiny Object Detection Challenge:Methods and Results

The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection. The TinyPerson dataset was used for the TOD Challenge and is publicly released. It has 1610 images and 72651 box-levelannotations. Around 36 participating teams from the globe competed inthe 1st TOD Challenge. In this paper, we provide a brief summary of the1st TOD Challenge including brief introductions to the top three methods.The submission leaderboard will be reopened for researchers that areinterested in the TOD challenge. The benchmark dataset and other information can be found at: https://github.com/ucas-vg/TinyBenchmark.

Privacy-preserving Transfer Learning via Secure Maximum Mean Discrepancy

The success of machine learning algorithms often relies on a large amount of high-quality data to train well-performed models. However, data is a valuable resource and are always held by different parties in reality. An effective solution to such a data isolation problem is to employ federated learning, which allows multiple parties to collaboratively train a model. In this paper, we propose a Secure version of the widely used Maximum Mean Discrepancy (SMMD) based on homomorphic encryption to enable effective knowledge transfer under the data federation setting without compromising the data privacy. The proposed SMMD is able to avoid the potential information leakage in transfer learning when aligning the source and target data distribution. As a result, both the source domain and target domain can fully utilize their data to build more scalable models. Experimental results demonstrate that our proposed SMMD is secure and effective.