Knowledge distillation aims at transferring knowledge acquired in one model (a teacher) to another model (a student) that is typically smaller. Previous approaches can be expressed as a form of training the student to mimic output activations of individual data examples represented by the teacher. We introduce a novel approach, dubbed relational knowledge distillation (RKD), that transfers mutual relations of data examples instead. For concrete realizations of RKD, we propose distance-wise and angle-wise distillation losses that penalize structural differences in relations. Experiments conducted on different tasks show that the proposed method improves educated student models with a significant margin. In particular for metric learning, it allows students to outperform their teachers' performance, achieving the state of the arts on standard benchmark datasets.

/pdf/relational-knowledge-distillation-5ddm5be5vj.pdf

Relational Knowledge Distillation

Background A novel coronavirus (COVID-19) has emerged recently as an acute respiratory syndrome. The outbreak was originally reported in Wuhan, China, but has subsequently been spread world-widely. As the COVID-19 continues to spread rapidly across the world, computed tomography (CT) has become essentially important for fast diagnoses. Thus, it is urgent to develop an accurate computer-aided method to assist clinicians to identify COVID-19-infected patients by CT images. Materials and Methods We collected chest CT scans of 88 patients diagnosed with the COVID-19 from hospitals of two provinces in China, 101 patients infected with bacteria pneumonia, and 86 healthy persons for comparison and modeling. Based on the collected dataset, a deep learning-based CT diagnosis system (DeepPneumonia) was developed to identify patients with COVID-19. Results The experimental results showed that our model can accurately identify the COVID-19 patients from others with an excellent AUC of 0.99 and recall (sensitivity) of 0.93. In addition, our model was capable of discriminating the COVID-19 infected patients and bacteria pneumonia-infected patients with an AUC of 0.95, recall (sensitivity) of 0.96. Moreover, our model could localize the main lesion features, especially the ground-glass opacity (GGO) that is of great help to assist doctors in diagnosis. The diagnosis for a patient could be finished in 30 seconds, and the implementation on Tianhe-2 supercompueter enables a parallel executions of thousands of tasks simultaneously. An online server is available for online diagnoses with CT images by http://biomed.nscc-gz.cn/server/Ncov2019. Conclusions The established models can achieve a rapid and accurate identification of COVID-19 in human samples, thereby allowing identification of patients.

/pdf/deep-learning-enables-accurate-diagnosis-of-novel-3rvbn6do0k.pdf

Deep learning Enables Accurate Diagnosis of Novel Coronavirus (COVID-19) with CT images

Delicate feature representation about object parts plays a critical role in fine-grained recognition. For example, experts can even distinguish fine-grained objects relying only on object parts according to professional knowledge. In this paper, we propose a novel "Destruction and Construction Learning" (DCL) method to enhance the difficulty of fine-grained recognition and exercise the classification model to acquire expert knowledge. Besides the standard classification backbone network, another "destruction and construction" stream is introduced to carefully "destruct" and then "reconstruct" the input image, for learning discriminative regions and features. More specifically, for "destruction", we first partition the input image into local regions and then shuffle them by a Region Confusion Mechanism (RCM). To correctly recognize these destructed images, the classification network has to pay more attention to discriminative regions for spotting the differences. To compensate the noises introduced by RCM, an adversarial loss, which distinguishes original images from destructed ones, is applied to reject noisy patterns introduced by RCM. For "construction", a region alignment network, which tries to restore the original spatial layout of local regions, is followed to model the semantic correlation among local regions. By jointly training with parameter sharing, our proposed DCL injects more discriminative local details to the classification network. Experimental results show that our proposed framework achieves state-of-the-art performance on three standard benchmarks. Moreover, our proposed method does not need any external knowledge during training, and there is no computation overhead at inference time except the standard classification network feed-forwarding. Source code: https://github.com/JDAI-CV/DCL.

/pdf/destruction-and-construction-learning-for-fine-grained-image-3dv8s9bb8h.pdf

Destruction and Construction Learning for Fine-Grained Image Recognition

An outbreak of a novel coronavirus disease (i.e., COVID-19) has been recorded in Wuhan, China since late December 2019, which subsequently became pandemic around the world. Although COVID-19 is an acutely treated disease, it can also be fatal with a risk of fatality of 4.03% in China and the highest of 13.04% in Algeria and 12.67% Italy (as of 8th April 2020). The onset of serious illness may result in death as a consequence of substantial alveolar damage and progressive respiratory failure. Although laboratory testing, e.g., using reverse transcription polymerase chain reaction (RT-PCR), is the golden standard for clinical diagnosis, the tests may produce false negatives. Moreover, under the pandemic situation, shortage of RT-PCR testing resources may also delay the following clinical decision and treatment. Under such circumstances, chest CT imaging has become a valuable tool for both diagnosis and prognosis of COVID-19 patients. In this study, we propose a weakly supervised deep learning strategy for detecting and classifying COVID-19 infection from CT images. The proposed method can minimise the requirements of manual labelling of CT images but still be able to obtain accurate infection detection and distinguish COVID-19 from non-COVID-19 cases. Based on the promising results obtained qualitatively and quantitatively, we can envisage a wide deployment of our developed technique in large-scale clinical studies.

/pdf/weakly-supervised-deep-learning-for-covid-19-infection-h1hysbb53v.pdf

Weakly Supervised Deep Learning for COVID-19 Infection Detection and Classification From CT Images

Natural gradient descent is an optimization method traditionally motivated from the perspective of information geometry, and works well for many applications as an alternative to stochastic gradient descent. In this paper we critically analyze this method and its properties, and show how it can be viewed as a type of 2nd-order optimization method, with the Fisher information matrix acting as a substitute for the Hessian. In many important cases, the Fisher information matrix is shown to be equivalent to the Generalized Gauss-Newton matrix, which both approximates the Hessian, but also has certain properties that favor its use over the Hessian. This perspective turns out to have significant implications for the design of a practical and robust natural gradient optimizer, as it motivates the use of techniques like trust regions and Tikhonov regularization. Additionally, we make a series of contributions to the understanding of natural gradient and 2nd-order methods, including: a thorough analysis of the convergence speed of stochastic natural gradient descent (and more general stochastic 2nd-order methods) as applied to convex quadratics, a critical examination of the oft-used "empirical" approximation of the Fisher matrix, and an analysis of the (approximate) parameterization invariance property possessed by natural gradient methods (which we show also holds for certain other curvature, but notably not the Hessian).

New insights and perspectives on the natural gradient method

Fine-grained classification is challenging due to the difficulty of finding discriminative features. Finding those subtle traits that fully characterize the object is not straightforward. To handle this circumstance, we propose a novel self-supervision mechanism to effectively localize informative regions without the need of bounding-box/part annotations. Our model, termed NTS-Net for Navigator-Teacher-Scrutinizer Network, consists of a Navigator agent, a Teacher agent and a Scrutinizer agent. In consideration of intrinsic consistency between informativeness of the regions and their probability being ground-truth class, we design a novel training paradigm, which enables Navigator to detect most informative regions under the guidance from Teacher. After that, the Scrutinizer scrutinizes the proposed regions from Navigator and makes predictions. Our model can be viewed as a multi-agent cooperation, wherein agents benefit from each other, and make progress together. NTS-Net can be trained end-to-end, while provides accurate fine-grained classification predictions as well as highly informative regions during inference. We achieve state-of-the-art performance in extensive benchmark datasets.

/pdf/learning-to-navigate-for-fine-grained-classification-5aw33uzgtx.pdf

Learning to Navigate for Fine-grained Classification

Applying artificial intelligence techniques in medical imaging is one of the most promising areas in medicine. However, most of the recent success in this area highly relies on large amounts of carefully annotated data, whereas annotating medical images is a costly process. In this paper, we propose a novel method, called FocalMix, which, to the best of our knowledge, is the first to leverage recent advances in semi-supervised learning (SSL) for 3D medical image detection. We conducted extensive experiments on two widely used datasets for lung nodule detection, LUNA16 and NLST. Results show that our proposed SSL methods can achieve a substantial improvement of up to 17.3% over state-of-the-art supervised learning approaches with 400 unlabeled CT scans.

/pdf/focalmix-semi-supervised-learning-for-3d-medical-image-44f4wo7qxq.pdf

FocalMix: Semi-Supervised Learning for 3D Medical Image Detection

Recently, neural models for information retrieval are becoming increasingly popular. They provide effective approaches for product search due to their competitive advantages in semantic matching. However, it is challenging to use graph-based features, though proved very useful in IR literature, in these neural approaches. In this paper, we leverage the recent advances in graph embedding techniques to enable neural retrieval models to exploit graph-structured data for automatic feature extraction. The proposed approach can not only help to overcome the long-tail problem of click-through data, but also incorporate external heterogeneous information to improve search results. Extensive experiments on a real-world e-commerce dataset demonstrate significant improvement achieved by our proposed approach over multiple strong baselines both as an individual retrieval model and as a feature used in learning-to-rank frameworks.

Neural IR Meets Graph Embedding: A Ranking Model for Product Search

First-order methods such as stochastic gradient descent (SGD) are currently the standard algorithm for training deep neural networks. Second-order methods, despite their better convergence rate, are rarely used in practice due to the prohibitive computational cost in calculating the second-order information. In this paper, we propose a novel Gram-Gauss-Newton (GGN) algorithm to train deep neural networks for regression problems with square loss. Our method draws inspiration from the connection between neural network optimization and kernel regression of neural tangent kernel (NTK). Different from typical second-order methods that have heavy computational cost in each iteration, GGN only has minor overhead compared to first-order methods such as SGD. We also give theoretical results to show that for sufficiently wide neural networks, the convergence rate of GGN is \emph{quadratic}. Furthermore, we provide convergence guarantee for mini-batch GGN algorithm, which is, to our knowledge, the first convergence result for the mini-batch version of a second-order method on overparameterized neural networks. Preliminary experiments on regression tasks demonstrate that for training standard networks, our GGN algorithm converges much faster and achieves better performance than SGD.

/pdf/gram-gauss-newton-method-learning-overparameterized-neural-2w75bd99wj.pdf

Dong Wang

Papers

Learning to Navigate for Fine-grained Classification

FocalMix: Semi-Supervised Learning for 3D Medical Image Detection

FocalMix: Semi-Supervised Learning for 3D Medical Image Detection

Neural IR Meets Graph Embedding: A Ranking Model for Product Search

Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems