Deep learning methods usually require a large amount of training data and lack interpretability. In this paper, we propose a novel knowledge distillation and model interpretation framework for medical image classification that jointly solves the above two issues. Specifically, to address the data-hungry issue, a small student model is learned with less data by distilling knowledge from a cumbersome pretrained teacher model. To interpret the teacher model and assist the learning of the student, an explainer module is introduced to highlight the regions of an input that are important for the predictions of the teacher model. Furthermore, the joint framework is trained by a principled way derived from the information-theoretic perspective. Our framework outperforms on the knowledge distillation and model interpretation tasks compared to state-of-the-art methods on a fundus dataset.
Peking University（北京大学）；Lancaster University（兰卡斯特大学）；Peking University Third Hospital（北京大学第三医院）
Due to the characteristics of COVID-19, the epidemic develops rapidly and overwhelms health service systems worldwide. Many patients suffer from systemic life-threatening problems and need to be carefully monitored in ICUs. Thus the intelligent prognosis is in an urgent need to assist physicians to take an early intervention, prevent the adverse outcome, and optimize the medical resource allocation. However, in the early stage of the epidemic outbreak, the data available for analysis is limited due to the lack of effective diagnostic mechanisms, rarity of the cases, and privacy concerns. In th…
The First Affiliated Hospital of Jinan University（暨南大学附属第一医院）；The Fifth Affiliated Hospital of Sun Yat-sen University（中山大学附属第五医院）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；The Chinese University of Hong Kong（香港中文大学）；Future Network of Intelligence Institute (FNii)（未来智能网络研究院）；Sun Yat-sen University（中山大学）；Jinan University（暨南大学）；Guangdong Provincial Key Laboratory of Big Data Computing（广东省大数据计算重点实验室）
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 …
This short technical report demonstrates a simple technique that yields state of the art results in medical image-text matching tasks. We analyze the use of OpenAI's CLIP, a general image-text matching model, and observe that CLIP's limited textual input size has negative impact on downstream performance in the medical domain where encoding longer textual contexts is often required. We thus train and release ClipMD, which is trained with a simple sliding window technique to encode textual captions. ClipMD was tested on two medical image-text datasets and compared with other image-text matching…
Siemens Healthineers, X-ray products（西门子医疗 X 射线产品部）；Siemens Healthineers, Medical Imaging Technologies（西门子医疗医学影像技术部）；School of Information Technologies, University of Sydney（悉尼大学信息技术学院）
While deep convolutional neural networks (CNN) have been successfully applied for 2D image analysis, it is still challenging to apply them to 3D anisotropic volumes, especially when the within-slice resolution is much higher than the between-slice resolution and when the amount of 3D volumes is relatively small. On one hand, direct learning of CNN with 3D convolution kernels suffers from the lack of data and likely ends up with poor generalization; insufficient GPU memory limits the model size or representational power. On the other hand, applying 2D CNN with generalizable features to 2D slice…
The texture is defined as spatial structure of the intensities of the pixels in an image that is repeated periodically in the whole image or regions, and makes the concept of the image. Texture, color and shape are three main components which are used by human visual system to recognize image contents. In this paper, first of all, efficient and updated texture analysis operators are survived with details. Next, some state-of-the-art methods are survived that use texture analysis in medical applications and disease diagnosis. Finally, different approaches are compared in terms of accuracy, data…
This paper proposes a new method, OFA-OCR, to transfer multimodal pretrained models to text recognition. Specifically, we recast text recognition as image captioning and directly transfer a unified vision-language pretrained model to the end task. Without pretraining on large-scale annotated or synthetic text recognition data, OFA-OCR outperforms the baselines and achieves state-of-the-art performance in the Chinese text recognition benchmark. Additionally, we construct an OCR pipeline with OFA-OCR, and we demonstrate that it can achieve competitive performance with the product-level API. The …
Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features in a target domain is an interesting and difficult problem that is rarely discussed in the current literature. This problem is essential for many real-world applications such as improving diagnostic classification or prediction in medical imaging. To address this problem, we propose Mutual-Information-based Disentangled Neural Networks (MIDNet) to extract ge…
Politecnico di Torino（都灵理工大学）；Istituto Italiano di Tecnologia（意大利理工学院）
Deep learning has thrived by training on large-scale datasets. However, in many applications, as for medical image diagnosis, getting massive amount of data is still prohibitive due to privacy, lack of acquisition homogeneity and annotation cost. In this scenario, transfer learning from natural image collections is a standard practice that attempts to tackle shape, texture and color discrepancies all at once through pretrained model fine-tuning. In this work, we propose to disentangle those challenges and design a dedicated network module that focuses on color adaptation. We combine learning f…
The performance on deep learning is significantly affected by volume of training data. Models pre-trained from massive dataset such as ImageNet become a powerful weapon for speeding up training convergence and improving accuracy. Similarly, models based on large dataset are important for the development of deep learning in 3D medical images. However, it is extremely challenging to build a sufficiently large dataset due to difficulty of data acquisition and annotation in 3D medical imaging. We aggregate the dataset from several medical challenges to build 3DSeg-8 dataset with diverse modalities…
The ability to automatically learn task specific feature representations has led to a huge success of deep learning methods. When large training data is scarce, such as in medical imaging problems, transfer learning has been very effective. In this paper, we systematically investigate the process of transferring a Convolutional Neural Network, trained on ImageNet images to perform image classification, to kidney detection problem in ultrasound images. We study how the detection performance depends on the extent of transfer. We show that a transferred and tuned CNN can outperform a state-of-the…
Deep learning-based computer-aided diagnosis is gradually deployed to review and analyze medical images. However, this paradigm is restricted in real-world clinical applications due to the poor robustness and generalization. The issue is more sinister with a lack of training data. In this paper, we address the challenge from the transfer learning point of view. Different from the common setting that transferring knowledge from the natural image domain to the medical image domain, we find the knowledge from the same domain further boosts the model robustness and generalization. Therefore, we pr…
Search is at the heart of modern e-commerce. As a result, the task of ranking search results automatically (learning to rank) is a multibillion dollar machine learning problem. Traditional models optimize over a few hand-constructed features based on the item's text. In this paper, we introduce a multimodal learning to rank model that combines these traditional features with visual semantic features transferred from a deep convolutional neural network. In a large scale experiment using data from the online marketplace Etsy, we verify that moving to a multimodal representation significantly imp…
Learning on a massive amount of speech corpus leads to the recent success of many self-supervised speech models. With knowledge distillation, these models may also benefit from the knowledge encoded by language models that are pre-trained on rich sources of texts. The distillation process, however, is challenging due to the modal disparity between textual and speech embedding spaces. This paper studies metric-based distillation to align the embedding space of text and speech with only a small amount of data without modifying the model structure. Since the semantic and granularity gap between t…
University of Bonn（波恩大学）；Indian Institute of Technology (ISM) Dhanbad（印度理工学院（印度矿业学院）丹巴德分校）；National University of Singapore（新加坡国立大学）
Can we teach a robot to recognize and make predictions for activities that it has never seen before? We tackle this problem by learning models for video from text. This paper presents a hierarchical model that generalizes instructional knowledge from large-scale text corpora and transfers the knowledge to video. Given a portion of an instructional video, our model recognizes and predicts coherent and plausible actions multiple steps into the future, all in rich natural language. To demonstrate the capabilities of our model, we introduce the \emph{Tasty Videos Dataset V2}, a collection of 4022 …
University of Washington（华盛顿大学）；Tel Aviv University（特拉维夫大学）；Swedish Medical Group（瑞典医疗集团）；University of California, Irvine（加州大学欧文分校）；Allen Institute for AI（艾伦人工智能研究所）
Understanding the relationship between figures and text is key to scientific document understanding. Medical figures in particular are quite complex, often consisting of several subfigures (75% of figures in our dataset), with detailed text describing their content. Previous work studying figures in scientific papers focused on classifying figure content rather than understanding how images relate to the text. To address challenges in figure retrieval and figure-to-text alignment, we introduce MedICaT, a dataset of medical images in context. MedICaT consists of 217K images from 131K open acces…
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Adobe（奥多比公司）；Carle Illinois College of Medicine（卡尔伊利诺伊医学院）
Existing vision-text contrastive learning like CLIP aims to match the paired image and caption embeddings while pushing others apart, which improves representation transferability and supports zero-shot prediction. However, medical image-text datasets are orders of magnitude below the general images and captions from the internet. Moreover, previous methods encounter many false negatives, i.e., images and reports from separate patients probably carry the same semantics but are wrongly treated as negatives. In this paper, we decouple images and texts for multimodal contrastive learning thus sca…
Adaptive Knowledge Transferring with Switching Dual-Student Framework for Semi-Supervised Medical Image Segmentation
North Carolina A&T State University（北卡罗来纳农工州立大学）；Carnegie Mellon University（卡内基梅隆大学）；Ho Chi Minh University of Technology（胡志明市理工大学）；University of Pittsburgh（匹兹堡大学）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）
University of Oulu（奥卢大学）；Beijing University of Posts and Telecommunications（北京邮电大学）
Dynamic texture and scene classification are two fundamental problems in understanding natural video content. Extracting robust and effective features is a crucial step towards solving these problems. However the existing approaches suffer from the sensitivity to either varying illumination, or viewpoint changing, or even camera motion, and/or the lack of spatial information. Inspired by the success of deep structures in image classification, we attempt to leverage a deep structure to extract feature for dynamic texture and scene classification. To tackle with the challenges in training a deep…
School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）；ByteDance Inc（字节跳动公司）
Image-text pretrained models, e.g., CLIP, have shown impressive general multi-modal knowledge learned from large-scale image-text data pairs, thus attracting increasing attention for their potential to improve visual representation learning in the video domain. In this paper, based on the CLIP model, we revisit temporal modeling in the context of image-to-video knowledge transferring, which is the key point for extending image-text pretrained models to the video domain. We find that current temporal modeling mechanisms are tailored to either high-level semantic-dominant tasks (e.g., retrieval)…
The University of Sydney（悉尼大学）；Baidu Inc.（百度公司）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. Along with the growth of computational capacity, we now have open-source vision-language pre-trained models in large scales of the model architecture and amount of data. In this study, we focus on transferring knowledge for video classification tasks. Conventional methods randomly initialize the linear classifier head for vision classification, but they leave the usage of the text encoder for downstream visual recognition tasks undiscovered. In this paper, w…
Feature Representation Transferring to Lightweight Models via Perception Coherence
Ampere Software Technology（Ampere软件技术公司）；Institut de mathématiques de Toulouse（图卢兹数学研究所）；Institut de Recherche en Informatique de Toulouse（图卢兹信息研究所）；Laboratoire Jean Alexandre Dieudonné, Université Côte d’Azur（Jean Alexandre Dieudonné实验室，蔚蓝海岸大学）；Université Côte d’Azur（蔚蓝海岸大学）
Video question answering (VideoQA) is designed to answer a given question based on a relevant video clip. The current available large-scale datasets have made it possible to formulate VideoQA as the joint understanding of visual and language information. However, this training procedure is costly and still less competent with human performance. In this paper, we investigate a transfer learning method by the introduction of domain-agnostic knowledge and domain-specific knowledge. First, we develop a novel transfer learning framework, which finetunes the pre-trained model by applying domain-agno…
Federal Institute of Education, Science and Technology of Brasilia（巴西利亚联邦教育、科学与技术学院）
Telemedicine and mobile health applications, especially during the quarantine imposed by the covid-19 pandemic, led to an increase on the need of transferring health monitor readings from patients to specialists. Considering that most home medical devices use seven-segment displays, an automatic display reading algorithm should provide a more reliable tool for remote health care. This work proposes an end-to-end method for detection and reading seven-segment displays from medical devices based on deep learning object detection models. Two state of the art model families, EfficientDet and Effic…
Knowledge distillation (KD), which can efficiently transfer knowledge from a cumbersome network (teacher) to a compact network (student), has demonstrated its advantages in some computer vision applications. The representation of knowledge is vital for knowledge transferring and student learning, which is generally defined in hand-crafted manners or uses the intermediate features directly. In this paper, we propose a model-agnostic meta knowledge distillation method under the teacher-student architecture for the single image super-resolution task. It provides a more flexible and accurate way t…
