In Digital Holography (DH), it is crucial to extract the object distance from a hologram in order to reconstruct its amplitude and phase. This step is called auto-focusing and it is conventionally solved by first reconstructing a stack of images and then by sharpening each reconstructed image using a focus metric such as entropy or variance. The distance corresponding to the sharpest image is considered the focal position. This approach, while effective, is computationally demanding and time-consuming. In this paper, the determination of the distance is performed by Deep Learning (DL). Two deep learning (DL) architectures are compared: Convolutional Neural Network (CNN) and Vision Transformer (ViT). ViT and CNN are used to cope with the problem of auto-focusing as a classification problem. Compared to a first attempt [11] in which the distance between two consecutive classes was 100$μ$m, our proposal allows us to drastically reduce this distance to 1$μ$m. Moreover, ViT reaches similar accuracy and is more robust than CNN.
Digital holography enables us to reconstruct objects in three-dimensional space from holograms captured by an imaging device. For the reconstruction, we need to know the depth position of the recoded object in advance. In this study, we propose depth prediction using convolutional neural network (CNN)-based regression. In the previous researches, the depth of an object was estimated through reconstructed images at different depth positions from a hologram using a certain metric that indicates the most focused depth position; however, such a depth search is time-consuming. The CNN of the propos…
the University of New South Wales（新南威尔士大学）；the University of Sydney（悉尼大学）；Data61, The Commonwealth Scientific and Industrial Research Organisation (CSIRO)（联邦科学与工业研究组织（CSIRO）Data61）
Deep learning technology can be used as an assistive technology to help doctors quickly and accurately identify COVID-19 infections. Recently, Vision Transformer (ViT) has shown great potential towards image classification due to its global receptive field. However, due to the lack of inductive biases inherent to CNNs, the ViT-based structure leads to limited feature richness and difficulty in model training. In this paper, we propose a new structure called Transformer for COVID-19 (COVT) to improve the performance of ViT-based architectures on small COVID-19 datasets. It uses CNN as a feature…
University of Munich（慕尼黑大学）；Google Research（谷歌研究院）
Recent advances in Vision Transformer (ViT) have demonstrated its impressive performance in image classification, which makes it a promising alternative to Convolutional Neural Network (CNN). Unlike CNNs, ViT represents an input image as a sequence of image patches. The patch-based input image representation makes the following question interesting: How does ViT perform when individual input image patches are perturbed with natural corruptions or adversarial perturbations, compared to CNNs? In this work, we study the robustness of ViT to patch-wise perturbations. Surprisingly, we find that ViT…
State of the art magnetic resonance (MR) image super-resolution methods (ISR) using convolutional neural networks (CNNs) leverage limited contextual information due to the limited spatial coverage of CNNs. Vision transformers (ViT) learn better global context that is helpful in generating superior quality HR images. We combine local information of CNNs and global information from ViTs for image super resolution and output super resolved images that have superior quality than those produced by state of the art methods. We include extra constraints through multiple novel loss functions that pres…
Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation
Graduate School of Data Science, Chonnam National University（全南国立大学数据科学研究生院）；Department of Computer Science, National Yang Ming Chiao Tung University（国立阳明交通大学计算机科学系）；Digital Transformation Center, FPT Telecom（FPT电信数字化转型中心）；AI Graduate School, GIST（光州科学技术院人工智能研究生院）
nnMobileNet: Rethinking CNN for Retinopathy Research
School of Computing and Augmented Intelligence, Arizona State University（亚利桑那州立大学计算与增强智能学院）；School of Computing, Clemson University（克莱姆森大学计算学院）；Children’s Hospital Los Angeles（洛杉矶儿童医院）；Mayo Clinic（梅奥诊所）
本文针对 ViT 在视网膜疾病诊断中数据与计算需求高、小病灶定位困难的问题，选择性改进 MobileNet，提出 nnMobileNet，并在多个眼底基准上超过 ViT 模型。
Carnegie Mellon University（卡内基梅隆大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）
The Vision Transformer (ViT) architecture has recently achieved competitive performance across a variety of computer vision tasks. One of the motivations behind ViTs is weaker inductive biases, when compared to convolutional neural networks (CNNs). However this also makes ViTs more difficult to train. They require very large training datasets, heavy regularization, and strong data augmentations. The data augmentation strategies used to train ViTs have largely been inherited from CNN training, despite the significant differences between the two architectures. In this work, we empirical evaluate…
A Lightweight Complex-Valued Deformable CNN for High-Quality Computer-Generated Holography
Thrust of Microelectronics of Function Hub, The Hong Kong University of Science and Technology (Guangzhou)（功能枢纽微电子研究所，香港理工大学（广州））；College of Electronics and Information Engineering, Sichuan University（电子信息工程学院，四川大学）
Pohang University of Science and Technology（浦项科技大学）
Vision transformers (ViTs) have recently demonstrated state-of-the-art performance in a variety of vision tasks, replacing convolutional neural networks (CNNs). Meanwhile, since ViT has a different architecture than CNN, it may behave differently. To investigate the reliability of ViT, this paper studies the behavior and robustness of ViT. We compared the robustness of CNN and ViT by assuming various image corruptions that may appear in practical vision tasks. We confirmed that for most image transformations, ViT showed robustness comparable to CNN or more improved. However, for contrast enhan…
Zhejiang University（浙江大学）；Shanghai Institute for Advanced Study of Zhejiang University（浙江大学上海高等研究院）
Recently, vision Transformers (ViTs) are developing rapidly and starting to challenge the domination of convolutional neural networks (CNNs) in the realm of computer vision (CV). With the general-purpose Transformer architecture replacing the hard-coded inductive biases of convolution, ViTs have surpassed CNNs, especially in data-sufficient circumstances. However, ViTs are prone to over-fit on small datasets and thus rely on large-scale pre-training, which expends enormous time. In this paper, we strive to liberate ViTs from pre-training by introducing CNNs' inductive biases back to ViTs while…
Due to the complex attention mechanisms and model design, most existing vision Transformers (ViTs) can not perform as efficiently as convolutional neural networks (CNNs) in realistic industrial deployment scenarios, e.g. TensorRT and CoreML. This poses a distinct challenge: Can a visual neural network be designed to infer as fast as CNNs and perform as powerful as ViTs? Recent works have tried to design CNN-Transformer hybrid architectures to address this issue, yet the overall performance of these works is far away from satisfactory. To end these, we propose a next generation vision Transform…
Beihang University（北京航空航天大学）；Peking University（北京大学）；Shanghai AI Laboratory（上海人工智能实验室）
Vision Transformers (ViTs) have achieved impressive performance on various vision tasks, yet their generalization under distribution shifts (DS) is rarely understood. In this work, we comprehensively study the out-of-distribution (OOD) generalization of ViTs. For systematic investigation, we first present a taxonomy of DS. We then perform extensive evaluations of ViT variants under different DS and compare their generalization with Convolutional Neural Network (CNN) models. Important observations are obtained: 1) ViTs learn weaker biases on backgrounds and textures, while they are equipped wit…
Diabetic retinopathy (DR) is a leading cause of vision loss among middle-aged and elderly people, which significantly impacts their daily lives and mental health. To improve the efficiency of clinical screening and enable the early detection of DR, a variety of automated DR diagnosis systems have been recently established based on convolutional neural network (CNN) or vision Transformer (ViT). However, due to the own shortages of CNN / ViT, the performance of existing methods using single-type backbone has reached a bottleneck. One potential way for the further improvements is integrating diff…
Unleashing Vision Foundation Models for Coronary Artery Segmentation: Parallel ViT-CNN Encoding and Variational Fusion
National-Local Joint Engineering Research Center of Biodiagnosis \& Biotherapy, the Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an, 710004, China Institute of Medical Artificial Intelligence, the Second Affiliated Hospital of Xi’an Jiaotong University, Xi'an, 710004, China Viadrina European University, Frankfurt (Oder), 15230, Germany
Texture Representations in Deep Vision Models: Comparing CNNs, Vision Transformers, and Human Perception
Department of Neuroscience International School for Advanced Studies (SISSA) Trieste Italy（神经科学系国际先进研究学院（SISSA）特里埃斯特意大利）；Department of Language and Translation Sciences Pompeu Fabra University Barcelona Spain（语言与翻译科学系庞培法布拉大学巴塞罗那西班牙）；ICREA Barcelona Spain（ICREA巴塞罗那西班牙）；Department of Data Science International School for Advanced Studies (SISSA) Trieste Italy（数据科学系国际先进研究学院（SISSA）特里埃斯特意大利）
OPPO；North China University of Technology（北方工业大学）；Neolix Autonomous Vehicle（新石器自动驾驶）；University of Science and Technology of China（中国科学技术大学）
Vision Transformers (ViTs) have recently dominated a range of computer vision tasks, yet it suffers from low training data efficiency and inferior local semantic representation capability without appropriate inductive bias. Convolutional neural networks (CNNs) inherently capture regional-aware semantics, inspiring researchers to introduce CNNs back into the architecture of the ViTs to provide desirable inductive bias for ViTs. However, is the locality achieved by the micro-level CNNs embedded in ViTs good enough? In this paper, we investigate the problem by profoundly exploring how the macro a…
The Chinese University of Hong Kong（香港中文大学）；Samsung AI Cambridge（三星剑桥人工智能中心）；Queen Mary University of London（伦敦玛丽女王大学）
Self-attention based models such as vision transformers (ViTs) have emerged as a very competitive architecture alternative to convolutional neural networks (CNNs) in computer vision. Despite increasingly stronger variants with ever-higher recognition accuracies, due to the quadratic complexity of self-attention, existing ViTs are typically demanding in computation and model size. Although several successful design choices (e.g., the convolutions and hierarchical multi-stage structure) of prior CNNs have been reintroduced into recent ViTs, they are still not sufficient to meet the limited resou…
H-CNN-ViT: A Hierarchical Gated Attention Multi-Branch Model for Bladder Cancer Recurrence Prediction
Engineering, University of Notre Dame, USA（工程学院，诺特大学，美国）；Department of Urology, The First Affiliated Hospital, Sun Yat-sen University, China（泌尿科，中山大学附属第一医院，中国）
For several skin conditions such as vitiligo, accurate segmentation of lesions from skin images is the primary measure of disease progression and severity. Existing methods for vitiligo lesion segmentation require manual intervention. Unfortunately, manual segmentation is time and labor-intensive, as well as irreproducible between physicians. We introduce a convolutional neural network (CNN) that quickly and robustly performs vitiligo skin lesion segmentation. Our CNN has a U-Net architecture with a modified contracting path. We use the CNN to generate an initial segmentation of the lesion, th…
Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；International Digital Economy Academy (IDEA)（国际数字经济研究院（IDEA））；Beihang University（北京航空航天大学）
Knowledge Distillation (KD) for Convolutional Neural Network (CNN) is extensively studied as a way to boost the performance of a small model. Recently, Vision Transformer (ViT) has achieved great success on many computer vision tasks and KD for ViT is also desired. However, besides the output logit-based KD, other feature-based KD methods for CNNs cannot be directly applied to ViT due to the huge structure gap. In this paper, we explore the way of feature-based distillation for ViT. Based on the nature of feature maps in ViT, we design a series of controlled experiments and derive three practi…
Hamburg University of Technology（汉堡工业大学）；Jung Diagnostics GmbH（荣格诊断有限公司）
Radiographs are a versatile diagnostic tool for the detection and assessment of pathologies, for treatment planning or for navigation and localization purposes in clinical interventions. However, their interpretation and assessment by radiologists can be tedious and error-prone. Thus, a wide variety of deep learning methods have been proposed to support radiologists interpreting radiographs. Mostly, these approaches rely on convolutional neural networks (CNN) to extract features from images. Especially for the multi-label classification of pathologies on chest radiographs (Chest X-Rays, CXR), …
A Comparative Study of Vision Transformers and CNNs for Few-Shot Rigid Transformation and Fundamental Matrix Estimation
Department of Computer Science, Ben-Gurion University of the Negev（本·古里安大学内盖夫分校计算机科学系）；School of Electrical and Computer Engineering, Ben-Gurion University of the Negev（本·古里安大学内盖夫分校电气与计算机工程学院）；GE Healthcare Science and Technology（通用电气医疗科技）
Zhejiang University（浙江大学）；Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）
Continual learning is a longstanding research topic due to its crucial role in tackling continually arriving tasks. Up to now, the study of continual learning in computer vision is mainly restricted to convolutional neural networks (CNNs). However, recently there is a tendency that the newly emerging vision transformers (ViTs) are gradually dominating the field of computer vision, which leaves CNN-based continual learning lagging behind as they can suffer from severe performance degradation if straightforwardly applied to ViTs. In this paper, we study ViT-backed continual learning to strive fo…
Convolutional Neural Networks (CNNs) have become the de facto gold standard in computer vision applications in the past years. Recently, however, new model architectures have been proposed challenging the status quo. The Vision Transformer (ViT) relies solely on attention modules, while the MLP-Mixer architecture substitutes the self-attention modules with Multi-Layer Perceptrons (MLPs). Despite their great success, CNNs have been widely known to be vulnerable to adversarial attacks, causing serious concerns for security-sensitive applications. Thus, it is critical for the community to know wh…
Hybrid Convolution and Vision Transformer NAS Search Space for TinyML Image Classification
Chair of Electronic Design Automation, Technical University of Munich（电子设计自动化研究所，慕尼黑技术大学）；Department of Computer Science, University of Tübingen（计算机科学系，图宾根大学）；Institute of Computer Engineering, TU Wien（计算机工程研究所，维也纳技术大学）
University of Oslo（奥斯陆大学）；Oslo New University College（奥斯陆新大学学院）
Behavioral studies have shown that the memorability of images is similar across groups of people, suggesting that memorability is a function of the intrinsic properties of images, and is unrelated to people's individual experiences and traits. Deep learning networks can be trained on such properties and be used to predict memorability in new data sets. Convolutional neural networks (CNN) have pioneered image memorability prediction, but more recently developed vision transformer (ViT) models may have the potential to yield even better predictions. In this paper, we present the ViTMem, a new me…
Fixed-Threshold Evaluation of a Hybrid CNN-ViT for AI-Generated Image Detection Across Photos and Art
Department of Computer Science and Engineering, Indian Institute of Technology Kharagpur, India（计算机科学与工程系，印度理工学院Kharagpur分校）；Department of Electrical and Electronic Engineering, Chittagong University of Engineering and Technology, Bangladesh（电气与电子工程系，查塔格工学院）
Zhejiang University（浙江大学）；University of Munich（慕尼黑大学）；Tencent（腾讯）
Vision Transformer (ViT), as a powerful alternative to Convolutional Neural Network (CNN), has received much attention. Recent work showed that ViTs are also vulnerable to adversarial examples like CNNs. To build robust ViTs, an intuitive way is to apply adversarial training since it has been shown as one of the most effective ways to accomplish robust CNNs. However, one major limitation of adversarial training is its heavy computational cost. The self-attention mechanism adopted by ViTs is a computationally intense operation whose expense increases quadratically with the number of input patch…
Evaluating Graphical Perception Capabilities of Vision Transformers
Viscom Group, Institute of Media Informatics, Ulm University（Viscom集团，媒体信息学研究所，乌尔姆大学）；ViRVIG Group, Universitat Politècnica de Catalunya - BarcelonaTech（ViRVIG集团，巴塞罗那技术大学-加泰罗尼亚理工大学）；Ulm University（乌尔姆大学）
This paper proposes a working recipe of using Vision Transformer (ViT) in class incremental learning. Although this recipe only combines existing techniques, developing the combination is not trivial. Firstly, naive application of ViT to replace convolutional neural networks (CNNs) in incremental learning results in serious performance degradation. Secondly, we nail down three issues of naively using ViT: (a) ViT has very slow convergence when the number of classes is small, (b) more bias towards new classes is observed in ViT than CNN-based architectures, and (c) the conventional learning rat…
