We present a method for semantically transferring the visual appearance of one natural image to another. Specifically, our goal is to generate an image in which objects in a source structure image are "painted" with the visual appearance of their semantically related objects in a target appearance image. Our method works by training a generator given only a single structure/appearance image pair as input. To integrate semantic information into our framework - a pivotal component in tackling this task - our key idea is to leverage a pre-trained and fixed Vision Transformer (ViT) model which serves as an external semantic prior. Specifically, we derive novel representations of structure and appearance extracted from deep ViT features, untwisting them from the learned self-attention modules. We then establish an objective function that splices the desired structure and appearance representations, interweaving them together in the space of ViT features. Our framework, which we term "Splice", does not involve adversarial training, nor does it require any additional input information such as semantic segmentation or correspondences, and can generate high-resolution results, e.g., work in HD. We demonstrate high quality results on a variety of in-the-wild image pairs, under significant variations in the number of objects, their pose and appearance.
Guangdong Provincial People’s Hospital（广东省人民医院）；Guangdong Academy of Medical Sciences（广东省医学科学院）；Guangdong Cardiovascular Institute（广东省心血管病研究所）；Wuhan University（武汉大学）；Guangzhou Women and Children’s Medical Center（广州市妇女儿童医疗中心）；Guangzhou Medical University（广州医科大学）
Background: Medical images are more difficult to acquire and annotate than natural images, which results in data augmentation technologies often being used in medical image segmentation tasks. Most data augmentation technologies used in medical segmentation were originally developed on natural images and do not take into account the characteristic that the overall layout of medical images is standard and fixed. Methods: Based on the characteristics of medical images, we developed the cutting-splicing data augmentation (CS-DA) method, a novel data augmentation technology for medical image segme…
Dongguan Polytechnic（东莞职业技术学院）；Huazhong University of Science and Technology（华中科技大学）
For the problems of low recognition rate and slow recognition speed of traditional detection methods in IC appearance defect detection, we propose an IC appearance defect detection algo-rithm IH-ViT. Our proposed model takes advantage of the respective strengths of CNN and ViT to acquire image features from both local and global aspects, and finally fuses the two features for decision making to determine the class of defects, thus obtaining better accuracy of IC defect recognition. To address the problem that IC appearance defects are mainly reflected in the dif-ferences in details, which are …
The past few years have seen an increased interest in aerial image object detection due to its critical value to large-scale geo-scientific research like environmental studies, urban planning, and intelligence monitoring. However, the task is very challenging due to the birds-eye view perspective, complex backgrounds, large and various image sizes, different appearances of objects, and the scarcity of well-annotated datasets. Recent advances in computer vision have shown promise tackling the challenge. Specifically, Vision Transformer Detector (ViTDet) was proposed to extract multi-scale featu…
Al-Ahliyya Amman University（安曼阿赫利亚大学）；Budapest University of Technology and Economics（布达佩斯技术与经济大学）；Queensland University of Technology（昆士兰科技大学）；Arab American University（阿拉伯美国大学）；Columbia University（哥伦比亚大学）
Trichomonas Vaginalis Segmentation in Microscope Images
Qingdao Huajing Biotechnology CO., LTD（青岛华景生物科技有限公司）；Ocean University of China（海洋大学）；Qingdao University of Science and Technology（青岛科技大学）；Inception Institute of Artificial Intelligence（创启人工智能研究院）
University of Science and Technology of China（中国科学技术大学）；Peking University（北京大学）
This paper presents 6D-ViT, a transformer-based instance representation learning network, which is suitable for highly accurate category-level object pose estimation on RGB-D images. Specifically, a novel two-stream encoder-decoder framework is dedicated to exploring complex and powerful instance representations from RGB images, point clouds and categorical shape priors. For this purpose, the whole framework consists of two main branches, named Pixelformer and Pointformer. The Pixelformer contains a pyramid transformer encoder with an all-MLP decoder to extract pixelwise appearance representat…
The Johns Hopkins University（约翰斯·霍普金斯大学）；University of California at Los Angeles（加利福尼亚大学洛杉矶分校）
Recent advances in brain clearing and imaging have made it possible to image entire mammalian brains at sub-micron resolution. These images offer the potential to assemble brain-wide atlases of neuron morphology, but manual neuron reconstruction remains a bottleneck. Several automatic reconstruction algorithms exist, but most focus on single neuron images. In this paper, we present a probabilistic reconstruction method, ViterBrain, which combines a hidden Markov state process that encodes neuron geometry with a random field appearance model of neuron fluorescence. Our method utilizes dynamic p…
Shenzhen Key Lab of Comp. Vis. & Pat. Rec., Shenzhen Institutes of Advanced Technology, CAS（中国科学院深圳先进技术研究院计算机视觉与模式识别深圳市重点实验室）；The Chinese University of Hong Kong（香港中文大学）；SenseTime Group Limited（商汤集团有限公司）；Tsinghua University（清华大学）；The University of Sydney（悉尼大学）
Object detection in videos has drawn increasing attention recently with the introduction of the large-scale ImageNet VID dataset. Different from object detection in static images, temporal information in videos is vital for object detection. To fully utilize temporal information, state-of-the-art methods are based on spatiotemporal tubelets, which are essentially sequences of associated bounding boxes across time. However, the existing methods have major limitations in generating tubelets in terms of quality and efficiency. Motion-based methods are able to obtain dense tubelets efficiently, bu…
Enormous hand images with reliable annotations are collected through marker-based MoCap. Unfortunately, degradations caused by markers limit their application in hand appearance reconstruction. A clear appearance recovery insight is an image-to-image translation trained with unpaired data. However, most frameworks fail because there exists structure inconsistency from a degraded hand to a bare one. The core of our approach is to first disentangle the bare hand structure from those degraded images and then wrap the appearance to this structure with a dual adversarial discrimination (DAD) scheme…
Mamba-Sea: A Mamba-based Framework with Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation
Shanghai Jiao Tong University School of Medicine（上海交通大学医学院）；National Institute of Healthcare Data Science（健康数据科学国家研究院）；State Key Laboratory for Novel Software Technology（新型软件技术国家重点实验室）；School of Computer Science and Engineering（计算机科学与工程学院）；Key Lab of Computer Network and Information Integration（计算机网络与信息集成重点实验室）；School of Electrical and Information Engineering（电气与信息工程学院）；The University of Sydney（悉尼大学）
Self-supervised video transformer pre-training has recently benefited from the mask-and-predict pipeline. They have demonstrated outstanding effectiveness on downstream video tasks and superior data efficiency on small datasets. However, temporal relation is not fully exploited by these methods. In this work, we explicitly investigate motion cues in videos as extra prediction target and propose our Masked Appearance-Motion Modeling (MAM2) framework. Specifically, we design an encoder-regressor-decoder pipeline for this task. The regressor separates feature encoding and pretext tasks completion…
LineArt: A Knowledge-guided Training-free High-quality Appearance Transfer for Design Drawing with Diffusion Model
KTH Royal Institute of Technology（瑞典皇家理工学院）；Jilin University（吉林大学）；Tokyo Institute of Technology（东京工业大学）；Japan Advanced Institute of Science and Technology (JAIST)（日本先进科学技术学院）
Zhejiang University（浙江大学）；Zhejiang University-University of Illinois Urbana-Champaign Institute（浙江大学伊利诺伊大学厄巴纳香槟校区联合学院）；Donghua University（东华大学）；Hangzhou Dianzi University（杭州电子科技大学）
Image-based fashion design with AI techniques has attracted increasing attention in recent years. We focus on a new fashion design task, where we aim to transfer a reference appearance image onto a clothing image while preserving the structure of the clothing image. It is a challenging task since there are no reference images available for the newly designed output fashion images. Although diffusion-based image translation or neural style transfer (NST) has enabled flexible style transfer, it is often difficult to maintain the original structure of the image realistically during the reverse di…
Disentangled representation learning finds compact, independent and easy-to-interpret factors of the data. Learning such has been shown to require an inductive bias, which we explicitly encode in a generative model of images. Specifically, we propose a model with two latent spaces: one that represents spatial transformations of the input data, and another that represents the transformed data. We find that the latter naturally captures the intrinsic appearance of the data. To realize the generative model, we propose a Variationally Inferred Transformational Autoencoder (VITAE) that incorporates…
Diffusion-based image translation guided by semantic texts or a single target image has enabled flexible style transfer which is not limited to the specific domains. Unfortunately, due to the stochastic nature of diffusion models, it is often difficult to maintain the original content of the image during the reverse diffusion. To address this, here we present a novel diffusion-based unsupervised image translation method using disentangled style and content representation. Specifically, inspired by the splicing Vision Transformer, we extract intermediate keys of multihead self attention layer f…
LQ-Adapter: ViT-Adapter with Learnable Queries for Gallbladder Cancer Detection from Ultrasound Image
IIT Delhi（印度理工学院德里分校）；University of California San Diego（加利福尼亚大学圣迭戈分校）；Samsung R&D Institute Bangalore（三星研发班加罗尔研究所）；PGIMER, Chandigarh（昌迪加尔医学教育与研究研究生院）
Learning image representations with ConvNets by pre-training on ImageNet has proven useful across many visual understanding tasks including object detection, semantic segmentation, and image captioning. Although any image representation can be applied to video frames, a dedicated spatiotemporal representation is still vital in order to incorporate motion patterns that cannot be captured by appearance based models alone. This paper presents an empirical ConvNet architecture search for spatiotemporal feature learning, culminating in a deep 3-dimensional (3D) Residual ConvNet. Our proposed archit…
Weizmann Institute of Science（魏茨曼科学研究所）；NVIDIA Research（英伟达研究院）
We present Neural Congealing -- a zero-shot self-supervised framework for detecting and jointly aligning semantically-common content across a given set of images. Our approach harnesses the power of pre-trained DINO-ViT features to learn: (i) a joint semantic atlas -- a 2D grid that captures the mode of DINO-ViT features in the input set, and (ii) dense mappings from the unified atlas to each of the input images. We derive a new robust self-supervised framework that optimizes the atlas representation and mappings per image set, requiring only a few real-world images as input without any additi…
BrainFusionNet: a deep learning and XAI model to understand local, global, and sequential features of MRI images for improved brain tumour detection
School of Mathematics, Physics and Computing, University of Southern Queensland（南方昆士兰大学数学、物理与计算学院）；School of Engineering, University of Southern Queensland（南方昆士兰大学工程学院）
Institute of Cyber-Systems and Control, Zhejiang University（浙江大学网络系统与控制研究所）；State Key Laboratory of Industrial Control Technology（工业控制技术国家重点实验室）
Autonomous robots enjoy a wide popularity nowadays and have been applied in many applications, such as home security, entertainment, delivery, navigation and guidance. It is vital to robots to track objects accurately in these applications, so it is necessary to focus on tracking algorithms to improve the robustness and accuracy. In this paper, we propose a robust object tracking algorithm based on a hierarchical ensemble framework which can incorporate information including individual pixel features, local patches and holistic target models. The framework combines multiple ensemble models sim…
Autonomous systems need to localize and track surrounding objects in 3D space for safe motion planning. As a result, 3D multi-object tracking (MOT) plays a vital role in autonomous navigation. Most MOT methods use a tracking-by-detection pipeline, which includes object detection and data association processing. However, many approaches detect objects in 2D RGB sequences for tracking, which is lack of reliability when localizing objects in 3D space. Furthermore, it is still challenging to learn discriminative features for temporally-consistent detection in different frames, and the affinity mat…
University of South Carolina（南卡罗来纳大学）；PAII Inc.（PAII公司）；University of Rochester（罗切斯特大学）；Chang Gung Memorial Hospital（长庚纪念医院）；Ping An Technology（平安科技）
Accurate segmentation of anatomical structures is vital for medical image analysis. The state-of-the-art accuracy is typically achieved by supervised learning methods, where gathering the requisite expert-labeled image annotations in a scalable manner remains a main obstacle. Therefore, annotation-efficient methods that permit to produce accurate anatomical structure segmentation are highly desirable. In this work, we present Contour Transformer Network (CTN), a one-shot anatomy segmentation method with a naturally built-in human-in-the-loop mechanism. We formulate anatomy segmentation as a co…
Nitte Meenakshi Institute of Technology（尼特·米纳克希理工学院）
It is human nature to give prime importance to facial appearances. Often, to look good is to feel good. Also, facial features are unique to every individual on this planet, which means it is a source of vital information. This work proposes a framework named E-Pro for the detection and recognition of faces by taking facial images as inputs. E-Pro has its potential application in various domains, namely attendance, surveillance, crowd monitoring, biometric-based authentication etc. E-Pro is developed here as a mobile application that aims to aid lecturers to mark attendance in a classroom by de…
SDF-Net: Structure-Aware Disentangled Feature Learning for Opticall-SAR Ship Re-identification
Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences（中国科学院空间利用技术与工程中心）；Key Laboratory of Space Utilization, Chinese Academy of Sciences（中国科学院空间利用重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；School of Software, Beihang University（北航软件学院）
Revisiting Feature Prediction for Learning Visual Representations from Video
FAIR at Meta（Meta FAIR实验室）；Inria（法国国家信息与自动化研究所）；École normale supérieure, CNRS, PSL Research University（巴黎高等师范学院、法国国家科学研究中心、PSL大学）；Univ. Gustave Eiffel, CNRS, LIGM（古斯塔夫·埃菲尔大学、法国国家科学研究中心、LIGM实验室）；Courant Institute, New York University（纽约大学柯朗数学科学研究所）；Center for Data Science, New York University（纽约大学数据科学中心）
