Authors: Narongrid Seesawad, Piyalitt Ittichaiwong, Thapanun Sudhawiyangkul, Phattarapong Sawangjai, Peti Thuwajit, Paisarn Boonsakan, Supasan Sripodok, Kanyakorn Veerakanjana, Phoomraphee Luenam, Komgrid Charngkaew, Ananya Pongpaibul, Napat Angkathunyakul, Narit Hnoohom, Sumeth Yuenyong, Chanitra Thuwajit, Theerawit Wilaiprasitporn
Patch classification models based on deep learning have been utilized in whole-slide images (WSI) of H&E-stained tissue samples to assist pathologists in grading follicular lymphoma patients. However, these approaches still require pathologists to manually identify centroblast cells and provide refined labels for optimal performance. To address this, we propose PseudoCell, an object detection framework to automate centroblast detection in WSI (source code is available at https://github.com/IoBT-VISTEC/PseudoCell.git). This framework incorporates centroblast labels from pathologists and combines them with pseudo-negative labels obtained from undersampled false-positive predictions using the cell's morphological features. By employing PseudoCell, pathologists' workload can be reduced as it accurately narrows down the areas requiring their attention during examining tissue. Depending on the confidence threshold, PseudoCell can eliminate 58.18-99.35% of non-centroblasts tissue areas on WSI. This study presents a practical centroblast prescreening method that does not require pathologists' refined labels for improvement. Detailed guidance on the practical implementation of PseudoCell is provided in the discussion section.
Authors: Weiliang Chan, Qianqian Ren
Urban region embedding is an important and yet highly challenging issue due to the complexity and constantly changing nature of urban data. To address the challenges, we propose a Region-Wise Multi-View Representation Learning (ROMER) to capture multi-view dependencies and learn expressive representations of urban regions without the constraints of rigid neighbourhood region conditions. Our model focus on learn urban region representation from multi-source urban data. First, we capture the multi-view correlations from mobility flow patterns, POI semantics and check-in dynamics. Then, we adopt global graph attention networks to learn similarity of any two vertices in graphs. To comprehensively consider and share features of multiple views, a two-stage fusion module is further proposed to learn weights with external attention to fuse multi-view embeddings. Extensive experiments for two downstream tasks on real-world datasets demonstrate that our model outperforms state-of-the-art methods by up to 17\% improvement.
Authors: Mahdi Alehdaghi, Arthur Josi, Pourya Shamsolmoali, Rafael M. O. Cruz, Eric Granger
Visible-infrared person re-identification seeks to retrieve images of the same individual captured over a distributed network of RGB and IR sensors. Several V-I ReID approaches directly integrate both V and I modalities to discriminate persons within a shared representation space. However, given the significant gap in data distributions between V and I modalities, cross-modal V-I ReID remains challenging. Some recent approaches improve generalization by leveraging intermediate spaces that can bridge V and I modalities, yet effective methods are required to select or generate data for such informative domains. In this paper, the Adaptive Generation of Privileged Intermediate Information training approach is introduced to adapt and generate a virtual domain that bridges discriminant information between the V and I modalities. The key motivation behind AGPI^2 is to enhance the training of a deep V-I ReID backbone by generating privileged images that provide additional information. These privileged images capture shared discriminative features that are not easily accessible within the original V or I modalities alone. Towards this goal, a non-linear generative module is trained with an adversarial objective, translating V images into intermediate spaces with a smaller domain shift w.r.t. the I domain. Meanwhile, the embedding module within AGPI^2 aims to produce similar features for both V and generated images, encouraging the extraction of features that are common to all modalities. In addition to these contributions, AGPI^2 employs adversarial objectives for adapting the intermediate images, which play a crucial role in creating a non-modality-specific space to address the large domain shifts between V and I domains. Experimental results conducted on challenging V-I ReID datasets indicate that AGPI^2 increases matching accuracy without extra computational resources during inference.
Authors: Jie Zhang, Masanori Suganuma, Takayuki Okatani
Recent studies on visual anomaly detection (AD) of industrial objects/textures have achieved quite good performance. They consider an unsupervised setting, specifically the one-class setting, in which we assume the availability of a set of normal (\textit{i.e.}, anomaly-free) images for training. In this paper, we consider a more challenging scenario of unsupervised AD, in which we detect anomalies in a given set of images that might contain both normal and anomalous samples. The setting does not assume the availability of known normal data and thus is completely free from human annotation, which differs from the standard AD considered in recent studies. For clarity, we call the setting blind anomaly detection (BAD). We show that BAD can be converted into a local outlier detection problem and propose a novel method named PatchCluster that can accurately detect image- and pixel-level anomalies. Experimental results show that PatchCluster shows a promising performance without the knowledge of normal data, even comparable to the SOTA methods applied in the one-class setting needing it.
Authors: Kai Yan, Fujun Luan, MiloŠ HaŠAn, Thibault Groueix, Valentin Deschaintre, Shuang Zhao
A 3D digital scene contains many components: lights, materials and geometries, interacting to reach the desired appearance. Staging such a scene is time-consuming and requires both artistic and technical skills. In this work, we propose PSDR-Room, a system allowing to optimize lighting as well as the pose and materials of individual objects to match a target image of a room scene, with minimal user input. To this end, we leverage a recent path-space differentiable rendering approach that provides unbiased gradients of the rendering with respect to geometry, lighting, and procedural materials, allowing us to optimize all of these components using gradient descent to visually match the input photo appearance. We use recent single-image scene understanding methods to initialize the optimization and search for appropriate 3D models and materials. We evaluate our method on real photographs of indoor scenes and demonstrate the editability of the resulting scene components.
Authors: Clayton Fields, Casey Kennington
Vision language tasks, such as answering questions about or generating captions that describe an image, are difficult tasks for computers to perform. A relatively recent body of research has adapted the pretrained transformer architecture introduced in \citet{vaswani2017attention} to vision language modeling. Transformer models have greatly improved performance and versatility over previous vision language models. They do so by pretraining models on a large generic datasets and transferring their learning to new tasks with minor changes in architecture and parameter values. This type of transfer learning has become the standard modeling practice in both natural language processing and computer vision. Vision language transformers offer the promise of producing similar advancements in tasks which require both vision and language. In this paper, we provide a broad synthesis of the currently available research on vision language transformer models and offer some analysis of their strengths, limitations and some open questions that remain.
Authors: Heejong Kim, Victor Ion Butoi, Adrian V. Dalca, Mert R. Sabuncu
Most state-of-the-art techniques for medical image segmentation rely on deep-learning models. These models, however, are often trained on narrowly-defined tasks in a supervised fashion, which requires expensive labeled datasets. Recent advances in several machine learning domains, such as natural language generation have demonstrated the feasibility and utility of building foundation models that can be customized for various downstream tasks with little to no labeled data. This likely represents a paradigm shift for medical imaging, where we expect that foundation models may shape the future of the field. In this paper, we consider a recently developed foundation model for medical image segmentation, UniverSeg. We conduct an empirical evaluation study in the context of prostate imaging and compare it against the conventional approach of training a task-specific segmentation model. Our results and discussion highlight several important factors that will likely be important in the development and adoption of foundation models for medical image segmentation.
Authors: Louis Airale (UGA, LIG), Dominique Vaufreydaz (LIG), Xavier Alameda-Pineda (UGA)
Animating still face images with deep generative models using a speech input signal is an active research topic and has seen important recent progress. However, much of the effort has been put into lip syncing and rendering quality while the generation of natural head motion, let alone the audio-visual correlation between head motion and speech, has often been neglected. In this work, we propose a multi-scale audio-visual synchrony loss and a multi-scale autoregressive GAN to better handle short and long-term correlation between speech and the dynamics of the head and lips. In particular, we train a stack of syncer models on multimodal input pyramids and use these models as guidance in a multi-scale generator network to produce audio-aligned motion unfolding over diverse time scales. Our generator operates in the facial landmark domain, which is a standard low-dimensional head representation. The experiments show significant improvements over the state of the art in head motion dynamics quality and in multi-scale audio-visual synchrony both in the landmark domain and in the image domain.
Authors: Mokshagna Sai Teja Karanam, Tushar Kataria, Shireen Elhabian
Statistical shape models (SSM) have been well-established as an excellent tool for identifying variations in the morphology of anatomy across the underlying population. Shape models use consistent shape representation across all the samples in a given cohort, which helps to compare shapes and identify the variations that can detect pathologies and help in formulating treatment plans. In medical imaging, computing these shape representations from CT/MRI scans requires time-intensive preprocessing operations, including but not limited to anatomy segmentation annotations, registration, and texture denoising. Deep learning models have demonstrated exceptional capabilities in learning shape representations directly from volumetric images, giving rise to highly effective and efficient Image-to-SSM. Nevertheless, these models are data-hungry and due to the limited availability of medical data, deep learning models tend to overfit. Offline data augmentation techniques, that use kernel density estimation based (KDE) methods for generating shape-augmented samples, have successfully aided Image-to-SSM networks in achieving comparable accuracy to traditional SSM methods. However, these augmentation methods focus on shape augmentation, whereas deep learning models exhibit texture bias results in sub-optimal models. This paper introduces a novel strategy for on-the-fly data augmentation for the Image-to-SSM framework by leveraging data-dependent noise generation or texture augmentation. The proposed framework is trained as an adversary to the Image-to-SSM network, augmenting diverse and challenging noisy samples. Our approach achieves improved accuracy by encouraging the model to focus on the underlying geometry rather than relying solely on pixel values.
Authors: Enfa George, Mihai Surdeanu
We introduce SexTok, a multi-modal dataset composed of TikTok videos labeled as sexually suggestive (from the annotator's point of view), sex-educational content, or neither. Such a dataset is necessary to address the challenge of distinguishing between sexually suggestive content and virtual sex education videos on TikTok. Children's exposure to sexually suggestive videos has been shown to have adversarial effects on their development. Meanwhile, virtual sex education, especially on subjects that are more relevant to the LGBTQIA+ community, is very valuable. The platform's current system removes or penalizes some of both types of videos, even though they serve different purposes. Our dataset contains video URLs, and it is also audio transcribed. To validate its importance, we explore two transformer-based models for classifying the videos. Our preliminary results suggest that the task of distinguishing between these types of videos is learnable but challenging. These experiments suggest that this dataset is meaningful and invites further study on the subject.
Authors: Tushar Kataria, Beatrice Knudsen, Shireen Elhabian
Annotating medical imaging datasets is costly, so fine-tuning (or transfer learning) is the most effective method for digital pathology vision applications such as disease classification and semantic segmentation. However, due to texture bias in models trained on real-world images, transfer learning for histopathology applications might result in underperforming models, which necessitates the need for using unlabeled histopathology data and self-supervised methods to discover domain-specific characteristics. Here, we tested the premise that histopathology-specific pretrained models provide better initializations for pathology vision tasks, i.e., gland and cell segmentation. In this study, we compare the performance of gland and cell segmentation tasks with domain-specific and non-domain-specific pretrained weights. Moreover, we investigate the data size at which domain-specific pretraining produces a statistically significant difference in performance. In addition, we investigated whether domain-specific initialization improves the effectiveness of out-of-domain testing on distinct datasets but the same task. The results indicate that performance gain using domain-specific pretraining depends on both the task and the size of the training dataset. In instances with limited dataset sizes, a significant improvement in gland segmentation performance was also observed, whereas models trained on cell segmentation datasets exhibit no improvement.
Authors: Nicolás Gaggion, Candelaria Mosquera, Lucas Mansilla, Martina Aineseder, Diego H. Milone, Enzo Ferrante
The development of successful artificial intelligence models for chest X-ray analysis relies on large, diverse datasets with high-quality annotations. While several databases of chest X-ray images have been released, most include disease diagnosis labels but lack detailed pixel-level anatomical segmentation labels. To address this gap, we introduce an extensive chest X-ray multi-center segmentation dataset with uniform and fine-grain anatomical annotations for images coming from six well-known publicly available databases: CANDID-PTX, ChestX-ray8, Chexpert, MIMIC-CXR-JPG, Padchest, and VinDr-CXR, resulting in 676,803 segmentation masks. Our methodology utilizes the HybridGNet model to ensure consistent and high-quality segmentations across all datasets. Rigorous validation, including expert physician evaluation and automatic quality control, was conducted to validate the resulting masks. Additionally, we provide individualized quality indices per mask and an overall quality estimation per dataset. This dataset serves as a valuable resource for the broader scientific community, streamlining the development and assessment of innovative methodologies in chest X-ray analysis. The CheXmask dataset is publicly available at: \url{https://physionet.org/content/chexmask-cxr-segmentation-data/}.
Authors: Na Zhang
MOBIO is a bi-modal database that was captured almost exclusively on mobile phones. It aims to improve research into deploying biometric techniques to mobile devices. Research has been shown that face and speaker recognition can be performed in a mobile environment. Facial landmark localization aims at finding the coordinates of a set of pre-defined key points for 2D face images. A facial landmark usually has specific semantic meaning, e.g. nose tip or eye centre, which provides rich geometric information for other face analysis tasks such as face recognition, emotion estimation and 3D face reconstruction. Pretty much facial landmark detection methods adopt still face databases, such as 300W, AFW, AFLW, or COFW, for evaluation, but seldomly use mobile data. Our work is first to perform facial landmark detection evaluation on the mobile still data, i.e., face images from MOBIO database. About 20,600 face images have been extracted from this audio-visual database and manually labeled with 22 landmarks as the groundtruth. Several state-of-the-art facial landmark detection methods are adopted to evaluate their performance on these data. The result shows that the data from MOBIO database is pretty challenging. This database can be a new challenging one for facial landmark detection evaluation.
Authors: Hengcan Shi, Munawar Hayat, Jianfei Cai
In recent years, open-vocabulary (OV) object detection has attracted increasing research attention. Unlike traditional detection, which only recognizes fixed-category objects, OV detection aims to detect objects in an open category set. Previous works often leverage vision-language (VL) training data (e.g., referring grounding data) to recognize OV objects. However, they only use pairs of nouns and individual objects in VL data, while these data usually contain much more information, such as scene graphs, which are also crucial for OV detection. In this paper, we propose a novel Scene-Graph-Based Discovery Network (SGDN) that exploits scene graph cues for OV detection. Firstly, a scene-graph-based decoder (SGDecoder) including sparse scene-graph-guided attention (SSGA) is presented. It captures scene graphs and leverages them to discover OV objects. Secondly, we propose scene-graph-based prediction (SGPred), where we build a scene-graph-based offset regression (SGOR) mechanism to enable mutual enhancement between scene graph extraction and object localization. Thirdly, we design a cross-modal learning mechanism in SGPred. It takes scene graphs as bridges to improve the consistency between cross-modal embeddings for OV object classification. Experiments on COCO and LVIS demonstrate the effectiveness of our approach. Moreover, we show the ability of our model for OV scene graph detection, while previous OV scene graph generation methods cannot tackle this task.
Authors: Zhonghan Zhao, Wenhao Chai, Shengyu Hao, Wenhao Hu, Guanhong Wang, Shidong Cao, Mingli Song, Jenq-Neng Hwang, Gaoang Wang
Deep learning has the potential to revolutionize sports performance, with applications ranging from perception and comprehension to decision. This paper presents a comprehensive survey of deep learning in sports performance, focusing on three main aspects: algorithms, datasets and virtual environments, and challenges. Firstly, we discuss the hierarchical structure of deep learning algorithms in sports performance which includes perception, comprehension and decision while comparing their strengths and weaknesses. Secondly, we list widely used existing datasets in sports and highlight their characteristics and limitations. Finally, we summarize current challenges and point out future trends of deep learning in sports. Our survey provides valuable reference material for researchers interested in deep learning in sports applications.
Authors: Chunhui Zhang, Xin Sun, Li Liu, Yiqian Yang, Qiong Liu, Xi Zhou, Yanfeng Wang
Current mainstream vision-language (VL) tracking framework consists of three parts, \ie a visual feature extractor, a language feature extractor, and a fusion model. To pursue better performance, a natural modus operandi for VL tracking is employing customized and heavier unimodal encoders, and multi-modal fusion models. Albeit effective, existing VL trackers separate feature extraction and feature integration, resulting in extracted features that lack semantic guidance and have limited target-aware capability in complex scenarios, \eg similar distractors and extreme illumination. In this work, inspired by the recent success of exploring foundation models with unified architecture for both natural language and computer vision tasks, we propose an All-in-One framework, which learns joint feature extraction and interaction by adopting a unified transformer backbone. Specifically, we mix raw vision and language signals to generate language-injected vision tokens, which we then concatenate before feeding into the unified backbone architecture. This approach achieves feature integration in a unified backbone, removing the need for carefully-designed fusion modules and resulting in a more effective and efficient VL tracking framework. To further improve the learning efficiency, we introduce a multi-modal alignment module based on cross-modal and intra-modal contrastive objectives, providing more reasonable representations for the unified All-in-One transformer backbone. Extensive experiments on five benchmarks, \ie OTB99-L, TNL2K, LaSOT, LaSOT$_{\rm Ext}$ and WebUAV-3M, demonstrate the superiority of the proposed tracker against existing state-of-the-arts on VL tracking. Codes will be made publicly available.
Authors: Yunqiu Lv, Jing Zhang, Nick Barnes, Yuchao Dai
Unsupervised object discovery (UOD) refers to the task of discriminating the whole region of objects from the background within a scene without relying on labeled datasets, which benefits the task of bounding-box-level localization and pixel-level segmentation. This task is promising due to its ability to discover objects in a generic manner. We roughly categorise existing techniques into two main directions, namely the generative solutions based on image resynthesis, and the clustering methods based on self-supervised models. We have observed that the former heavily relies on the quality of image reconstruction, while the latter shows limitations in effectively modeling semantic correlations. To directly target at object discovery, we focus on the latter approach and propose a novel solution by incorporating weakly-supervised contrastive learning (WCL) to enhance semantic information exploration. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images, which is achieved by fine-tuning the feature encoder of a self-supervised model, namely DINO, via WCL. Subsequently, we introduce Principal Component Analysis (PCA) to localize object regions. The principal projection direction, corresponding to the maximal eigenvalue, serves as an indicator of the object region(s). Extensive experiments on benchmark unsupervised object discovery datasets demonstrate the effectiveness of our proposed solution. The source code and experimental results are publicly available via our project page at https://github.com/npucvr/WSCUOD.git.
Authors: Nhi Kieu, Kien Nguyen, Sridha Sridharan, Clinton Fookes
The advent of high-resolution multispectral/hyperspectral sensors, LiDAR DSM (Digital Surface Model) information and many others has provided us with an unprecedented wealth of data for Earth Observation. Multimodal AI seeks to exploit those complementary data sources, particularly for complex tasks like semantic segmentation. While specialized architectures have been developed, they are highly complicated via significant effort in model design, and require considerable re-engineering whenever a new modality emerges. Recent trends in general-purpose multimodal networks have shown great potential to achieve state-of-the-art performance across multiple multimodal tasks with one unified architecture. In this work, we investigate the performance of PerceiverIO, one in the general-purpose multimodal family, in the remote sensing semantic segmentation domain. Our experiments reveal that this ostensibly universal network struggles with object scale variation in remote sensing images and fails to detect the presence of cars from a top-down view. To address these issues, even with extreme class imbalance issues, we propose a spatial and volumetric learning component. Specifically, we design a UNet-inspired module that employs 3D convolution to encode vital local information and learn cross-modal features simultaneously, while reducing network computational burden via the cross-attention mechanism of PerceiverIO. The effectiveness of the proposed component is validated through extensive experiments comparing it with other methods such as 2D convolution, and dual local module (\ie the combination of Conv2D 1x1 and Conv2D 3x3 inspired by UNetFormer). The proposed method achieves competitive results with specialized architectures like UNetFormer and SwinUNet, showing its potential to minimize network architecture engineering with a minimal compromise on the performance.
Authors: Wenmiao Hu, Yichen Zhang, Yuxuan Liang, Yifang Yin, Andrei Georgescu, An Tran, Hannes Kruppa, See-Kiong Ng, Roger Zimmermann
Street-view imagery provides us with novel experiences to explore different places remotely. Carefully calibrated street-view images (e.g. Google Street View) can be used for different downstream tasks, e.g. navigation, map features extraction. As personal high-quality cameras have become much more affordable and portable, an enormous amount of crowdsourced street-view images are uploaded to the internet, but commonly with missing or noisy sensor information. To prepare this hidden treasure for "ready-to-use" status, determining missing location information and camera orientation angles are two equally important tasks. Recent methods have achieved high performance on geo-localization of street-view images by cross-view matching with a pool of geo-referenced satellite imagery. However, most of the existing works focus more on geo-localization than estimating the image orientation. In this work, we re-state the importance of finding fine-grained orientation for street-view images, formally define the problem and provide a set of evaluation metrics to assess the quality of the orientation estimation. We propose two methods to improve the granularity of the orientation estimation, achieving 82.4% and 72.3% accuracy for images with estimated angle errors below 2 degrees for CVUSA and CVACT datasets, corresponding to 34.9% and 28.2% absolute improvement compared to previous works. Integrating fine-grained orientation estimation in training also improves the performance on geo-localization, giving top 1 recall 95.5%/85.5% and 86.8%/80.4% for orientation known/unknown tests on the two datasets.
Authors: Andreas L. Teigen, Yeonsoo Park, Annette Stahl, Rudolf Mester
Building on the success of Neural Radiance Fields (NeRFs), recent years have seen significant advances in the domain of novel view synthesis. These models capture the scene's volumetric radiance field, creating highly convincing dense photorealistic models through the use of simple, differentiable rendering equations. Despite their popularity, these algorithms suffer from severe ambiguities in visual data inherent to the RGB sensor, which means that although images generated with view synthesis can visually appear very believable, the underlying 3D model will often be wrong. This considerably limits the usefulness of these models in practical applications like Robotics and Extended Reality (XR), where an accurate dense 3D reconstruction otherwise would be of significant value. In this technical report, we present the vital differences between view synthesis models and 3D reconstruction models. We also comment on why a depth sensor is essential for modeling accurate geometry in general outward-facing scenes using the current paradigm of novel view synthesis methods. Focusing on the structure-from-motion task, we practically demonstrate this need by extending the Plenoxel radiance field model: Presenting an analytical differential approach for dense mapping and tracking with radiance fields based on RGB-D data without a neural network. Our method achieves state-of-the-art results in both the mapping and tracking tasks while also being faster than competing neural network-based approaches.
Authors: Dahyun Kang, Piotr Koniusz, Minsu Cho, Naila Murray
We address the task of weakly-supervised few-shot image classification and segmentation, by leveraging a Vision Transformer (ViT) pretrained with self-supervision. Our proposed method takes token representations from the self-supervised ViT and leverages their correlations, via self-attention, to produce classification and segmentation predictions through separate task heads. Our model is able to effectively learn to perform classification and segmentation in the absence of pixel-level labels during training, using only image-level labels. To do this it uses attention maps, created from tokens generated by the self-supervised ViT backbone, as pixel-level pseudo-labels. We also explore a practical setup with ``mixed" supervision, where a small number of training images contains ground-truth pixel-level labels and the remaining images have only image-level labels. For this mixed setup, we propose to improve the pseudo-labels using a pseudo-label enhancer that was trained using the available ground-truth pixel-level labels. Experiments on Pascal-5i and COCO-20i demonstrate significant performance gains in a variety of supervision settings, and in particular when little-to-no pixel-level labels are available.
Authors: Shuaikai Shi, Lijun Zhang, Yoann Altmann, Jie Chen
Hyperspectral images (HSI) with abundant spectral information reflected materials property usually perform low spatial resolution due to the hardware limits. Meanwhile, multispectral images (MSI), e.g., RGB images, have a high spatial resolution but deficient spectral signatures. Hyperspectral and multispectral image fusion can be cost-effective and efficient for acquiring both high spatial resolution and high spectral resolution images. Many of the conventional HSI and MSI fusion algorithms rely on known spatial degradation parameters, i.e., point spread function, spectral degradation parameters, spectral response function, or both of them. Another class of deep learning-based models relies on the ground truth of high spatial resolution HSI and needs large amounts of paired training images when working in a supervised manner. Both of these models are limited in practical fusion scenarios. In this paper, we propose an unsupervised HSI and MSI fusion model based on the cycle consistency, called CycFusion. The CycFusion learns the domain transformation between low spatial resolution HSI (LrHSI) and high spatial resolution MSI (HrMSI), and the desired high spatial resolution HSI (HrHSI) are considered to be intermediate feature maps in the transformation networks. The CycFusion can be trained with the objective functions of marginal matching in single transform and cycle consistency in double transforms. Moreover, the estimated PSF and SRF are embedded in the model as the pre-training weights, which further enhances the practicality of our proposed model. Experiments conducted on several datasets show that our proposed model outperforms all compared unsupervised fusion methods. The codes of this paper will be available at this address: https: //github.com/shuaikaishi/CycFusion for reproducibility.
Authors: Tianqi Li, Guansong Pang, Xiao Bai, Jin Zheng, Lei Zhou, Xin Ning
Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with only their side semantic information presented during training. It cannot handle real-life, open-world scenarios where there are test samples of unknown classes for which neither samples (e.g., images) nor their side semantic information is known during training. Open-Set Recognition (OSR) is dedicated to addressing the unknown class issue, but existing OSR methods are not designed to model the semantic information of the unseen classes. To tackle this combined ZSL and OSR problem, we consider the case of "Zero-Shot Open-Set Recognition" (ZS-OSR), where a model is trained under the ZSL setting but it is required to accurately classify samples from the unseen classes while being able to reject samples from the unknown classes during inference. We perform large experiments on combining existing state-of-the-art ZSL and OSR models for the ZS-OSR task on four widely used datasets adapted from the ZSL task, and reveal that ZS-OSR is a non-trivial task as the simply combined solutions perform badly in distinguishing the unseen-class and unknown-class samples. We further introduce a novel approach specifically designed for ZS-OSR, in which our model learns to generate adversarial semantic embeddings of the unknown classes to train an unknowns-informed ZS-OSR classifier. Extensive empirical results show that our method 1) substantially outperforms the combined solutions in detecting the unknown classes while retaining the classification accuracy on the unseen classes and 2) achieves similar superiority under generalized ZS-OSR settings.
Authors: Mingyuan Meng, Lei Bi, Michael Fulham, Dagan Feng, Jinman Kim
Image registration is a fundamental requirement for medical image analysis. Deep registration methods based on deep learning have been widely recognized for their capabilities to perform fast end-to-end registration. Many deep registration methods achieved state-of-the-art performance by performing coarse-to-fine registration, where multiple registration steps were iterated with cascaded networks. Recently, Non-Iterative Coarse-to-finE (NICE) registration methods have been proposed to perform coarse-to-fine registration in a single network and showed advantages in both registration accuracy and runtime. However, existing NICE registration methods mainly focus on deformable registration, while affine registration, a common prerequisite, is still reliant on time-consuming traditional optimization-based methods or extra affine registration networks. In addition, existing NICE registration methods are limited by the intrinsic locality of convolution operations. Transformers may address this limitation for their capabilities to capture long-range dependency, but the benefits of using transformers for NICE registration have not been explored. In this study, we propose a Non-Iterative Coarse-to-finE Transformer network (NICE-Trans) for image registration. Our NICE-Trans is the first deep registration method that (i) performs joint affine and deformable coarse-to-fine registration within a single network, and (ii) embeds transformers into a NICE registration framework to model long-range relevance between images. Extensive experiments with seven public datasets show that our NICE-Trans outperforms state-of-the-art registration methods on both registration accuracy and runtime.
Authors: Shuaikai Shi, Lijun Zhang, Jie Chen
Hyperspectral images (HSI) have a large amount of spectral information reflecting the characteristics of matter, while their spatial resolution is low due to the limitations of imaging technology. Complementary to this are multispectral images (MSI), e.g., RGB images, with high spatial resolution but insufficient spectral bands. Hyperspectral and multispectral image fusion is a technique for acquiring ideal images that have both high spatial and high spectral resolution cost-effectively. Many existing HSI and MSI fusion algorithms rely on known imaging degradation models, which are often not available in practice. In this paper, we propose a deep fusion method based on the conditional denoising diffusion probabilistic model, called DDPM-Fus. Specifically, the DDPM-Fus contains the forward diffusion process which gradually adds Gaussian noise to the high spatial resolution HSI (HrHSI) and another reverse denoising process which learns to predict the desired HrHSI from its noisy version conditioning on the corresponding high spatial resolution MSI (HrMSI) and low spatial resolution HSI (LrHSI). Once the training is completes, the proposed DDPM-Fus implements the reverse process on the test HrMSI and LrHSI to generate the fused HrHSI. Experiments conducted on one indoor and two remote sensing datasets show the superiority of the proposed model when compared with other advanced deep learningbased fusion methods. The codes of this work will be opensourced at this address: https://github.com/shuaikaishi/DDPMFus for reproducibility.
Authors: Yinghan Guan, Haoran Dai, Zekuan Yu, Shouyu Wang, Yuanjie Gu
Multimodal fusion detection always places high demands on the imaging system and image pre-processing, while either a high-quality pre-registration system or image registration processing is costly. Unfortunately, the existing fusion methods are designed for registered source images, and the fusion of inhomogeneous features, which denotes a pair of features at the same spatial location that expresses different semantic information, cannot achieve satisfactory performance via these methods. As a result, we propose IA-VFDnet, a CNN-Transformer hybrid learning framework with a unified high-quality multimodal feature matching module (AKM) and a fusion module (WDAF), in which AKM and DWDAF work in synergy to perform high-quality infrared-aware visible fusion detection, which can be applied to smoke and wildfire detection. Furthermore, experiments on the M3FD dataset validate the superiority of the proposed method, with IA-VFDnet achieving the best detection performance than other state-of-the-art methods under conventional registered conditions. In addition, the first unregistered multimodal smoke and wildfire detection benchmark is openly available in this letter.
Authors: Mingyuan Meng, Lei Bi, Michael Fulham, Dagan Feng, Jinman Kim
Survival prediction is crucial for cancer patients as it provides early prognostic information for treatment planning. Recently, deep survival models based on deep learning and medical images have shown promising performance for survival prediction. However, existing deep survival models are not well developed in utilizing multi-modality images (e.g., PET-CT) and in extracting region-specific information (e.g., the prognostic information in Primary Tumor (PT) and Metastatic Lymph Node (MLN) regions). In view of this, we propose a merging-diverging learning framework for survival prediction from multi-modality images. This framework has a merging encoder to fuse multi-modality information and a diverging decoder to extract region-specific information. In the merging encoder, we propose a Hybrid Parallel Cross-Attention (HPCA) block to effectively fuse multi-modality features via parallel convolutional layers and cross-attention transformers. In the diverging decoder, we propose a Region-specific Attention Gate (RAG) block to screen out the features related to lesion regions. Our framework is demonstrated on survival prediction from PET-CT images in Head and Neck (H&N) cancer, by designing an X-shape merging-diverging hybrid transformer network (named XSurv). Our XSurv combines the complementary information in PET and CT images and extracts the region-specific prognostic information in PT and MLN regions. Extensive experiments on the public dataset of HEad and neCK TumOR segmentation and outcome prediction challenge (HECKTOR 2022) demonstrate that our XSurv outperforms state-of-the-art survival prediction methods.
Authors: Wangbo Yu, Yanbo Fan, Yong Zhang, Xuan Wang, Fei Yin, Yunpeng Bai, Yan-Pei Cao, Ying Shan, Yang Wu, Zhongqian Sun, Baoyuan Wu
3D facial avatar reconstruction has been a significant research topic in computer graphics and computer vision, where photo-realistic rendering and flexible controls over poses and expressions are necessary for many related applications. Recently, its performance has been greatly improved with the development of neural radiance fields (NeRF). However, most existing NeRF-based facial avatars focus on subject-specific reconstruction and reenactment, requiring multi-shot images containing different views of the specific subject for training, and the learned model cannot generalize to new identities, limiting its further applications. In this work, we propose a one-shot 3D facial avatar reconstruction framework that only requires a single source image to reconstruct a high-fidelity 3D facial avatar. For the challenges of lacking generalization ability and missing multi-view information, we leverage the generative prior of 3D GAN and develop an efficient encoder-decoder network to reconstruct the canonical neural volume of the source image, and further propose a compensation network to complement facial details. To enable fine-grained control over facial dynamics, we propose a deformation field to warp the canonical volume into driven expressions. Through extensive experimental comparisons, we achieve superior synthesis results compared to several state-of-the-art methods.
Authors: Zizheng Yan, Yushuang Wu, Yipeng Qin, Xiaoguang Han, Shuguang Cui, Guanbin Li
In this paper, we introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA), which i) requires only a pre-trained source model, ii) allows the source and target domain to have different label sets, i.e., they share a common label set and hold their own private label set, and iii) requires only a few labeled samples in each class of the target domain. To address USMA, we propose a collaborative consistency training framework that regularizes the prediction consistency between two models, i.e., a pre-trained source model and its variant pre-trained with target data only, and combines their complementary strengths to learn a more powerful model. The rationale of our framework stems from the observation that the source model performs better on common categories than the target-only model, while on target-private categories, the target-only model performs better. We also propose a two-perspective, i.e., sample-wise and class-wise, consistency regularization to improve the training. Experimental results demonstrate the effectiveness of our method on several benchmark datasets.
Authors: Konrad Heidler, Lichao Mou, Erik Loebel, Mirko Scheinert, Sébastien Lefèvre, Xiao Xiang Zhu
Choosing how to encode a real-world problem as a machine learning task is an important design decision in machine learning. The task of glacier calving front modeling has often been approached as a semantic segmentation task. Recent studies have shown that combining segmentation with edge detection can improve the accuracy of calving front detectors. Building on this observation, we completely rephrase the task as a contour tracing problem and propose a model for explicit contour detection that does not incorporate any dense predictions as intermediate steps. The proposed approach, called ``Charting Outlines by Recurrent Adaptation'' (COBRA), combines Convolutional Neural Networks (CNNs) for feature extraction and active contour models for the delineation. By training and evaluating on several large-scale datasets of Greenland's outlet glaciers, we show that this approach indeed outperforms the aforementioned methods based on segmentation and edge-detection. Finally, we demonstrate that explicit contour detection has benefits over pixel-wise methods when quantifying the models' prediction uncertainties. The project page containing the code and animated model predictions can be found at \url{https://khdlr.github.io/COBRA/}.
Authors: Zelun Zhang, Xue Pan
The AllInOne training paradigm squeezes a wide range of tasks into a unified model in a multi-task learning manner. However, optimization in multi-task learning is more challenge than single-task learning, as the gradient norm from different tasks may vary greatly, making the backbone overly biased towards one specific task. To address this issue, we propose the task-level backbone-oriented gradient clip paradigm, compared with the vanilla gradient clip method, it has two points of emphasis:1) gradient clip is performed independently for each task. 2) backbone gradients generated from each task are rescaled to the same norm scale. Based on the experimental results, we argue that the task-level backbone-oriented gradient clip paradigm can relieve the gradient bias problem to some extent. We also propose a novel multi-branch data augmentation strategy where conflict augmentations are placed in different branches. Our approach has been shown to be effective and finally achieve 1st place in the Leaderboard A and 2nd place in the Leaderboard B of the CVPR2023 Foundation Model Challenge. It's worth noting that instead of evaluating all three tasks(detection, segmentation and fine-grained classification) in Leaderboard A, the segmentation task is not evaluated in Leaderboard B, in which our team has a huge advantage.
Authors: Jan Brederecke
Freezing of Gait (FOG) is a common motor symptom in patients with Parkinson's disease (PD). During episodes of FOG, patients suddenly lose their ability to stride as intended. Patient-worn accelerometers can capture information on the patient's movement during these episodes and machine learning algorithms can potentially classify this data. The combination therefore holds the potential to detect FOG in real-time. In this work I present a simple 1-D convolutional neural network that was trained to detect FOG events in accelerometer data. Model performance was assessed by measuring the success of the model to discriminate normal movement from FOG episodes and resulted in a mean average precision of 0.356 on the private leaderboard on Kaggle. Ultimately, the model ranked 8th out of 1379 teams in the Parkinson's Freezing of Gait Prediction competition. The results underscore the potential of Deep Learning-based solutions in advancing the field of FOG detection, contributing to improved interventions and management strategies for PD patients.
Authors: Yi Wen, Siwei Wang, Qing Liao, Weixuan Liang, Ke Liang, Xinhang Wan, Xinwang Liu
Multi-view clustering (MVC), which effectively fuses information from multiple views for better performance, has received increasing attention. Most existing MVC methods assume that multi-view data are fully paired, which means that the mappings of all corresponding samples between views are pre-defined or given in advance. However, the data correspondence is often incomplete in real-world applications due to data corruption or sensor differences, referred as the data-unpaired problem (DUP) in multi-view literature. Although several attempts have been made to address the DUP issue, they suffer from the following drawbacks: 1) Most methods focus on the feature representation while ignoring the structural information of multi-view data, which is essential for clustering tasks; 2) Existing methods for partially unpaired problems rely on pre-given cross-view alignment information, resulting in their inability to handle fully unpaired problems; 3) Their inevitable parameters degrade the efficiency and applicability of the models. To tackle these issues, we propose a novel parameter-free graph clustering framework termed Unpaired Multi-view Graph Clustering framework with Cross-View Structure Matching (UPMGC-SM). Specifically, unlike the existing methods, UPMGC-SM effectively utilizes the structural information from each view to refine cross-view correspondences. Besides, our UPMGC-SM is a unified framework for both the fully and partially unpaired multi-view graph clustering. Moreover, existing graph clustering methods can adopt our UPMGC-SM to enhance their ability for unpaired scenarios. Extensive experiments demonstrate the effectiveness and generalization of our proposed framework for both paired and unpaired datasets.
Authors: Jia-Qi Zhang, Hao-Bin Duan, Jun-Long Chen, Ariel Shamir, Miao Wang
The task of lane detection has garnered considerable attention in the field of autonomous driving due to its complexity. Lanes can present difficulties for detection, as they can be narrow, fragmented, and often obscured by heavy traffic. However, it has been observed that the lanes have a geometrical structure that resembles a straight line, leading to improved lane detection results when utilizing this characteristic. To address this challenge, we propose a hierarchical Deep Hough Transform (DHT) approach that combines all lane features in an image into the Hough parameter space. Additionally, we refine the point selection method and incorporate a Dynamic Convolution Module to effectively differentiate between lanes in the original image. Our network architecture comprises a backbone network, either a ResNet or Pyramid Vision Transformer, a Feature Pyramid Network as the neck to extract multi-scale features, and a hierarchical DHT-based feature aggregation head to accurately segment each lane. By utilizing the lane features in the Hough parameter space, the network learns dynamic convolution kernel parameters corresponding to each lane, allowing the Dynamic Convolution Module to effectively differentiate between lane features. Subsequently, the lane features are fed into the feature decoder, which predicts the final position of the lane. Our proposed network structure demonstrates improved performance in detecting heavily occluded or worn lane images, as evidenced by our extensive experimental results, which show that our method outperforms or is on par with state-of-the-art techniques.
Authors: Ben Chen, Caihua Xiong, Quanlin Li, Zhonghua Wan
Accurate detection and localization of X-corner on both planar and non-planar patterns is a core step in robotics and machine vision. However, previous works could not make a good balance between accuracy and robustness, which are both crucial criteria to evaluate the detectors performance. To address this problem, in this paper we present a novel detection algorithm which can maintain high sub-pixel precision on inputs under multiple interference, such as lens distortion, extreme poses and noise. The whole algorithm, adopting a coarse-to-fine strategy, contains a X-corner detection network and three post-processing techniques to distinguish the correct corner candidates, as well as a mixed sub-pixel refinement technique and an improved region growth strategy to recover the checkerboard pattern partially visible or occluded automatically. Evaluations on real and synthetic images indicate that the presented algorithm has the higher detection rate, sub-pixel accuracy and robustness than other commonly used methods. Finally, experiments of camera calibration and pose estimation verify it can also get smaller re-projection error in quantitative comparisons to the state-of-the-art.
Authors: Paolo Soleni, Wouter B. Verschoof-van der Vaart, Žiga Kokalj, Arianna Traviglia, Marco Fiorucci
When applying deep learning to remote sensing data in archaeological research, a notable obstacle is the limited availability of suitable datasets for training models. The application of transfer learning is frequently employed to mitigate this drawback. However, there is still a need to explore its effectiveness when applied across different archaeological datasets. This paper compares the performance of various transfer learning configurations using two semantic segmentation deep neural networks on two LiDAR datasets. The experimental results indicate that transfer learning-based approaches in archaeology can lead to performance improvements, although a systematic enhancement has not yet been observed. We provide specific insights about the validity of such techniques that can serve as a baseline for future works.
Authors: Xiaoyu Bai, Fan Bai, Xiaofei Huo, Jia Ge, Tony C. W. Mok, Zi Li, Minfeng Xu, Jingren Zhou, Le Lu, Dakai Jin, Xianghua Ye, Jingjing Lu, Ke Yan
Radiotherapists require accurate registration of MR/CT images to effectively use information from both modalities. In a typical registration pipeline, rigid or affine transformations are applied to roughly align the fixed and moving images before proceeding with the deformation step. While recent learning-based methods have shown promising results in the rigid/affine step, these methods often require images with similar field-of-view (FOV) for successful alignment. As a result, aligning images with different FOVs remains a challenging task. Self-supervised landmark detection methods like self-supervised Anatomical eMbedding (SAM) have emerged as a useful tool for mapping and cropping images to similar FOVs. However, these methods are currently limited to intra-modality use only. To address this limitation and enable cross-modality matching, we propose a new approach called Cross-SAM. Our approach utilizes a novel iterative process that alternates between embedding learning and CT-MRI registration. We start by applying aggressive contrast augmentation on both CT and MRI images to train a SAM model. We then use this SAM to identify corresponding regions on paired images using robust grid-points matching, followed by a point-set based affine/rigid registration, and a deformable fine-tuning step to produce registered paired images. We use these registered pairs to enhance the matching ability of SAM, which is then processed iteratively. We use the final model for cross-modality matching tasks. We evaluated our approach on two CT-MRI affine registration datasets and found that Cross-SAM achieved robust affine registration on both datasets, significantly outperforming other methods and achieving state-of-the-art performance.
Authors: Chenping Fu, Wanqi Yuan, Jiewen Xiao, Risheng Liu, Xin Fan
Underwater degraded images greatly challenge existing algorithms to detect objects of interest. Recently, researchers attempt to adopt attention mechanisms or composite connections for improving the feature representation of detectors. However, this solution does \textit{not} eliminate the impact of degradation on image content such as color and texture, achieving minimal improvements. Another feasible solution for underwater object detection is to develop sophisticated deep architectures in order to enhance image quality or features. Nevertheless, the visually appealing output of these enhancement modules do \textit{not} necessarily generate high accuracy for deep detectors. More recently, some multi-task learning methods jointly learn underwater detection and image enhancement, accessing promising improvements. Typically, these methods invoke huge architecture and expensive computations, rendering inefficient inference. Definitely, underwater object detection and image enhancement are two interrelated tasks. Leveraging information coming from the two tasks can benefit each task. Based on these factual opinions, we propose a bilevel optimization formulation for jointly learning underwater object detection and image enhancement, and then unroll to a dual perception network (DPNet) for the two tasks. DPNet with one shared module and two task subnets learns from the two different tasks, seeking a shared representation. The shared representation provides more structural details for image enhancement and rich content information for object detection. Finally, we derive a cooperative training strategy to optimize parameters for DPNet. Extensive experiments on real-world and synthetic underwater datasets demonstrate that our method outputs visually favoring images and higher detection accuracy.
Authors: Xiao Liu, Guangyi Chen, Yansong Tang, Guangrun Wang, Ser-Nam Lim
Composing simple elements into complex concepts is crucial yet challenging, especially for 3D action generation. Existing methods largely rely on extensive neural language annotations to discern composable latent semantics, a process that is often costly and labor-intensive. In this study, we introduce a novel framework to generate compositional actions without reliance on language auxiliaries. Our approach consists of three main components: Action Coupling, Conditional Action Generation, and Decoupling Refinement. Action Coupling utilizes an energy model to extract the attention masks of each sub-action, subsequently integrating two actions using these attentions to generate pseudo-training examples. Then, we employ a conditional generative model, CVAE, to learn a latent space, facilitating the diverse generation. Finally, we propose Decoupling Refinement, which leverages a self-supervised pre-trained model MAE to ensure semantic consistency between the sub-actions and compositional actions. This refinement process involves rendering generated 3D actions into 2D space, decoupling these images into two sub-segments, using the MAE model to restore the complete image from sub-segments, and constraining the recovered images to match images rendered from raw sub-actions. Due to the lack of existing datasets containing both sub-actions and compositional actions, we created two new datasets, named HumanAct-C and UESTC-C, and present a corresponding evaluation metric. Both qualitative and quantitative assessments are conducted to show our efficacy.
Authors: Emmanuel Hartman, Emery Pierson
We present a novel geometric deep learning layer that leverages the varifold gradient (VariGrad) to compute feature vector representations of 3D geometric data. These feature vectors can be used in a variety of downstream learning tasks such as classification, registration, and shape reconstruction. Our model's use of parameterization independent varifold representations of geometric data allows our model to be both trained and tested on data independent of the given sampling or parameterization. We demonstrate the efficiency, generalizability, and robustness to resampling demonstrated by the proposed VariGrad layer.
Authors: Xingyu Lin, John So, Sashwat Mahalingam, Fangchen Liu, Pieter Abbeel
The existing internet-scale image and video datasets cover a wide range of everyday objects and tasks, bringing the potential of learning policies that have broad generalization. Prior works have explored visual pre-training with different self-supervised objectives, but the generalization capabilities of the learned policies remain relatively unknown. In this work, we take the first step towards this challenge, focusing on how pre-trained representations can help the generalization of the learned policies. We first identify the key bottleneck in using a frozen pre-trained visual backbone for policy learning. We then propose SpawnNet, a novel two-stream architecture that learns to fuse pre-trained multi-layer representations into a separate network to learn a robust policy. Through extensive simulated and real experiments, we demonstrate significantly better categorical generalization compared to prior approaches in imitation learning settings.
Authors: Maryamalsadat Mahootiha, Hemin Ali Qadir, Jacob Bergsland, Ilangko Balasingham
Renal cell carcinoma represents a significant global health challenge with a low survival rate. This research aimed to devise a comprehensive deep-learning model capable of predicting survival probabilities in patients with renal cell carcinoma by integrating CT imaging and clinical data and addressing the limitations observed in prior studies. The aim is to facilitate the identification of patients requiring urgent treatment. The proposed framework comprises three modules: a 3D image feature extractor, clinical variable selection, and survival prediction. The feature extractor module, based on the 3D CNN architecture, predicts the ISUP grade of renal cell carcinoma tumors linked to mortality rates from CT images. A selection of clinical variables is systematically chosen using the Spearman score and random forest importance score as criteria. A deep learning-based network, trained with discrete LogisticHazard-based loss, performs the survival prediction. Nine distinct experiments are performed, with varying numbers of clinical variables determined by different thresholds of the Spearman and importance scores. Our findings demonstrate that the proposed strategy surpasses the current literature on renal cancer prognosis based on CT scans and clinical factors. The best-performing experiment yielded a concordance index of 0.84 and an area under the curve value of 0.8 on the test cohort, which suggests strong predictive power. The multimodal deep-learning approach developed in this study shows promising results in estimating survival probabilities for renal cell carcinoma patients using CT imaging and clinical data. This may have potential implications in identifying patients who require urgent treatment, potentially improving patient outcomes. The code created for this project is available for the public on: \href{https://github.com/Balasingham-AI-Group/Survival_CTplusClinical}{GitHub}
Authors: Valentin Comte, Mireia Alenya, Andrea Urru, Judith Recober, Ayako Nakaki, Francesca Crovetto, Oscar Camara, Eduard Gratacós, Elisenda Eixarch, Fàtima Crispi, Gemma Piella, Mario Ceresa, Miguel A. González Ballester
Accurate segmentation of fetal brain magnetic resonance images is crucial for analyzing fetal brain development and detecting potential neurodevelopmental abnormalities. Traditional deep learning-based automatic segmentation, although effective, requires extensive training data with ground-truth labels, typically produced by clinicians through a time-consuming annotation process. To overcome this challenge, we propose a novel unsupervised segmentation method based on multi-atlas segmentation, that accurately segments multiple tissues without relying on labeled data for training. Our method employs a cascaded deep learning network for 3D image registration, which computes small, incremental deformations to the moving image to align it precisely with the fixed image. This cascaded network can then be used to register multiple annotated images with the image to be segmented, and combine the propagated labels to form a refined segmentation. Our experiments demonstrate that the proposed cascaded architecture outperforms the state-of-the-art registration methods that were tested. Furthermore, the derived segmentation method achieves similar performance and inference time to nnU-Net while only using a small subset of annotated data for the multi-atlas segmentation task and none for training the network. Our pipeline for registration and multi-atlas segmentation is publicly available at https://github.com/ValBcn/CasReg.
Authors: Paula Feldman, Miguel Fainstein, Viviana Siless, Claudio Delrieux, Emmanuel Iarussi
We present a data-driven generative framework for synthesizing blood vessel 3D geometry. This is a challenging task due to the complexity of vascular systems, which are highly variating in shape, size, and structure. Existing model-based methods provide some degree of control and variation in the structures produced, but fail to capture the diversity of actual anatomical data. We developed VesselVAE, a recursive variational Neural Network that fully exploits the hierarchical organization of the vessel and learns a low-dimensional manifold encoding branch connectivity along with geometry features describing the target surface. After training, the VesselVAE latent space can be sampled to generate new vessel geometries. To the best of our knowledge, this work is the first to utilize this technique for synthesizing blood vessels. We achieve similarities of synthetic and real data for radius (.97), length (.95), and tortuosity (.96). By leveraging the power of deep neural networks, we generate 3D models of blood vessels that are both accurate and diverse, which is crucial for medical and surgical training, hemodynamic simulations, and many other purposes.
Authors: Shilong Zhang, Peize Sun, Shoufa Chen, Min Xiao, Wenqi Shao, Wenwei Zhang, Kai Chen, Ping Luo
Instruction tuning large language model (LLM) on image-text pairs has achieved unprecedented vision-language multimodal abilities. However, their vision-language alignments are only built on image-level, the lack of region-level alignment limits their advancements to fine-grained multimodal understanding. In this paper, we propose instruction tuning on region-of-interest. The key design is to reformulate the bounding box as the format of spatial instruction. The interleaved sequences of visual features extracted by the spatial instruction and the language embedding are input to LLM, and trained on the transformed region-text data in instruction tuning format. Our region-level vision-language model, termed as GPT4RoI, brings brand new conversational and interactive experience beyond image-level understanding. (1) Controllability: Users can interact with our model by both language and spatial instructions to flexibly adjust the detail level of the question. (2) Capacities: Our model supports not only single-region spatial instruction but also multi-region. This unlocks more region-level multimodal capacities such as detailed region caption and complex region reasoning. (3) Composition: Any off-the-shelf object detector can be a spatial instruction provider so as to mine informative object attributes from our model, like color, shape, material, action, relation to other objects, etc. The code, data, and demo can be found at https://github.com/jshilong/GPT4RoI.
Authors: Matvei Panteleev, Houari Bettahar
Stereo vision systems have become popular in computer vision applications, such as 3D reconstruction, object tracking, and autonomous navigation. However, traditional stereo vision systems that use rectilinear lenses may not be suitable for certain scenarios due to their limited field of view. This has led to the popularity of vision systems based on one or multiple fisheye cameras in different orientations, which can provide a field of view of 180x180 degrees or more. However, fisheye cameras introduce significant distortion at the edges that affects the accuracy of stereo matching and depth estimation. To overcome these limitations, this paper proposes a method for distortion-removal and depth estimation analysis for stereovision system using orthogonally divergent fisheye cameras (ODFC). The proposed method uses two virtual pinhole cameras (VPC), each VPC captures a small portion of the original view and presents it without any lens distortions, emulating the behavior of a pinhole camera. By carefully selecting the captured regions, it is possible to create a stereo pair using two VPCs. The performance of the proposed method is evaluated in both simulation using virtual environment and experiments using real cameras and their results compared to stereo cameras with parallel optical axes. The results demonstrate the effectiveness of the proposed method in terms of distortion removal and depth estimation accuracy.
Authors: Kaiwen Cai, Qiyue Xia, Peize Li, John Stankovic, Chris Xiaoxuan Lu
The majority of human detection methods rely on the sensor using visible lights (e.g., RGB cameras) but such sensors are limited in scenarios with degraded vision conditions. In this paper, we present a multimodal human detection system that combines portable thermal cameras and single-chip mmWave radars. To mitigate the noisy detection features caused by the low contrast of thermal cameras and the multi-path noise of radar point clouds, we propose a Bayesian feature extractor and a novel uncertainty-guided fusion method that surpasses a variety of competing methods, either single-modal or multi-modal. We evaluate the proposed method on real-world data collection and demonstrate that our approach outperforms the state-of-the-art methods by a large margin.
Authors: Baoru Huang, Yicheng Hu, Anh Nguyen, Stamatia Giannarou, Daniel S. Elson
In surgical oncology, it is challenging for surgeons to identify lymph nodes and completely resect cancer even with pre-operative imaging systems like PET and CT, because of the lack of reliable intraoperative visualization tools. Endoscopic radio-guided cancer detection and resection has recently been evaluated whereby a novel tethered laparoscopic gamma detector is used to localize a preoperatively injected radiotracer. This can both enhance the endoscopic imaging and complement preoperative nuclear imaging data. However, gamma activity visualization is challenging to present to the operator because the probe is non-imaging and it does not visibly indicate the activity origination on the tissue surface. Initial failed attempts used segmentation or geometric methods, but led to the discovery that it could be resolved by leveraging high-dimensional image features and probe position information. To demonstrate the effectiveness of this solution, we designed and implemented a simple regression network that successfully addressed the problem. To further validate the proposed solution, we acquired and publicly released two datasets captured using a custom-designed, portable stereo laparoscope system. Through intensive experimentation, we demonstrated that our method can successfully and effectively detect the sensing area, establishing a new performance benchmark. Code and data are available at https://github.com/br0202/Sensing_area_detection.git
Authors: Dianye Huang, Yuan Bi, Nassir Navab, Zhongliang Jiang
Ultrasound (US) imaging is widely used for diagnosing and monitoring arterial diseases, mainly due to the advantages of being non-invasive, radiation-free, and real-time. In order to provide additional information to assist clinicians in diagnosis, the tubular structures are often segmented from US images. To improve the artery segmentation accuracy and stability during scans, this work presents a novel pulsation-assisted segmentation neural network (PAS-NN) by explicitly taking advantage of the cardiac-induced motions. Motion magnification techniques are employed to amplify the subtle motion within the frequency band of interest to extract the pulsation signals from sequential US images. The extracted real-time pulsation information can help to locate the arteries on cross-section US images; therefore, we explicitly integrated the pulsation into the proposed PAS-NN as attention guidance. Notably, a robotic arm is necessary to provide stable movement during US imaging since magnifying the target motions from the US images captured along a scan path is not manually feasible due to the hand tremor. To validate the proposed robotic US system for imaging arteries, experiments are carried out on volunteers' carotid and radial arteries. The results demonstrated that the PAS-NN could achieve comparable results as state-of-the-art on carotid and can effectively improve the segmentation performance for small vessels (radial artery).
Authors: Owen Howell, David Klee, Ondrej Biza, Linfeng Zhao, Robin Walters
Learning about the three-dimensional world from two-dimensional images is a fundamental problem in computer vision. An ideal neural network architecture for such tasks would leverage the fact that objects can be rotated and translated in three dimensions to make predictions about novel images. However, imposing SO(3)-equivariance on two-dimensional inputs is difficult because the group of three-dimensional rotations does not have a natural action on the two-dimensional plane. Specifically, it is possible that an element of SO(3) will rotate an image out of plane. We show that an algorithm that learns a three-dimensional representation of the world from two dimensional images must satisfy certain geometric consistency properties which we formulate as SO(2)-equivariance constraints. We use the induced and restricted representations of SO(2) on SO(3) to construct and classify architectures which satisfy these geometric consistency constraints. We prove that any architecture which respects said consistency constraints can be realized as an instance of our construction. We show that three previously proposed neural architectures for 3D pose prediction are special cases of our construction. We propose a new algorithm that is a learnable generalization of previously considered methods. We test our architecture on three pose predictions task and achieve SOTA results on both the PASCAL3D+ and SYMSOL pose estimation tasks.
Authors: Lakshmi Nair, Mikhail Bernadskiy, Arulselvan Madhavan, Craig Chan, Ayon Basumallik, Darius Bunandar
The recent rise of large language models (LLMs) has resulted in increased efforts towards running LLMs at reduced precision. Running LLMs at lower precision supports resource constraints and furthers their democratization, enabling users to run billion-parameter LLMs on their personal devices. To supplement this ongoing effort, we propose INT-FP-QSim: an open-source simulator that enables flexible evaluation of LLMs and vision transformers at various numerical precisions and formats. INT-FP-QSim leverages existing open-source repositories such as TensorRT, QPytorch and AIMET for a combined simulator that supports various floating point and integer formats. With the help of our simulator, we survey the impact of different numerical formats on the performance of LLMs and vision transformers at 4-bit weights and 4-bit or 8-bit activations. We also compare recently proposed methods like Adaptive Block Floating Point, SmoothQuant, GPTQ and RPTQ on the model performances. We hope INT-FP-QSim will enable researchers to flexibly simulate models at various precisions to support further research in quantization of LLMs and vision transformers.
Authors: Vladan Stojnić, Zakaria Laskar, Giorgos Tolias
Deep active learning in the presence of outlier examples poses a realistic yet challenging scenario. Acquiring unlabeled data for annotation requires a delicate balance between avoiding outliers to conserve the annotation budget and prioritizing useful inlier examples for effective training. In this work, we present an approach that leverages three highly synergistic components, which are identified as key ingredients: joint classifier training with inliers and outliers, semi-supervised learning through pseudo-labeling, and model ensembling. Our work demonstrates that ensembling significantly enhances the accuracy of pseudo-labeling and improves the quality of data acquisition. By enabling semi-supervision through the joint training process, where outliers are properly handled, we observe a substantial boost in classifier accuracy through the use of all available unlabeled examples. Notably, we reveal that the integration of joint training renders explicit outlier detection unnecessary; a conventional component for acquisition in prior work. The three key components align seamlessly with numerous existing approaches. Through empirical evaluations, we showcase that their combined use leads to a performance increase. Remarkably, despite its simplicity, our proposed approach outperforms all other methods in terms of performance. Code: https://github.com/vladan-stojnic/active-outliers
Authors: ZiHao Wang, ZhenZhou Wang
Automatic and robust segmentation of the left ventricle (LV) in magnetic resonance images (MRI) has remained challenging for many decades. With the great success of deep learning in object detection and classification, the research focus of LV segmentation has changed to convolutional neural network (CNN) in recent years. However, LV segmentation is a pixel-level classification problem and its categories are intractable compared to object detection and classification. In this paper, we proposed a robust LV segmentation method based on slope difference distribution (SDD) double threshold selection and circular Hough transform (CHT). The proposed method achieved 96.51% DICE score on the test set of automated cardiac diagnosis challenge (ACDC) which is higher than the best accuracy reported in recently published literatures.
Authors: Xu Tian, Jin Liu, Hulin Kuang, Yu Sheng, Jianxin Wang, The Alzheimer's Disease Neuroimaging Initiative
Accurately detecting Alzheimer's disease (AD) and predicting mini-mental state examination (MMSE) score are important tasks in elderly health by magnetic resonance imaging (MRI). Most of the previous methods on these two tasks are based on single-task learning and rarely consider the correlation between them. Since the MMSE score, which is an important basis for AD diagnosis, can also reflect the progress of cognitive impairment, some studies have begun to apply multi-task learning methods to these two tasks. However, how to exploit feature correlation remains a challenging problem for these methods. To comprehensively address this challenge, we propose a MRI-based multi-task decoupled learning method for AD detection and MMSE score prediction. First, a multi-task learning network is proposed to implement AD detection and MMSE score prediction, which exploits feature correlation by adding three multi-task interaction layers between the backbones of the two tasks. Each multi-task interaction layer contains two feature decoupling modules and one feature interaction module. Furthermore, to enhance the generalization between tasks of the features selected by the feature decoupling module, we propose the feature consistency loss constrained feature decoupling module. Finally, in order to exploit the specific distribution information of MMSE score in different groups, a distribution loss is proposed to further enhance the model performance. We evaluate our proposed method on multi-site datasets. Experimental results show that our proposed multi-task decoupled representation learning method achieves good performance, outperforming single-task learning and other existing state-of-the-art methods.
Authors: Moritz Rempe, Florian Mentzel, Kelsey L. Pomykala, Johannes Haubold, Felix Nensa, Kevin Kröninger, Jan Egger, Jens Kleesiek
Objectives: Present a novel deep learning-based skull stripping algorithm for magnetic resonance imaging (MRI) that works directly in the information rich k-space.
Materials and Methods: Using two datasets from different institutions with a total of 36,900 MRI slices, we trained a deep learning-based model to work directly with the complex raw k-space data. Skull stripping performed by HD-BET (Brain Extraction Tool) in the image domain were used as the ground truth.
Results: Both datasets were very similar to the ground truth (DICE scores of 92\%-98\% and Hausdorff distances of under 5.5 mm). Results on slices above the eye-region reach DICE scores of up to 99\%, while the accuracy drops in regions around the eyes and below, with partially blurred output. The output of k-strip often smoothed edges at the demarcation to the skull. Binary masks are created with an appropriate threshold.
Conclusion: With this proof-of-concept study, we were able to show the feasibility of working in the k-space frequency domain, preserving phase information, with consistent results. Future research should be dedicated to discovering additional ways the k-space can be used for innovative image analysis and further workflows.
Authors: Dmitry Petrov, Matheus Gadelha, Radomir Mech, Evangelos Kalogerakis
We present ANISE, a method that reconstructs a 3D~shape from partial observations (images or sparse point clouds) using a part-aware neural implicit shape representation. The shape is formulated as an assembly of neural implicit functions, each representing a different part instance. In contrast to previous approaches, the prediction of this representation proceeds in a coarse-to-fine manner. Our model first reconstructs a structural arrangement of the shape in the form of geometric transformations of its part instances. Conditioned on them, the model predicts part latent codes encoding their surface geometry. Reconstructions can be obtained in two ways: (i) by directly decoding the part latent codes to part implicit functions, then combining them into the final shape; or (ii) by using part latents to retrieve similar part instances in a part database and assembling them in a single shape. We demonstrate that, when performing reconstruction by decoding part representations into implicit functions, our method achieves state-of-the-art part-aware reconstruction results from both images and sparse point clouds.When reconstructing shapes by assembling parts retrieved from a dataset, our approach significantly outperforms traditional shape retrieval methods even when significantly restricting the database size. We present our results in well-known sparse point cloud reconstruction and single-view reconstruction benchmarks.
Authors: Yinghui Xing, Qirui Wu, De Cheng, Shizhou Zhang, Guoqiang Liang, Peng Wang, Yanning Zhang
With the emergence of large pre-trained vison-language model like CLIP, transferable representations can be adapted to a wide range of downstream tasks via prompt tuning. Prompt tuning tries to probe the beneficial information for downstream tasks from the general knowledge stored in the pre-trained model. A recently proposed method named Context Optimization (CoOp) introduces a set of learnable vectors as text prompt from the language side. However, tuning the text prompt alone can only adjust the synthesized "classifier", while the computed visual features of the image encoder can not be affected , thus leading to sub-optimal solutions. In this paper, we propose a novel Dual-modality Prompt Tuning (DPT) paradigm through learning text and visual prompts simultaneously. To make the final image feature concentrate more on the target visual concept, a Class-Aware Visual Prompt Tuning (CAVPT) scheme is further proposed in our DPT, where the class-aware visual prompt is generated dynamically by performing the cross attention between text prompts features and image patch token embeddings to encode both the downstream task-related information and visual instance information. Extensive experimental results on 11 datasets demonstrate the effectiveness and generalization ability of the proposed method. Our code is available in https://github.com/fanrena/DPT.
Authors: Ahmed Sabir
This paper focuses on enhancing the captions generated by image-caption generation systems. We propose an approach for improving caption generation systems by choosing the most closely related output to the image rather than the most likely output produced by the model. Our model revises the language generation output beam search from a visual context perspective. We employ a visual semantic measure in a word and sentence level manner to match the proper caption to the related information in the image. The proposed approach can be applied to any caption system as a post-processing based method.
Authors: Xiaoyu Geng, Qiang Guo, Shuaixiong Hui, Ming Yang, Caiming Zhang
Tensor robust principal component analysis (TRPCA) is a classical way for low-rank tensor recovery, which minimizes the convex surrogate of tensor rank by shrinking each tensor singular value equally. However, for real-world visual data, large singular values represent more significant information than small singular values. In this paper, we propose a nonconvex TRPCA (N-TRPCA) model based on the tensor adjustable logarithmic norm. Unlike TRPCA, our N-TRPCA can adaptively shrink small singular values more and shrink large singular values less. In addition, TRPCA assumes that the whole data tensor is of low rank. This assumption is hardly satisfied in practice for natural visual data, restricting the capability of TRPCA to recover the edges and texture details from noisy images and videos. To this end, we integrate nonlocal self-similarity into N-TRPCA, and further develop a nonconvex and nonlocal TRPCA (NN-TRPCA) model. Specifically, similar nonlocal patches are grouped as a tensor and then each group tensor is recovered by our N-TRPCA. Since the patches in one group are highly correlated, all group tensors have strong low-rank property, leading to an improvement of recovery performance. Experimental results demonstrate that the proposed NN-TRPCA outperforms existing TRPCA methods in visual data recovery. The demo code is available at https://github.com/qguo2010/NN-TRPCA.
Authors: Cheng Guo, Fei Hu, Yan Hu
Passive millimeter-wave (PMMW) is a significant potential technique for human security screening. Several popular object detection networks have been used for PMMW images. However, restricted by the low resolution and high noise of PMMW images, PMMW hidden object detection based on deep learning usually suffers from low accuracy and low classification confidence. To tackle the above problems, this paper proposes a Task-Aligned Detection Transformer network, named PMMW-DETR. In the first stage, a Denoising Coarse-to-Fine Transformer (DCFT) backbone is designed to extract long- and short-range features in the different scales. In the second stage, we propose the Query Selection module to introduce learned spatial features into the network as prior knowledge, which enhances the semantic perception capability of the network. In the third stage, aiming to improve the classification performance, we perform a Task-Aligned Dual-Head block to decouple the classification and regression tasks. Based on our self-developed PMMW security screening dataset, experimental results including comparison with State-Of-The-Art (SOTA) methods and ablation study demonstrate that the PMMW-DETR obtains higher accuracy and classification confidence than previous works, and exhibits robustness to the PMMW images of low quality.
Authors: Shantanu Ghosh, Ke Yu, Forough Arabshahi, Kayhan Batmanghelich
We use concept-based interpretable models to mitigate shortcut learning. Existing methods lack interpretability. Beginning with a Blackbox, we iteratively carve out a mixture of interpretable experts (MoIE) and a residual network. Each expert explains a subset of data using First Order Logic (FOL). While explaining a sample, the FOL from biased BB-derived MoIE detects the shortcut effectively. Finetuning the BB with Metadata Normalization (MDN) eliminates the shortcut. The FOLs from the finetuned-BB-derived MoIE verify the elimination of the shortcut. Our experiments show that MoIE does not hurt the accuracy of the original BB and eliminates shortcuts effectively.
Authors: Arindam Das, Sudip Das, Ganesh Sistu, Jonathan Horgan, Ujjwal Bhattacharya, Edward Jones, Martin Glavin, Ciarán Eising
Multimodal learning, particularly for pedestrian detection, has recently received emphasis due to its capability to function equally well in several critical autonomous driving scenarios such as low-light, night-time, and adverse weather conditions. However, in most cases, the training distribution largely emphasizes the contribution of one specific input that makes the network biased towards one modality. Hence, the generalization of such models becomes a significant problem where the non-dominant input modality during training could be contributing more to the course of inference. Here, we introduce a novel training setup with regularizer in the multimodal architecture to resolve the problem of this disparity between the modalities. Specifically, our regularizer term helps to make the feature fusion method more robust by considering both the feature extractors equivalently important during the training to extract the multimodal distribution which is referred to as removing the imbalance problem. Furthermore, our decoupling concept of output stream helps the detection task by sharing the spatial sensitive information mutually. Extensive experiments of the proposed method on KAIST and UTokyo datasets shows improvement of the respective state-of-the-art performance.
Authors: Elena Merlo (1, 2), Marta Lagomarsino (1, 3), Edoardo Lamon (1, 4), Arash Ajoudani (1) ((1) Human-Robot Interfaces and Interaction Laboratory, Istituto Italiano di Tecnologia, Genoa, Italy, (2) Dept. of Informatics, Bioengineering, Robotics, and Systems Engineering, University of Genoa, Genoa, Italy, (3) Dept. of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy, (4) Dept. of Information Engineering and Computer Science, University of Trento, Trento, Italy)
This paper presents a new method to describe spatio-temporal relations between objects and hands, to recognize both interactions and activities within video demonstrations of manual tasks. The approach exploits Scene Graphs to extract key interaction features from image sequences while simultaneously encoding motion patterns and context. Additionally, the method introduces event-based automatic video segmentation and clustering, which allow for the grouping of similar events and detect if a monitored activity is executed correctly. The effectiveness of the approach was demonstrated in two multi-subject experiments, showing the ability to recognize and cluster hand-object and object-object interactions without prior knowledge of the activity, as well as matching the same activity performed by different subjects.
Authors: Tushar Kataria, Beatrice Knudsen, Shireen Elhabian
Semantic segmentation is a critical step in automated image interpretation and analysis where pixels are classified into one or more predefined semantically meaningful classes. Deep learning approaches for semantic segmentation rely on harnessing the power of annotated images to learn features indicative of these semantic classes. Nonetheless, they often fail to generalize when there is a significant domain (i.e., distributional) shift between the training (i.e., source) data and the dataset(s) encountered when deployed (i.e., target), necessitating manual annotations for the target data to achieve acceptable performance. This is especially important in medical imaging because different image modalities have significant intra- and inter-site variations due to protocol and vendor variability. Current techniques are sensitive to hyperparameter tuning and target dataset size. This paper presents an unsupervised domain adaptation approach for semantic segmentation that alleviates the need for annotating target data. Using kernel density estimation, we match the target data distribution to the source in the feature space, particularly when the number of target samples is limited (3% of the target dataset size). We demonstrate the efficacy of our proposed approach on 2 datasets, multisite prostate MRI and histopathology images.
Authors: Zihao Zhao, Sheng Wang, Jinchen Gu, Yitao Zhu, Lanzhuju Mei, Zixu Zhuang, Zhiming Cui, Qian Wang, Dinggang Shen
The integration of Computer-Assisted Diagnosis (CAD) with Large Language Models (LLMs) holds great potential in clinical applications, specifically in the roles of virtual family doctors and clinic assistants. However, current works in this field are plagued by limitations, specifically a restricted scope of applicable image domains and the provision of unreliable medical advice. This restricts their overall processing capabilities. Furthermore, the mismatch in writing style between LLMs and radiologists undermines their practical usefulness. To tackle these challenges, we introduce ChatCAD+, which is designed to be universal and reliable. It is capable of handling medical images from diverse domains and leveraging up-to-date information from reputable medical websites to provide reliable medical advice. Additionally, it incorporates a template retrieval system that improves report generation performance via exemplar reports. This approach ensures greater consistency with the expertise of human professionals. The source code is available at https://github.com/zhaozh10/ChatCAD.
Authors: Noam Elata, Bahjat Kawar, Tomer Michaeli, Michael Elad
Diffusion models are the current state-of-the-art in image generation, synthesizing high-quality images by breaking down the generation process into many fine-grained denoising steps. Despite their good performance, diffusion models are computationally expensive, requiring many neural function evaluations (NFEs). In this work, we propose an anytime diffusion-based method that can generate viable images when stopped at arbitrary times before completion. Using existing pretrained diffusion models, we show that the generation scheme can be recomposed as two nested diffusion processes, enabling fast iterative refinement of a generated image. In experiments on ImageNet and Stable Diffusion-based text-to-image generation, we show, both qualitatively and quantitatively, that our method's intermediate generation quality greatly exceeds that of the original diffusion model, while the final generation result remains comparable. We illustrate the applicability of Nested Diffusion in several settings, including for solving inverse problems, and for rapid text-based content creation by allowing user intervention throughout the sampling process.
Authors: Robert Geirhos, Roland S. Zimmermann, Blair Bilodeau, Wieland Brendel, Been Kim
How do neural networks extract patterns from pixels? Feature visualizations attempt to answer this important question by visualizing highly activating patterns through optimization. Today, visualization methods form the foundation of our knowledge about the internal workings of neural networks, as a type of mechanistic interpretability. Here we ask: How reliable are feature visualizations? We start our investigation by developing network circuits that trick feature visualizations into showing arbitrary patterns that are completely disconnected from normal network behavior on natural input. We then provide evidence for a similar phenomenon occurring in standard, unmanipulated networks: feature visualizations are processed very differently from standard input, casting doubt on their ability to "explain" how neural networks process natural images. We underpin this empirical finding by theory proving that the set of functions that can be reliably understood by feature visualization is extremely small and does not include general black-box neural networks. Therefore, a promising way forward could be the development of networks that enforce certain structures in order to ensure more reliable feature visualizations.
Authors: Renjun Xu, Kaifan Yang, Ke Liu, Fengxiang He
Vision Transformer (ViT) has achieved remarkable performance in computer vision. However, positional encoding in ViT makes it substantially difficult to learn the intrinsic equivariance in data. Initial attempts have been made on designing equivariant ViT but are proved defective in some cases in this paper. To address this issue, we design a Group Equivariant Vision Transformer (GE-ViT) via a novel, effective positional encoding operator. We prove that GE-ViT meets all the theoretical requirements of an equivariant neural network. Comprehensive experiments are conducted on standard benchmark datasets, demonstrating that GE-ViT significantly outperforms non-equivariant self-attention networks. The code is available at https://github.com/ZJUCDSYangKaifan/GEVit.
Authors: Weizhen He, Shixiang Tang, Yiheng Deng, Qihao Chen, Qingsong Xie, Yizhou Wang, Lei Bai, Feng Zhu, Rui Zhao, Wanli Ouyang, Donglian Qi, Yunfeng Yan
Human intelligence can retrieve any person according to both visual and language descriptions. However, the current computer vision community studies specific person re-identification (ReID) tasks in different scenarios separately, which limits the applications in the real world. This paper strives to resolve this problem by proposing a new instruct-ReID task that requires the model to retrieve images according to the given image or language instructions.Our instruct-ReID is a more general ReID setting, where existing ReID tasks can be viewed as special cases by designing different instructions. We propose a large-scale OmniReID benchmark and an adaptive triplet loss as a baseline method to facilitate research in this new setting. Experimental results show that the baseline model trained on our OmniReID benchmark can improve +0.6%, +1.4%, 0.2% mAP on Market1501, CUHK03, MSMT17 for traditional ReID, +0.8%, +2.0%, +13.4% mAP on PRCC, VC-Clothes, LTCC for clothes-changing ReID, +11.7% mAP on COCAS+ real2 for clothestemplate based clothes-changing ReID when using only RGB images, +25.4% mAP on COCAS+ real2 for our newly defined language-instructed ReID. The dataset, model, and code will be available at https://github.com/hwz-zju/Instruct-ReID.
Authors: Aditya Aditya, Bharat Lohani, Jagannath Aryal, Stephan Winter
Vegetation is crucial for sustainable and resilient cities providing various ecosystem services and well-being of humans. However, vegetation is under critical stress with rapid urbanization and expanding infrastructure footprints. Consequently, mapping of this vegetation is essential in the urban environment. Recently, deep learning for point cloud semantic segmentation has shown significant progress. Advanced models attempt to obtain state-of-the-art performance on benchmark datasets, comprising multiple classes and representing real world scenarios. However, class specific segmentation with respect to vegetation points has not been explored. Therefore, selection of a deep learning model for vegetation points segmentation is ambiguous. To address this problem, we provide a comprehensive assessment of point-based deep learning models for semantic segmentation of vegetation class. We have selected four representative point-based models, namely PointCNN, KPConv (omni-supervised), RandLANet and SCFNet. These models are investigated on three different datasets, specifically Chandigarh, Toronto3D and Kerala, which are characterized by diverse nature of vegetation, varying scene complexity and changing per-point features. PointCNN achieves the highest mIoU on the Chandigarh (93.32%) and Kerala datasets (85.68%) while KPConv (omni-supervised) provides the highest mIoU on the Toronto3D dataset (91.26%). The paper develops a deeper insight, hitherto not reported, into the working of these models for vegetation segmentation and outlines the ingredients that should be included in a model specifically for vegetation segmentation. This paper is a step towards the development of a novel architecture for vegetation points segmentation.
Authors: Bohan Li, Jingxin Dong, Yunnan Wang, Jinming Liu, Lianying Yin, Wei Zhao, Zheng Zhu, Xin Jin, Wenjun Zeng
Recent works have explored the fundamental role of depth estimation in multi-view stereo (MVS) and semantic scene completion (SSC). They generally construct 3D cost volumes to explore geometric correspondence in depth, and estimate such volumes in a single step relying directly on the ground truth approximation. However, such problem cannot be thoroughly handled in one step due to complex empirical distributions, especially in challenging regions like occlusions, reflections, etc. In this paper, we formulate the depth estimation task as a multi-step distribution approximation process, and introduce a new paradigm of modeling the Volumetric Probability Distribution progressively (step-by-step) following a Markov chain with Diffusion models (VPDD). Specifically, to constrain the multi-step generation of volume in VPDD, we construct a meta volume guidance and a confidence-aware contextual guidance as conditional geometry priors to facilitate the distribution approximation. For the sampling process, we further investigate an online filtering strategy to maintain consistency in volume representations for stable training. Experiments demonstrate that our plug-and-play VPDD outperforms the state-of-the-arts for tasks of MVS and SSC, and can also be easily extended to different baselines to get improvement. It is worth mentioning that we are the first camera-based work that surpasses LiDAR-based methods on the SemanticKITTI dataset.
Authors: Jie Ning, Jiebao Sun, Yao Li, Zhichang Guo, Wangmeng Zuo
Deep neural networks (DNNs) have shown superior performance comparing to traditional image denoising algorithms. However, DNNs are inevitably vulnerable while facing adversarial attacks. In this paper, we propose an adversarial attack method named denoising-PGD which can successfully attack all the current deep denoising models while keep the noise distribution almost unchanged. We surprisingly find that the current mainstream non-blind denoising models (DnCNN, FFDNet, ECNDNet, BRDNet), blind denoising models (DnCNN-B, Noise2Noise, RDDCNN-B, FAN), plug-and-play (DPIR, CurvPnP) and unfolding denoising models (DeamNet) almost share the same adversarial sample set on both grayscale and color images, respectively. Shared adversarial sample set indicates that all these models are similar in term of local behaviors at the neighborhood of all the test samples. Thus, we further propose an indicator to measure the local similarity of models, called robustness similitude. Non-blind denoising models are found to have high robustness similitude across each other, while hybrid-driven models are also found to have high robustness similitude with pure data-driven non-blind denoising models. According to our robustness assessment, data-driven non-blind denoising models are the most robust. We use adversarial training to complement the vulnerability to adversarial attacks. Moreover, the model-driven image denoising BM3D shows resistance on adversarial attacks.
Authors: Siqi Hui, Sanping Zhou, Ye deng, Jinjun Wang
Despite the success of two-stage few-shot classification methods, in the episodic meta-training stage, the model suffers severe overfitting. We hypothesize that it is caused by over-discrimination, i.e., the model learns to over-rely on the superficial features that fit for base class discrimination while suppressing the novel class generalization. To penalize over-discrimination, we introduce knowledge distillation techniques to keep novel generalization knowledge from the teacher model during training. Specifically, we select the teacher model as the one with the best validation accuracy during meta-training and restrict the symmetric Kullback-Leibler (SKL) divergence between the output distribution of the linear classifier of the teacher model and that of the student model. This simple approach outperforms the standard meta-training process. We further propose the Nearest Neighbor Symmetric Kullback-Leibler (NNSKL) divergence for meta-training to push the limits of knowledge distillation techniques. NNSKL takes few-shot tasks as input and penalizes the output of the nearest neighbor classifier, which possesses an impact on the relationships between query embedding and support centers. By combining SKL and NNSKL in meta-training, the model achieves even better performance and surpasses state-of-the-art results on several benchmarks.
Authors: Weiyi Xiong, Jianan Liu, Tao Huang, Qing-Long Han, Yuxuan Xia, Bing Zhu
As an emerging technology and a relatively affordable device, the 4D imaging radar has already been confirmed effective in performing 3D object detection in autonomous driving. Nevertheless, the sparsity and noisiness of 4D radar point clouds hinder further performance improvement, and in-depth studies about its fusion with other modalities are lacking. On the other hand, most of the camera-based perception methods transform the extracted image perspective view features into the bird's-eye view geometrically via "depth-based splatting" proposed in Lift-Splat-Shoot (LSS), and some researchers exploit other modals such as LiDARs or ordinary automotive radars for enhancement. Recently, a few works have applied the "sampling" strategy for image view transformation, showing that it outperforms "splatting" even without image depth prediction. However, the potential of "sampling" is not fully unleashed. In this paper, we investigate the "sampling" view transformation strategy on the camera and 4D imaging radar fusion-based 3D object detection. In the proposed model, LXL, predicted image depth distribution maps and radar 3D occupancy grids are utilized to aid image view transformation, called "radar occupancy-assisted depth-based sampling". Experiments on VoD and TJ4DRadSet datasets show that the proposed method outperforms existing 3D object detection methods by a significant margin without bells and whistles. Ablation studies demonstrate that our method performs the best among different enhancement settings.
Authors: Md Abdul Kadir, Gowtham Krishna Addluri, Daniel Sonntag
Ensuring the trustworthiness and interpretability of machine learning models is critical to their deployment in real-world applications. Feature attribution methods have gained significant attention, which provide local explanations of model predictions by attributing importance to individual input features. This study examines the generalization of feature attributions across various deep learning architectures, such as convolutional neural networks (CNNs) and vision transformers. We aim to assess the feasibility of utilizing a feature attribution method as a future detector and examine how these features can be harmonized across multiple models employing distinct architectures but trained on the same data distribution. By exploring this harmonization, we aim to develop a more coherent and optimistic understanding of feature attributions, enhancing the consistency of local explanations across diverse deep-learning models. Our findings highlight the potential for harmonized feature attribution methods to improve interpretability and foster trust in machine learning applications, regardless of the underlying architecture.
Authors: Deepak Raina, Dimitrios Ntentia, SH Chandrashekhara, Richard Voyles, Subir Kumar Saha
Ultrasound imaging is a commonly used modality for several diagnostic and therapeutic procedures. However, the diagnosis by ultrasound relies heavily on the quality of images assessed manually by sonographers, which diminishes the objectivity of the diagnosis and makes it operator-dependent. The supervised learning-based methods for automated quality assessment require manually annotated datasets, which are highly labour-intensive to acquire. These ultrasound images are low in quality and suffer from noisy annotations caused by inter-observer perceptual variations, which hampers learning efficiency. We propose an UnSupervised UltraSound image Quality assessment Network, US2QNet, that eliminates the burden and uncertainty of manual annotations. US2QNet uses the variational autoencoder embedded with the three modules, pre-processing, clustering and post-processing, to jointly enhance, extract, cluster and visualize the quality feature representation of ultrasound images. The pre-processing module uses filtering of images to point the network's attention towards salient quality features, rather than getting distracted by noise. Post-processing is proposed for visualizing the clusters of feature representations in 2D space. We validated the proposed framework for quality assessment of the urinary bladder ultrasound images. The proposed framework achieved 78% accuracy and superior performance to state-of-the-art clustering methods.
Authors: Chaoxing Huang, Vincent Wai Sun Wong, Queenie Chan, Winnie Chiu Wing Chu, Weitian Chen
Objective: Quantitative $T_1\rho$ imaging has potential for assessment of biochemical alterations of liver pathologies. Deep learning methods have been employed to accelerate quantitative $T_1\rho$ imaging. To employ artificial intelligence-based quantitative imaging methods in complicated clinical environment, it is valuable to estimate the uncertainty of the predicated $T_1\rho$ values to provide the confidence level of the quantification results. The uncertainty should also be utilized to aid the post-hoc quantitative analysis and model learning tasks. Approach: To address this need, we propose a parametric map refinement approach for learning-based $T_1\rho$ mapping and train the model in a probabilistic way to model the uncertainty. We also propose to utilize the uncertainty map to spatially weight the training of an improved $T_1\rho$ mapping network to further improve the mapping performance and to remove pixels with unreliable $T_1\rho$ values in the region of interest. The framework was tested on a dataset of 51 patients with different liver fibrosis stages. Main results: Our results indicate that the learning-based map refinement method leads to a relative mapping error of less than 3% and provides uncertainty estimation simultaneously. The estimated uncertainty reflects the actual error level, and it can be used to further reduce relative $T_1\rho$ mapping error to 2.60% as well as removing unreliable pixels in the region of interest effectively. Significance: Our studies demonstrate the proposed approach has potential to provide a learning-based quantitative MRI system for trustworthy $T_1\rho$ mapping of the liver.
Authors: Tianhao Wu, Chuanxia Zheng, Tat-Jen Cham
Generating complete 360-degree panoramas from narrow field of view images is ongoing research as omnidirectional RGB data is not readily available. Existing GAN-based approaches face some barriers to achieving higher quality output, and have poor generalization performance over different mask types. In this paper, we present our 360-degree indoor RGB panorama outpainting model using latent diffusion models (LDM), called IPO-LDM. We introduce a new bi-modal latent diffusion structure that utilizes both RGB and depth panoramic data during training, but works surprisingly well to outpaint normal depth-free RGB images during inference. We further propose a novel technique of introducing progressive camera rotations during each diffusion denoising step, which leads to substantial improvement in achieving panorama wraparound consistency. Results show that our IPO-LDM not only significantly outperforms state-of-the-art methods on RGB panorama outpainting, but can also produce multiple and diverse well-structured results for different types of masks.