Authors: Anton Jeran Ratnarajah, Sahani Goonetilleke, Dumindu Tissera, Kapilan Balagopalan, Ranga Rodrigo
Video synopsis, summarizing a video to generate a shorter video by exploiting the spatial and temporal redundancies, is important for surveillance and archiving. Existing trajectory-based video synopsis algorithms will not able to work in real time, because of the complexity due to the number of object tubes that need to be included in the complex energy minimization algorithm. We propose a real-time algorithm by using a method that incrementally stitches each frame of the synopsis by extracting object frames from the user specified number of tubes in the buffer in contrast to global energy-minimization based systems. This also gives flexibility to the user to set the threshold of maximum number of objects in the synopsis video according his or her tracking ability and creates collision-free summarized videos which are visually pleasing. Experiments with six common test videos, indoors and outdoors with many moving objects, show that the proposed video synopsis algorithm produces better frame reduction rates than existing approaches.
Authors: Suman Kunwar, Jannatul Ferdush
As the global population continues to expand, the demand for natural resources increases. Unfortunately, human activities account for 23% of greenhouse gas emissions. On a positive note, remote sensing technologies have emerged as a valuable tool in managing our environment. These technologies allow us to monitor land use, plan urban areas, and drive advancements in areas such as agriculture, climate change mitigation, disaster recovery, and environmental monitoring. Recent advances in AI, computer vision, and earth observation data have enabled unprecedented accuracy in land use mapping. By using transfer learning and fine-tuning with RGB bands, we achieved an impressive 99.19% accuracy in land use analysis. Such findings can be used to inform conservation and urban planning policies.
Authors: Momchil Peychev, Mark Niklas Müller, Marc Fischer, Martin Vechev
While the ImageNet dataset has been driving computer vision research over the past decade, significant label noise and ambiguity have made top-1 accuracy an insufficient measure of further progress. To address this, new label-sets and evaluation protocols have been proposed for ImageNet showing that state-of-the-art models already achieve over 95% accuracy and shifting the focus on investigating why the remaining errors persist.
Recent work in this direction employed a panel of experts to manually categorize all remaining classification errors for two selected models. However, this process is time-consuming, prone to inconsistencies, and requires trained experts, making it unsuitable for regular model evaluation thus limiting its utility. To overcome these limitations, we propose the first automated error classification framework, a valuable tool to study how modeling choices affect error distributions. We use our framework to comprehensively evaluate the error distribution of over 900 models. Perhaps surprisingly, we find that across model architectures, scales, and pre-training corpora, top-1 accuracy is a strong predictor for the portion of all error types. In particular, we observe that the portion of severe errors drops significantly with top-1 accuracy indicating that, while it underreports a model's true performance, it remains a valuable performance metric.
We release all our code at https://github.com/eth-sri/automated-error-analysis .
Authors: Zichen Xie, Ken Xingze Wang
We show a monotonic relationship between performances of various computer vision tasks versus degrees of coherence of illumination. We simulate partially coherent illumination using computational methods, propagate the lightwave to form images, and subsequently employ a deep neural network to perform object recognition and depth sensing tasks. In each controlled experiment, we discover that, increased coherent length leads to improved image entropy, as well as enhanced object recognition and depth sensing performance.
Authors: DaiXun Li, Weiying Xie, ZiXuan Wang, YiBing Lu, Yunsong Li, Leyuan Fang
With the rapid development of imaging sensor technology in the field of remote sensing, multi-modal remote sensing data fusion has emerged as a crucial research direction for land cover classification tasks. While diffusion models have made great progress in generative models and image classification tasks, existing models primarily focus on single-modality and single-client control, that is, the diffusion process is driven by a single modal in a single computing node. To facilitate the secure fusion of heterogeneous data from clients, it is necessary to enable distributed multi-modal control, such as merging the hyperspectral data of organization A and the LiDAR data of organization B privately on each base station client. In this study, we propose a multi-modal collaborative diffusion federated learning framework called FedDiff. Our framework establishes a dual-branch diffusion model feature extraction setup, where the two modal data are inputted into separate branches of the encoder. Our key insight is that diffusion models driven by different modalities are inherently complementary in terms of potential denoising steps on which bilateral connections can be built. Considering the challenge of private and efficient communication between multiple clients, we embed the diffusion model into the federated learning communication structure, and introduce a lightweight communication module. Qualitative and quantitative experiments validate the superiority of our framework in terms of image quality and conditional consistency.
Authors: Dong-Yi Wu, Thi-Ngoc-Hanh Le, Sheng-Yi Yao, Yun-Chen Lin, Tong-Yee Lee
Image collage is a very useful tool for visualizing an image collection. Most of the existing methods and commercial applications for generating image collages are designed on simple shapes, such as rectangular and circular layouts. This greatly limits the use of image collages in some artistic and creative settings. Although there are some methods that can generate irregularly-shaped image collages, they often suffer from severe image overlapping and excessive blank space. This prevents such methods from being effective information communication tools. In this paper, we present a shape slicing algorithm and an optimization scheme that can create image collages of arbitrary shapes in an informative and visually pleasing manner given an input shape and an image collection. To overcome the challenge of irregular shapes, we propose a novel algorithm, called Shape-Aware Slicing, which partitions the input shape into cells based on medial axis and binary slicing tree. Shape-Aware Slicing, which is designed specifically for irregular shapes, takes human perception and shape structure into account to generate visually pleasing partitions. Then, the layout is optimized by analyzing input images with the goal of maximizing the total salient regions of the images. To evaluate our method, we conduct extensive experiments and compare our results against previous work. The evaluations show that our proposed algorithm can efficiently arrange image collections on irregular shapes and create visually superior results than prior work and existing commercial tools.
Authors: Simon Niedermayr, Josef Stumpfegger, Rüdiger Westermann
Recently, high-fidelity scene reconstruction with an optimized 3D Gaussian splat representation has been introduced for novel view synthesis from sparse image sets. Making such representations suitable for applications like network streaming and rendering on low-power devices requires significantly reduced memory consumption as well as improved rendering efficiency. We propose a compressed 3D Gaussian splat representation that utilizes sensitivity-aware vector clustering with quantization-aware training to compress directional colors and Gaussian parameters. The learned codebooks have low bitrates and achieve a compression rate of up to $31\times$ on real-world scenes with only minimal degradation of visual quality. We demonstrate that the compressed splat representation can be efficiently rendered with hardware rasterization on lightweight GPUs at up to $4\times$ higher framerates than reported via an optimized GPU compute pipeline. Extensive experiments across multiple datasets demonstrate the robustness and rendering speed of the proposed approach.
Authors: Jinyung Hong, Theodore P. Pavlic
Geometric Sensitive Hashing functions, a family of Local Sensitive Hashing functions, are neural network models that learn class-specific manifold geometry in supervised learning. However, given a set of supervised learning tasks, understanding the manifold geometries that can represent each task and the kinds of relationships between the tasks based on them has received little attention. We explore a formalization of this question by considering a generative process where each task is associated with a high-dimensional manifold, which can be done in brain-like models with neuromodulatory systems. Following this formulation, we define \emph{Task-specific Geometric Sensitive Hashing~(T-GSH)} and show that a randomly weighted neural network with a neuromodulation system can realize this function.
Authors: Oindrila Saha, Grant Van Horn, Subhransu Maji
The zero-shot performance of existing vision-language models (VLMs) such as CLIP is limited by the availability of large-scale, aligned image and text datasets in specific domains. In this work, we leverage two complementary sources of information -- descriptions of categories generated by large language models (LLMs) and abundant, fine-grained image classification datasets -- to improve the zero-shot classification performance of VLMs across fine-grained domains. On the technical side, we develop methods to train VLMs with this "bag-level" image-text supervision. We find that simply using these attributes at test-time does not improve performance, but our training strategy, for example, on the iNaturalist dataset, leads to an average improvement of 4-5% in zero-shot classification accuracy for novel categories of birds and flowers. Similar improvements are observed in domains where a subset of the categories was used to fine-tune the model. By prompting LLMs in various ways, we generate descriptions that capture visual appearance, habitat, and geographic regions and pair them with existing attributes such as the taxonomic structure of the categories. We systematically evaluate their ability to improve zero-shot categorization in natural domains. Our findings suggest that geographic priors can be just as effective and are complementary to visual appearance. Our method also outperforms prior work on prompt-based tuning of VLMs. We plan to release the benchmark, consisting of 7 datasets, which will contribute to future research in zero-shot recognition.
Authors: Elia Peruzzo, Vidit Goel, Dejia Xu, Xingqian Xu, Yifan Jiang, Zhangyang Wang, Humphrey Shi, Nicu Sebe
Recently, several works tackled the video editing task fostered by the success of large-scale text-to-image generative models. However, most of these methods holistically edit the frame using the text, exploiting the prior given by foundation diffusion models and focusing on improving the temporal consistency across frames. In this work, we introduce a framework that is object-centric and is designed to control both the object's appearance and, notably, to execute precise and explicit structural modifications on the object. We build our framework on a pre-trained image-conditioned diffusion model, integrate layers to handle the temporal dimension, and propose training strategies and architectural modifications to enable shape control. We evaluate our method on the image-driven video editing task showing similar performance to the state-of-the-art, and showcasing novel shape-editing capabilities. Further details, code and examples are available on our project page: https://helia95.github.io/vase-website/
Authors: Layton Aho, Mark Winter, Marc DeCarlo, Agne Frismantiene, Yannick Blum, Paolo Armando Gagliardi, Olivier Pertz, Andrew R. Cohen
Live cell microscopy captures 5-D $(x,y,z,channel,time)$ movies that display patterns of cellular motion and signaling dynamics. We present here an approach to finding spatiotemporal patterns of cell signaling dynamics in 5-D live cell microscopy movies unique in requiring no \emph{a priori} knowledge of expected pattern dynamics, and no training data. The proposed cell signaling structure function (SSF) is a Kolmogorov structure function that optimally measures cell signaling state as nuclear intensity w.r.t. surrounding cytoplasm, a significant improvement compared to the current state-of-the-art cytonuclear ratio. SSF kymographs store at each spatiotemporal cell centroid the SSF value, or a functional output such as velocity. Patterns of similarity are identified via the metric normalized compression distance (NCD). The NCD is a reproducing kernel for a Hilbert space that represents the input SSF kymographs as points in a low dimensional embedding that optimally captures the pattern similarity identified by the NCD throughout the space. The only parameter is the expected cell radii ($\mu m$). A new formulation of the cluster structure function optimally estimates how meaningful an embedding from the RKHS representation. Results are presented quantifying the impact of ERK and AKT signaling between different oncogenic mutations, and by the relation between ERK signaling and cellular velocity patterns for movies of 2-D monolayers of human breast epithelial (MCF10A) cells, 3-D MCF10A spheroids under optogenetic manipulation of ERK, and human induced pluripotent stem cells .
Authors: Md Ruman Islam, Mahadevan Subramaniam, Pei-Chi Huang (Department of Computer Science, University of Nebraska at Omaha, Omaha, NE, USA)
Smart Digital twins (SDTs) are being increasingly used to virtually replicate and predict the behaviors of complex physical systems through continual data assimilation enabling the optimization of the performance of these systems by controlling the actions of systems. Recently, deep learning (DL) models have significantly enhanced the capabilities of SDTs, particularly for tasks such as predictive maintenance, anomaly detection, and optimization. In many domains, including medicine, engineering, and education, SDTs use image data (image-based SDTs) to observe and learn system behaviors and control their behaviors. This paper focuses on various approaches and associated challenges in developing image-based SDTs by continually assimilating image data from physical systems. The paper also discusses the challenges involved in designing and implementing DL models for SDTs, including data acquisition, processing, and interpretation. In addition, insights into the future directions and opportunities for developing new image-based DL approaches to develop robust SDTs are provided. This includes the potential for using generative models for data augmentation, developing multi-modal DL models, and exploring the integration of DL with other technologies, including 5G, edge computing, and IoT. In this paper, we describe the image-based SDTs, which enable broader adoption of the digital twin DT paradigms across a broad spectrum of areas and the development of new methods to improve the abilities of SDTs in replicating, predicting, and optimizing the behavior of complex systems.
Authors: André Bauer, Simon Trapp, Michael Stenger, Robert Leppich, Samuel Kounev, Mark Leznik, Kyle Chard, Ian Foster
Recent years have witnessed a surge in the popularity of Machine Learning (ML), applied across diverse domains. However, progress is impeded by the scarcity of training data due to expensive acquisition and privacy legislation. Synthetic data emerges as a solution, but the abundance of released models and limited overview literature pose challenges for decision-making. This work surveys 417 Synthetic Data Generation (SDG) models over the last decade, providing a comprehensive overview of model types, functionality, and improvements. Common attributes are identified, leading to a classification and trend analysis. The findings reveal increased model performance and complexity, with neural network-based approaches prevailing, except for privacy-preserving data generation. Computer vision dominates, with GANs as primary generative models, while diffusion models, transformers, and RNNs compete. Implications from our performance evaluation highlight the scarcity of common metrics and datasets, making comparisons challenging. Additionally, the neglect of training and computational costs in literature necessitates attention in future research. This work serves as a guide for SDG model selection and identifies crucial areas for future exploration.
Authors: Ahmed Salah, David Yevick
This paper introduces a modified variational autoencoder (VAEs) that contains an additional neural network branch. The resulting branched VAE (BVAE) contributes a classification component based on the class labels to the total loss and therefore imparts categorical information to the latent representation. As a result, the latent space distributions of the input classes are separated and ordered, thereby enhancing the classification accuracy. The degree of improvement is quantified by numerical calculations employing the benchmark MNIST dataset for both unrotated and rotated digits. The proposed technique is then compared to and then incorporated into a VAE with fixed output distributions. This procedure is found to yield improved performance for a wide range of output distributions.
Authors: Mohamed S. E. Habib, Hossam A. H. Fahmy, Mohamed F. Abu-ElYazeed
Optical lithography is the main enabler to semiconductor manufacturing. It requires extensive processing to perform the Resolution Enhancement Techniques (RETs) required to transfer the design data to a working Integrated Circuits (ICs). The processing power and computational runtime for RETs tasks is ever increasing due to the continuous reduction of the feature size and the expansion of the chip area. State-of-the-art research sought Machine Learning (ML) technologies to reduce runtime and computational power, however they are still not used in production yet. In this study, we analyze the reasons holding back ML computational lithography from being production ready and present a novel highly scalable end-to-end flow that enables production ready ML-RET correction.
Authors: Pegah Ahadian, Maryam Babaei, Kourosh Parand
A brain tumor consists of cells showing abnormal brain growth. The area of the brain tumor significantly affects choosing the type of treatment and following the course of the disease during the treatment. At the same time, pictures of Brain MRIs are accompanied by noise. Eliminating existing noises can significantly impact the better segmentation and diagnosis of brain tumors. In this work, we have tried using the analysis of eigenvalues. We have used the MSVD algorithm, reducing the image noise and then using the deep neural network to segment the tumor in the images. The proposed method's accuracy was increased by 2.4% compared to using the original images. With Using the MSVD method, convergence speed has also increased, showing the proposed method's effectiveness
Authors: Dianye Huang, Chenguang Yang, Mingchuan Zhou, Angelos Karlas, Nassir Navab, Zhongliang Jiang
Deep Venous Thrombosis (DVT) is a common vascular disease with blood clots inside deep veins, which may block blood flow or even cause a life-threatening pulmonary embolism. A typical exam for DVT using ultrasound (US) imaging is by pressing the target vein until its lumen is fully compressed. However, the compression exam is highly operator-dependent. To alleviate intra- and inter-variations, we present a robotic US system with a novel hybrid force motion control scheme ensuring position and force tracking accuracy, and soft landing of the probe onto the target surface. In addition, a path-based virtual fixture is proposed to realize easy human-robot interaction for repeat compression operation at the lesion location. To ensure the biometric measurements obtained in different examinations are comparable, the 6D scanning path is determined in a coarse-to-fine manner using both an external RGBD camera and US images. The RGBD camera is first used to extract a rough scanning path on the object. Then, the segmented vascular lumen from US images are used to optimize the scanning path to ensure the visibility of the target object. To generate a continuous scan path for developing virtual fixtures, an arc-length based path fitting model considering both position and orientation is proposed. Finally, the whole system is evaluated on a human-like arm phantom with an uneven surface.
Authors: Rahul Ahuja, Chris Baker, Wilko Schwarting
Scene flow estimation is a crucial component in the development of autonomous driving and 3D robotics, providing valuable information for environment perception and navigation. Despite the advantages of learning-based scene flow estimation techniques, their domain specificity and limited generalizability across varied scenarios pose challenges. In contrast, non-learning optimization-based methods, incorporating robust priors or regularization, offer competitive scene flow estimation performance, require no training, and show extensive applicability across datasets, but suffer from lengthy inference times. In this paper, we present OptFlow, a fast optimization-based scene flow estimation method. Without relying on learning or any labeled datasets, OptFlow achieves state-of-the-art performance for scene flow estimation on popular autonomous driving benchmarks. It integrates a local correlation weight matrix for correspondence matching, an adaptive correspondence threshold limit for nearest-neighbor search, and graph prior rigidity constraints, resulting in expedited convergence and improved point correspondence identification. Moreover, we demonstrate how integrating a point cloud registration function within our objective function bolsters accuracy and differentiates between static and dynamic points without relying on external odometry data. Consequently, OptFlow outperforms the baseline graph-prior method by approximately 20% and the Neural Scene Flow Prior method by 5%-7% in accuracy, all while offering the fastest inference time among all non-learning scene flow estimation methods.
Authors: Parisa Boodaghi Malidarreh, Biraaj Rout, Mohammad Sadegh Nasr, Priyanshi Borad, Jillur Rahman Saurav, Jai Prakash Veerla, Kelli Fenelon, Theodora Koromila, Jacob M. Luber
In this paper, we introduce a pipeline based on Random Forest Regression to predict the future distribution of cells that are expressed by the Sog-D gene (active cells) in both the Anterior to posterior (AP) and the Dorsal to Ventral (DV) axis of the Drosophila in embryogenesis process. This method provides insights about how cells and living organisms control gene expression in super resolution whole embryo spatial transcriptomics imaging at sub cellular, single molecule resolution. A Random Forest Regression model was used to predict the next stage active distribution based on the previous one. To achieve this goal, we leveraged temporally resolved, spatial point processes by including Ripley's K-function in conjunction with the cell's state in each stage of embryogenesis, and found average predictive accuracy of active cell distribution. This tool is analogous to RNA Velocity for spatially resolved developmental biology, from one data point we can predict future spatially resolved gene expression using features from the spatial point processes.
Authors: Jai Prakash Veerla, Poojitha Thota, Partha Sai Guttikonda, Shirin Nilizadeh, Jacob M. Luber
In the dynamic landscape of medical artificial intelligence, this study explores the vulnerabilities of the Pathology Language-Image Pretraining (PLIP) model, a Vision Language Foundation model, under targeted adversarial conditions. Leveraging the Kather Colon dataset with 7,180 H&E images across nine tissue types, our investigation employs Projected Gradient Descent (PGD) adversarial attacks to intentionally induce misclassifications. The outcomes reveal a 100% success rate in manipulating PLIP's predictions, underscoring its susceptibility to adversarial perturbations. The qualitative analysis of adversarial examples delves into the interpretability challenges, shedding light on nuanced changes in predictions induced by adversarial manipulations. These findings contribute crucial insights into the interpretability, domain adaptation, and trustworthiness of Vision Language Models in medical imaging. The study emphasizes the pressing need for robust defenses to ensure the reliability of AI models.
Authors: Daoan Zhang, Junming Yang, Hanjia Lyu, Zijian Jin, Yuan Yao, Mingkai Chen, Jiebo Luo
When exploring the development of Artificial General Intelligence (AGI), a critical task for these models involves interpreting and processing information from multiple image inputs. However, Large Multimodal Models (LMMs) encounter two issues in such scenarios: (1) a lack of fine-grained perception, and (2) a tendency to blend information across multiple images. We first extensively investigate the capability of LMMs to perceive fine-grained visual details when dealing with multiple input images. The research focuses on two aspects: first, image-to-image matching (to evaluate whether LMMs can effectively reason and pair relevant images), and second, multi-image-to-text matching (to assess whether LMMs can accurately capture and summarize detailed image information). We conduct evaluations on a range of both open-source and closed-source large models, including GPT-4V, Gemini, OpenFlamingo, and MMICL. To enhance model performance, we further develop a Contrastive Chain-of-Thought (CoCoT) prompting approach based on multi-input multimodal models. This method requires LMMs to compare the similarities and differences among multiple image inputs, and then guide the models to answer detailed questions about multi-image inputs based on the identified similarities and differences. Our experimental results showcase CoCoT's proficiency in enhancing the multi-image comprehension capabilities of large multimodal models.
Authors: Van Minh Nguyen, Emma Sandidge, Trupti Mahendrakar, Ryan T. White
The accelerating deployment of spacecraft in orbit have generated interest in on-orbit servicing (OOS), inspection of spacecraft, and active debris removal (ADR). Such missions require precise rendezvous and proximity operations in the vicinity of non-cooperative, possible unknown, resident space objects. Safety concerns with manned missions and lag times with ground-based control necessitate complete autonomy. This requires robust characterization of the target's geometry. In this article, we present an approach for mapping geometries of satellites on orbit based on 3D Gaussian Splatting that can run on computing resources available on current spaceflight hardware. We demonstrate model training and 3D rendering performance on a hardware-in-the-loop satellite mock-up under several realistic lighting and motion conditions. Our model is shown to be capable of training on-board and rendering higher quality novel views of an unknown satellite nearly 2 orders of magnitude faster than previous NeRF-based algorithms. Such on-board capabilities are critical to enable downstream machine intelligence tasks necessary for autonomous guidance, navigation, and control tasks.
Authors: Meiling Li, Nan Zhong, Xinpeng Zhang, Zhenxing Qian, Sheng Li
Backdoor attack against image classification task has been widely studied and proven to be successful, while there exist little research on the backdoor attack against vision-language models. In this paper, we explore backdoor attack towards image captioning models by poisoning training data. Assuming the attacker has total access to the training dataset, and cannot intervene in model construction or training process. Specifically, a portion of benign training samples is randomly selected to be poisoned. Afterwards, considering that the captions are usually unfolded around objects in an image, we design an object-oriented method to craft poisons, which aims to modify pixel values by a slight range with the modification number proportional to the scale of the current detected object region. After training with the poisoned data, the attacked model behaves normally on benign images, but for poisoned images, the model will generate some sentences irrelevant to the given image. The attack controls the model behavior on specific test images without sacrificing the generation performance on benign test images. Our method proves the weakness of image captioning models to backdoor attack and we hope this work can raise the awareness of defending against backdoor attack in the image captioning field.
Authors: Wen Dong, Haiyang Mei, Ziqi Wei, Ao Jin, Sen Qiu, Qiang Zhang, Xin Yang
Car detection is an important task that serves as a crucial prerequisite for many automated driving functions. The large variations in lighting/weather conditions and vehicle densities of the scenes pose significant challenges to existing car detection algorithms to meet the highly accurate perception demand for safety, due to the unstable/limited color information, which impedes the extraction of meaningful/discriminative features of cars. In this work, we present a novel learning-based car detection method that leverages trichromatic linear polarization as an additional cue to disambiguate such challenging cases. A key observation is that polarization, characteristic of the light wave, can robustly describe intrinsic physical properties of the scene objects in various imaging conditions and is strongly linked to the nature of materials for cars (e.g., metal and glass) and their surrounding environment (e.g., soil and trees), thereby providing reliable and discriminative features for robust car detection in challenging scenes. To exploit polarization cues, we first construct a pixel-aligned RGB-Polarization car detection dataset, which we subsequently employ to train a novel multimodal fusion network. Our car detection network dynamically integrates RGB and polarization features in a request-and-complement manner and can explore the intrinsic material properties of cars across all learning samples. We extensively validate our method and demonstrate that it outperforms state-of-the-art detection methods. Experimental results show that polarization is a powerful cue for car detection.
Authors: Yuping Ye, Zhan Song, Juan Zhao
This paper presents a partition-based surface registration for 3D morphable model(3DMM). In the 3DMM, it often requires to warp a handcrafted template model into different captured models. The proposed method first utilizes the landmarks to partition the template model then scale each part and finally smooth the boundaries. This method is especially effective when the disparity between the template model and the target model is huge. The experiment result shows the method perform well than the traditional warp method and robust to the local minima.
Authors: Jincen Jiang, Lizhi Zhao, Xuequan Lu, Wei Hu, Imran Razzak, Meili Wang
Recent works attempt to extend Graph Convolution Networks (GCNs) to point clouds for classification and segmentation tasks. These works tend to sample and group points to create smaller point sets locally and mainly focus on extracting local features through GCNs, while ignoring the relationship between point sets. In this paper, we propose the Dynamic Hop Graph Convolution Network (DHGCN) for explicitly learning the contextual relationships between the voxelized point parts, which are treated as graph nodes. Motivated by the intuition that the contextual information between point parts lies in the pairwise adjacent relationship, which can be depicted by the hop distance of the graph quantitatively, we devise a novel self-supervised part-level hop distance reconstruction task and design a novel loss function accordingly to facilitate training. In addition, we propose the Hop Graph Attention (HGA), which takes the learned hop distance as input for producing attention weights to allow edge features to contribute distinctively in aggregation. Eventually, the proposed DHGCN is a plug-and-play module that is compatible with point-based backbone networks. Comprehensive experiments on different backbones and tasks demonstrate that our self-supervised method achieves state-of-the-art performance. Our source code is available at: https://github.com/Jinec98/DHGCN.
Authors: Jingyao Li, Pengguang Chen, Shaozuo Yu, Shu Liu, Jiaya Jia
The crux of effective out-of-distribution (OOD) detection lies in acquiring a robust in-distribution (ID) representation, distinct from OOD samples. While previous methods predominantly leaned on recognition-based techniques for this purpose, they often resulted in shortcut learning, lacking comprehensive representations. In our study, we conducted a comprehensive analysis, exploring distinct pretraining tasks and employing various OOD score functions. The results highlight that the feature representations pre-trained through reconstruction yield a notable enhancement and narrow the performance gap among various score functions. This suggests that even simple score functions can rival complex ones when leveraging reconstruction-based pretext tasks. Reconstruction-based pretext tasks adapt well to various score functions. As such, it holds promising potential for further expansion. Our OOD detection framework, MOODv2, employs the masked image modeling pretext task. Without bells and whistles, MOODv2 impressively enhances 14.30% AUROC to 95.68% on ImageNet and achieves 99.98% on CIFAR-10.
Authors: Yongxu Liu, Yinghui Quan, Guoyao Xiao, Aobo Li, Jinjian Wu
Quality assessment of images and videos emphasizes both local details and global semantics, whereas general data sampling methods (e.g., resizing, cropping or grid-based fragment) fail to catch them simultaneously. To address the deficiency, current approaches have to adopt multi-branch models and take as input the multi-resolution data, which burdens the model complexity. In this work, instead of stacking up models, a more elegant data sampling method (named as SAMA, scaling and masking) is explored, which compacts both the local and global content in a regular input size. The basic idea is to scale the data into a pyramid first, and reduce the pyramid into a regular data dimension with a masking strategy. Benefiting from the spatial and temporal redundancy in images and videos, the processed data maintains the multi-scale characteristics with a regular input size, thus can be processed by a single-branch model. We verify the sampling method in image and video quality assessment. Experiments show that our sampling method can improve the performance of current single-branch models significantly, and achieves competitive performance to the multi-branch models without extra model complexity. The source code will be available at https://github.com/Sissuire/SAMA.
Authors: Hao Zhang, Yu-Wing Tai, Chi-Keung Tang
The success of the GAN-NeRF structure has enabled face editing on NeRF to maintain 3D view consistency. However, achieving simultaneously multi-view consistency and temporal coherence while editing video sequences remains a formidable challenge. This paper proposes a novel face video editing architecture built upon the dynamic face GAN-NeRF structure, which effectively utilizes video sequences to restore the latent code and 3D face geometry. By editing the latent code, multi-view consistent editing on the face can be ensured, as validated by multiview stereo reconstruction on the resulting edited images in our dynamic NeRF. As the estimation of face geometries occurs on a frame-by-frame basis, this may introduce a jittering issue. We propose a stabilizer that maintains temporal coherence by preserving smooth changes of face expressions in consecutive frames. Quantitative and qualitative analyses reveal that our method, as the pioneering 4D face video editor, achieves state-of-the-art performance in comparison to existing 2D or 3D-based approaches independently addressing identity and motion. Codes will be released.
Authors: Ryota Iijima, Sayaka Shiota, Hitoshi Kiya
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, which means AEs generated for a source model can fool another black-box model (target model) with a non-trivial probability. In previous studies, it was confirmed that the vision transformer (ViT) is more robust against the property of adversarial transferability than convolutional neural network (CNN) models such as ConvMixer, and moreover encrypted ViT is more robust than ViT without any encryption. In this article, we propose a random ensemble of encrypted ViT models to achieve much more robust models. In experiments, the proposed scheme is verified to be more robust against not only black-box attacks but also white-box ones than convention methods.
Authors: Huy Nguyen, Kien Nguyen, Sridha Sridharan, Clinton Fookes
Aerial-ground person re-identification (Re-ID) presents unique challenges in computer vision, stemming from the distinct differences in viewpoints, poses, and resolutions between high-altitude aerial and ground-based cameras. Existing research predominantly focuses on ground-to-ground matching, with aerial matching less explored due to a dearth of comprehensive datasets. To address this, we introduce AG-ReID.v2, a dataset specifically designed for person Re-ID in mixed aerial and ground scenarios. This dataset comprises 100,502 images of 1,615 unique individuals, each annotated with matching IDs and 15 soft attribute labels. Data were collected from diverse perspectives using a UAV, stationary CCTV, and smart glasses-integrated camera, providing a rich variety of intra-identity variations. Additionally, we have developed an explainable attention network tailored for this dataset. This network features a three-stream architecture that efficiently processes pairwise image distances, emphasizes key top-down features, and adapts to variations in appearance due to altitude differences. Comparative evaluations demonstrate the superiority of our approach over existing baselines. We plan to release the dataset and algorithm source code publicly, aiming to advance research in this specialized field of computer vision. For access, please visit https://github.com/huynguyen792/AG-ReID.v2.
Authors: Aritra Mukherjee, Abhijit Das
Recent literature has witnessed significant interest towards 3D biometrics employing monocular vision for robust authentication methods. Motivated by this, in this work we seek to provide insight on recent development in the area of 3D biometrics employing monocular vision. We present the similarity and dissimilarity of 3D monocular biometrics and classical biometrics, listing the strengths and challenges. Further, we provide an overview of recent techniques in 3D biometrics with monocular vision, as well as application systems adopted by the industry. Finally, we discuss open research problems in this area of research
Authors: Saurabh Atreya, Maheswar Bora, Aritra Mukherjee, Abhijit Das
This work proposes a novel process of using pen tip and tail 3D trajectory for air signature. To acquire the trajectories we developed a new pen tool and a stereo camera was used. We proposed SliT-CNN, a novel 2D spatial-temporal convolutional neural network (CNN) for better featuring of the air signature. In addition, we also collected an air signature dataset from $45$ signers. Skilled forgery signatures per user are also collected. A detailed benchmarking of the proposed dataset using existing techniques and proposed CNN on existing and proposed dataset exhibit the effectiveness of our methodology.
Authors: Sunyi Zheng, Xiaonan Cui, Yuxuan Sun, Jingxiong Li, Honglin Li, Yunlong Zhang, Pingyi Chen, Xueping Jing, Zhaoxiang Ye, Lin Yang
Accurate image classification and retrieval are of importance for clinical diagnosis and treatment decision-making. The recent contrastive language-image pretraining (CLIP) model has shown remarkable proficiency in understanding natural images. Drawing inspiration from CLIP, PathCLIP is specifically designed for pathology image analysis, utilizing over 200,000 image and text pairs in training. While the performance the PathCLIP is impressive, its robustness under a wide range of image corruptions remains unknown. Therefore, we conduct an extensive evaluation to analyze the performance of PathCLIP on various corrupted images from the datasets of Osteosarcoma and WSSS4LUAD. In our experiments, we introduce seven corruption types including brightness, contrast, Gaussian blur, resolution, saturation, hue, and markup at four severity levels. Through experiments, we find that PathCLIP is relatively robustness to image corruptions and surpasses OpenAI-CLIP and PLIP in zero-shot classification. Among the seven corruptions, blur and resolution can cause server performance degradation of the PathCLIP. This indicates that ensuring the quality of images is crucial before conducting a clinical test. Additionally, we assess the robustness of PathCLIP in the task of image-image retrieval, revealing that PathCLIP performs less effectively than PLIP on Osteosarcoma but performs better on WSSS4LUAD under diverse corruptions. Overall, PathCLIP presents impressive zero-shot classification and retrieval performance for pathology images, but appropriate care needs to be taken when using it. We hope this study provides a qualitative impression of PathCLIP and helps understand its differences from other CLIP models.
Authors: SeokHyun Seo, Jinwoo Hong, JungWoo Chae, Kyungyul Kim, Sangheum Hwang
Utilizing well-trained representations in transfer learning often results in superior performance and faster convergence compared to training from scratch. However, even if such good representations are transferred, a model can easily overfit the limited training dataset and lose the valuable properties of the transferred representations. This phenomenon is more severe in ViT due to its low inductive bias. Through experimental analysis using attention maps in ViT, we observe that the rich representations deteriorate when trained on a small dataset. Motivated by this finding, we propose a novel and simple regularization method for ViT called Guided Transfer of spatial Attention (GTA). Our proposed method regularizes the self-attention maps between the source and target models. A target model can fully exploit the knowledge related to object localization properties through this explicit regularization. Our experimental results show that the proposed GTA consistently improves the accuracy across five benchmark datasets especially when the number of training data is small.
Authors: Yatharth Gupta, Vishnu V. Jaddipal, Harish Prabhala, Sayak Paul, Patrick Von Platen
Stable Diffusion XL (SDXL) has become the best open source text-to-image model (T2I) for its versatility and top-notch image quality. Efficiently addressing the computational demands of SDXL models is crucial for wider reach and applicability. In this work, we introduce two scaled-down variants, Segmind Stable Diffusion (SSD-1B) and Segmind-Vega, with 1.3B and 0.74B parameter UNets, respectively, achieved through progressive removal using layer-level losses focusing on reducing the model size while preserving generative quality. We release these models weights at https://hf.co/Segmind. Our methodology involves the elimination of residual networks and transformer blocks from the U-Net structure of SDXL, resulting in significant reductions in parameters, and latency. Our compact models effectively emulate the original SDXL by capitalizing on transferred knowledge, achieving competitive results against larger multi-billion parameter SDXL. Our work underscores the efficacy of knowledge distillation coupled with layer-level losses in reducing model size while preserving the high-quality generative capabilities of SDXL, thus facilitating more accessible deployment in resource-constrained environments.
Authors: Sasindu Wijeratne, Bingyi Zhang, Rajgopal Kannan, Viktor Prasanna, Carl Busart
Synthetic Aperture Radar (SAR) images are commonly utilized in military applications for automatic target recognition (ATR). Machine learning (ML) methods, such as Convolutional Neural Networks (CNN) and Graph Neural Networks (GNN), are frequently used to identify ground-based objects, including battle tanks, personnel carriers, and missile launchers. Determining the vehicle class, such as the BRDM2 tank, BMP2 tank, BTR60 tank, and BTR70 tank, is crucial, as it can help determine whether the target object is an ally or an enemy. While the ML algorithm provides feedback on the recognized target, the final decision is left to the commanding officers. Therefore, providing detailed information alongside the identified target can significantly impact their actions. This detailed information includes the SAR image features that contributed to the classification, the classification confidence, and the probability of the identified object being classified as a different object type or class. We propose a GNN-based ATR framework that provides the final classified class and outputs the detailed information mentioned above. This is the first study to provide a detailed analysis of the classification class, making final decisions more straightforward. Moreover, our GNN framework achieves an overall accuracy of 99.2\% when evaluated on the MSTAR dataset, improving over previous state-of-the-art GNN methods.
Authors: Pengying Wu, Yao Mu, Bingxian Wu, Yi Hou, Ji Ma, Shanghang Zhang, Chang Liu
In the realm of household robotics, the Zero-Shot Object Navigation (ZSON) task empowers agents to adeptly traverse unfamiliar environments and locate objects from novel categories without prior explicit training. This paper introduces VoroNav, a novel semantic exploration framework that proposes the Reduced Voronoi Graph to extract exploratory paths and planning nodes from a semantic map constructed in real time. By harnessing topological and semantic information, VoroNav designs text-based descriptions of paths and images that are readily interpretable by a large language model (LLM). Our approach presents a synergy of path and farsight descriptions to represent the environmental context, enabling the LLM to apply commonsense reasoning to ascertain the optimal waypoints for navigation. Extensive evaluation on the HM3D and HSSD datasets validates that VoroNav surpasses existing ZSON benchmarks in both success rates and exploration efficiency (+2.8% Success and +3.7% SPL on HM3D, +2.6% Success and +3.8% SPL on HSSD). Additionally introduced metrics that evaluate obstacle avoidance proficiency and perceptual efficiency further corroborate the enhancements achieved by our method in ZSON planning.
Authors: Ziying Song, Guoxin Zhang, Jun Xie, Lin Liu, Caiyan Jia, Shaoqing Xu, Zhepeng Wang
LiDAR-camera fusion can enhance the performance of 3D object detection by utilizing complementary information between depth-aware LiDAR points and semantically rich images. Existing voxel-based methods face significant challenges when fusing sparse voxel features with dense image features in a one-to-one manner, resulting in the loss of the advantages of images, including semantic and continuity information, leading to sub-optimal detection performance, especially at long distances. In this paper, we present VoxelNextFusion, a multi-modal 3D object detection framework specifically designed for voxel-based methods, which effectively bridges the gap between sparse point clouds and dense images. In particular, we propose a voxel-based image pipeline that involves projecting point clouds onto images to obtain both pixel- and patch-level features. These features are then fused using a self-attention to obtain a combined representation. Moreover, to address the issue of background features present in patches, we propose a feature importance module that effectively distinguishes between foreground and background features, thus minimizing the impact of the background features. Extensive experiments were conducted on the widely used KITTI and nuScenes 3D object detection benchmarks. Notably, our VoxelNextFusion achieved around +3.20% in AP@0.7 improvement for car detection in hard level compared to the Voxel R-CNN baseline on the KITTI test dataset
Authors: Chuyun Shen, Wenhao Li, Haoqing Chen, Xiaoling Wang, Fengping Zhu, Yuxin Li, Xiangfeng Wang, Bo Jin
Radiologists must utilize multiple modal images for tumor segmentation and diagnosis due to the limitations of medical imaging and the diversity of tumor signals. This leads to the development of multimodal learning in segmentation. However, the redundancy among modalities creates challenges for existing subtraction-based joint learning methods, such as misjudging the importance of modalities, ignoring specific modal information, and increasing cognitive load. These thorny issues ultimately decrease segmentation accuracy and increase the risk of overfitting. This paper presents the complementary information mutual learning (CIML) framework, which can mathematically model and address the negative impact of inter-modal redundant information. CIML adopts the idea of addition and removes inter-modal redundant information through inductive bias-driven task decomposition and message passing-based redundancy filtering. CIML first decomposes the multimodal segmentation task into multiple subtasks based on expert prior knowledge, minimizing the information dependence between modalities. Furthermore, CIML introduces a scheme in which each modality can extract information from other modalities additively through message passing. To achieve non-redundancy of extracted information, the redundant filtering is transformed into complementary information learning inspired by the variational information bottleneck. The complementary information learning procedure can be efficiently solved by variational inference and cross-modal spatial attention. Numerical results from the verification task and standard benchmarks indicate that CIML efficiently removes redundant information between modalities, outperforming SOTA methods regarding validation accuracy and segmentation effect.
Authors: Yunshan Zhong, Yuyao Zhou, Yuxin Zhang, Fei Chao, Rongrong Ji
This paper focuses on addressing the issue of image demoireing. Unlike the large volume of existing studies that rely on learning from paired real data, we attempt to learn a demoireing model from unpaired real data, i.e., moire images associated with irrelevant clean images. The proposed method, referred to as Unpaired Demoireing (UnDeM), synthesizes pseudo moire images from unpaired datasets, generating pairs with clean images for training demoireing models. To achieve this, we divide real moire images into patches and group them in compliance with their moire complexity. We introduce a novel moire generation framework to synthesize moire images with diverse moire features, resembling real moire patches, and details akin to real moire-free images. Additionally, we introduce an adaptive denoise method to eliminate the low-quality pseudo moire images that adversely impact the learning of demoireing models. We conduct extensive experiments on the commonly-used FHDMi and UHDM datasets. Results manifest that our UnDeM performs better than existing methods when using existing demoireing models such as MBCNN and ESDNet-L. Code: https://github.com/zysxmu/UnDeM
Authors: Muhammad Yaqub, Shahzad Ahmad, Malik Abdul Manan, Imran Shabir Chuhan
Real-time traffic flow prediction holds significant importance within the domain of Intelligent Transportation Systems (ITS). The task of achieving a balance between prediction precision and computational efficiency presents a significant challenge. In this article, we present a novel deep-learning method called Federated Learning and Asynchronous Graph Convolutional Network (FLAGCN). Our framework incorporates the principles of asynchronous graph convolutional networks with federated learning to enhance the accuracy and efficiency of real-time traffic flow prediction. The FLAGCN model employs a spatial-temporal graph convolution technique to asynchronously address spatio-temporal dependencies within traffic data effectively. To efficiently handle the computational requirements associated with this deep learning model, this study used a graph federated learning technique known as GraphFL. This approach is designed to facilitate the training process. The experimental results obtained from conducting tests on two distinct traffic datasets demonstrate that the utilization of FLAGCN leads to the optimization of both training and inference durations while maintaining a high level of prediction accuracy. FLAGCN outperforms existing models with significant improvements by achieving up to approximately 6.85% reduction in RMSE, 20.45% reduction in MAPE, compared to the best-performing existing models.
Authors: Hui Zeng, Biwei Chen, Anjie Peng
Adversarial examples (AEs) have been extensively studied due to their potential for privacy protection and inspiring robust neural networks. However, making a targeted AE transferable across unknown models remains challenging. In this paper, to alleviate the overfitting dilemma common in an AE crafted by existing simple iterative attacks, we propose fine-tuning it in the feature space. Specifically, starting with an AE generated by a baseline attack, we encourage the features that contribute to the target class and discourage the features that contribute to the original class in a middle layer of the source model. Extensive experiments demonstrate that only a few iterations of fine-tuning can boost existing attacks in terms of targeted transferability nontrivially and universally. Our results also verify that the simple iterative attacks can yield comparable or even better transferability than the resource-intensive methods, which rely on training target-specific classifiers or generators with additional data. The code is available at: github.com/zengh5/TA_feature_FT.
Authors: Alfirsa Damasyifa Fauzulhaq, Wahyu Parwitayasa, Joseph Ananda Sugihdharma, M. Fadli Ridhani, Novanto Yudistira
Neuron labeling is an approach to visualize the behaviour and respond of a certain neuron to a certain pattern that activates the neuron. Neuron labeling extract information about the features captured by certain neurons in a deep neural network, one of which uses the encoder-decoder image captioning approach. The encoder used can be a pretrained CNN-based model and the decoder is an RNN-based model for text generation. Previous work, namely MILAN (Mutual Information-guided Linguistic Annotation of Neuron), has tried to visualize the neuron behaviour using modified Show, Attend, and Tell (SAT) model in the encoder, and LSTM added with Bahdanau attention in the decoder. MILAN can show great result on short sequence neuron captioning, but it does not show great result on long sequence neuron captioning, so in this work, we would like to improve the performance of MILAN even more by utilizing different kind of attention mechanism and additionally adding several attention result into one, in order to combine all the advantages from several attention mechanism. Using our compound dataset, we obtained higher BLEU and F1-Score on our proposed model, achieving 17.742 and 0.4811 respectively. At some point where the model converges at the peak, our model obtained BLEU of 21.2262 and BERTScore F1-Score of 0.4870.
Authors: David Gimeno-Gómez, Ana-Maria Bucur, Adrian Cosma, Carlos-David Martínez-Hinarejos, Paolo Rosso
Depression, a prominent contributor to global disability, affects a substantial portion of the population. Efforts to detect depression from social media texts have been prevalent, yet only a few works explored depression detection from user-generated video content. In this work, we address this research gap by proposing a simple and flexible multi-modal temporal model capable of discerning non-verbal depression cues from diverse modalities in noisy, real-world videos. We show that, for in-the-wild videos, using additional high-level non-verbal cues is crucial to achieving good performance, and we extracted and processed audio speech embeddings, face emotion embeddings, face, body and hand landmarks, and gaze and blinking information. Through extensive experiments, we show that our model achieves state-of-the-art results on three key benchmark datasets for depression detection from video by a substantial margin. Our code is publicly available on GitHub.
Authors: Amin Rezaei, Fatemeh Asadi
This review presents various image segmentation methods using complex networks.
Image segmentation is one of the important steps in image analysis as it helps analyze and understand complex images. At first, it has been tried to classify complex networks based on how it being used in image segmentation.
In computer vision and image processing applications, image segmentation is essential for analyzing complex images with irregular shapes, textures, or overlapping boundaries. Advanced algorithms make use of machine learning, clustering, edge detection, and region-growing techniques. Graph theory principles combined with community detection-based methods allow for more precise analysis and interpretation of complex images. Hybrid approaches combine multiple techniques for comprehensive, robust segmentation, improving results in computer vision and image processing tasks.
Authors: Manoj S H, Arya A Bosale
This research paper addresses the critical challenge of diabetic retinopathy (DR), a severe complication of diabetes leading to potential blindness. The proposed methodology leverages transfer learning with convolutional neural networks (CNNs) for automatic DR detection using a single fundus photograph, demonstrating high effectiveness with a quadratic weighted kappa score of 0.92546 in the APTOS 2019 Blindness Detection Competition. The paper reviews existing literature on DR detection, spanning classical computer vision methods to deep learning approaches, particularly focusing on CNNs. It identifies gaps in the research, emphasizing the lack of exploration in integrating pretrained large language models with segmented image inputs for generating recommendations and understanding dynamic interactions within a web application context.Objectives include developing a comprehensive DR detection methodology, exploring model integration, evaluating performance through competition ranking, contributing significantly to DR detection methodologies, and identifying research gaps.The methodology involves data preprocessing, data augmentation, and the use of a U-Net neural network architecture for segmentation. The U-Net model efficiently segments retinal structures, including blood vessels, hard and soft exudates, haemorrhages, microaneurysms, and the optical disc. High evaluation scores in Jaccard, F1, recall, precision, and accuracy underscore the model's potential for enhancing diagnostic capabilities in retinal pathology assessment.The outcomes of this research hold promise for improving patient outcomes through timely diagnosis and intervention in the fight against diabetic retinopathy, marking a significant contribution to the field of medical image analysis.
Authors: Hugo Chan-To-Hing, Bharadwaj Veeravalli
Self-supervised frameworks for representation learning have recently stirred up interest among the remote sensing community, given their potential to mitigate the high labeling costs associated with curating large satellite image datasets. In the realm of multimodal data fusion, while the often used contrastive learning methods can help bridging the domain gap between different sensor types, they rely on data augmentations techniques that require expertise and careful design, especially for multispectral remote sensing data. A possible but rather scarcely studied way to circumvent these limitations is to use a masked image modelling based pretraining strategy. In this paper, we introduce Fus-MAE, a self-supervised learning framework based on masked autoencoders that uses cross-attention to perform early and feature-level data fusion between synthetic aperture radar and multispectral optical data - two modalities with a significant domain gap. Our empirical findings demonstrate that Fus-MAE can effectively compete with contrastive learning strategies tailored for SAR-optical data fusion and outperforms other masked-autoencoders frameworks trained on a larger corpus.
Authors: Ryo Fujii, Ryo Hachiuma, Hideo Saito
Surgical tool detection is essential for analyzing and evaluating minimally invasive surgery videos. Current approaches are mostly based on supervised methods that require large, fully instance-level labels (i.e., bounding boxes). However, large image datasets with instance-level labels are often limited because of the burden of annotation. Thus, surgical tool detection is important when providing image-level labels instead of instance-level labels since image-level annotations are considerably more time-efficient than instance-level annotations. In this work, we propose to strike a balance between the extremely costly annotation burden and detection performance. We further propose a co-occurrence loss, which considers a characteristic that some tool pairs often co-occur together in an image to leverage image-level labels. Encapsulating the knowledge of co-occurrence using the co-occurrence loss helps to overcome the difficulty in classification that originates from the fact that some tools have similar shapes and textures. Extensive experiments conducted on the Endovis2018 dataset in various data settings show the effectiveness of our method.
Authors: Sandeep Mishra, Mukul Jha, Alan C. Bovik
We conducted a large-scale subjective study of the perceptual quality of User-Generated Mobile Video Content on a set of mobile-originated videos obtained from the Indian social media platform ShareChat. The content viewed by volunteer human subjects under controlled laboratory conditions has the benefit of culturally diversifying the existing corpus of User-Generated Content (UGC) video quality datasets. There is a great need for large and diverse UGC-VQA datasets, given the explosive global growth of the visual internet and social media platforms. This is particularly true in regard to videos obtained by smartphones, especially in rapidly emerging economies like India. ShareChat provides a safe and cultural community oriented space for users to generate and share content in their preferred Indian languages and dialects. Our subjective quality study, which is based on this data, offers a boost of cultural, visual, and language diversification to the video quality research community. We expect that this new data resource will also allow for the development of systems that can predict the perceived visual quality of Indian social media videos, to control scaling and compression protocols for streaming, provide better user recommendations, and guide content analysis and processing. We demonstrate the value of the new data resource by conducting a study of leading blind video quality models on it, including a new model, called MoEVA, which deploys a mixture of experts to predict video quality. Both the new LIVE-ShareChat dataset and sample source code for MoEVA are being made freely available to the research community at https://github.com/sandeep-sm/LIVE-SC
Authors: Yuta Okuyama, Yuki Endo, Yoshihiro Kanamori
Pose and body shape editing in a human image has received increasing attention. However, current methods often struggle with dataset biases and deteriorate realism and the person's identity when users make large edits. We propose a one-shot approach that enables large edits with identity preservation. To enable large edits, we fit a 3D body model, project the input image onto the 3D model, and change the body's pose and shape. Because this initial textured body model has artifacts due to occlusion and the inaccurate body shape, the rendered image undergoes a diffusion-based refinement, in which strong noise destroys body structure and identity whereas insufficient noise does not help. We thus propose an iterative refinement with weak noise, applied first for the whole body and then for the face. We further enhance the realism by fine-tuning text embeddings via self-supervised learning. Our quantitative and qualitative evaluations demonstrate that our method outperforms other existing methods across various datasets.
Authors: Junjie Wen, Yichen Zhu, Minjie Zhu, Jinming Li, Zhiyuan Xu, Zhengping Che, Chaomin Shen, Yaxin Peng, Dong Liu, Feifei Feng, Jian Tang
Humans interpret scenes by recognizing both the identities and positions of objects in their observations. For a robot to perform tasks such as \enquote{pick and place}, understanding both what the objects are and where they are located is crucial. While the former has been extensively discussed in the literature that uses the large language model to enrich the text descriptions, the latter remains underexplored. In this work, we introduce the \textit{Object-Centric Instruction Augmentation (OCI)} framework to augment highly semantic and information-dense language instruction with position cues. We utilize a Multi-modal Large Language Model (MLLM) to weave knowledge of object locations into natural language instruction, thus aiding the policy network in mastering actions for versatile manipulation. Additionally, we present a feature reuse mechanism to integrate the vision-language features from off-the-shelf pre-trained MLLM into policy networks. Through a series of simulated and real-world robotic tasks, we demonstrate that robotic manipulator imitation policies trained with our enhanced instructions outperform those relying solely on traditional language instructions.
Authors: Yabin Zhu, Xiao Wang, Chenglong Li, Bo Jiang, Lin Zhu, Zhixiang Huang, Yonghong Tian, Jin Tang
Existing datasets for RGB-DVS tracking are collected with DVS346 camera and their resolution ($346 \times 260$) is low for practical applications. Actually, only visible cameras are deployed in many practical systems, and the newly designed neuromorphic cameras may have different resolutions. The latest neuromorphic sensors can output high-definition event streams, but it is very difficult to achieve strict alignment between events and frames on both spatial and temporal views. Therefore, how to achieve accurate tracking with unaligned neuromorphic and visible sensors is a valuable but unresearched problem. In this work, we formally propose the task of object tracking using unaligned neuromorphic and visible cameras. We build the first unaligned frame-event dataset CRSOT collected with a specially built data acquisition system, which contains 1,030 high-definition RGB-Event video pairs, 304,974 video frames. In addition, we propose a novel unaligned object tracking framework that can realize robust tracking even using the loosely aligned RGB-Event data. Specifically, we extract the template and search regions of RGB and Event data and feed them into a unified ViT backbone for feature embedding. Then, we propose uncertainty perception modules to encode the RGB and Event features, respectively, then, we propose a modality uncertainty fusion module to aggregate the two modalities. These three branches are jointly optimized in the training phase. Extensive experiments demonstrate that our tracker can collaborate the dual modalities for high-performance tracking even without strictly temporal and spatial alignment. The source code, dataset, and pre-trained models will be released at https://github.com/Event-AHU/Cross_Resolution_SOT.
Authors: Wencong Wu, An Ge, Guannan Lv, Yuelong Xia, Yungang Zhang, Wen Xiong
Deep convolutional neural networks (CNNs) for image denoising can effectively exploit rich hierarchical features and have achieved great success. However, many deep CNN-based denoising models equally utilize the hierarchical features of noisy images without paying attention to the more important and useful features, leading to relatively low performance. To address the issue, we design a new Two-stage Progressive Residual Dense Attention Network (TSP-RDANet) for image denoising, which divides the whole process of denoising into two sub-tasks to remove noise progressively. Two different attention mechanism-based denoising networks are designed for the two sequential sub-tasks: the residual dense attention module (RDAM) is designed for the first stage, and the hybrid dilated residual dense attention module (HDRDAM) is proposed for the second stage. The proposed attention modules are able to learn appropriate local features through dense connection between different convolutional layers, and the irrelevant features can also be suppressed. The two sub-networks are then connected by a long skip connection to retain the shallow feature to enhance the denoising performance. The experiments on seven benchmark datasets have verified that compared with many state-of-the-art methods, the proposed TSP-RDANet can obtain favorable results both on synthetic and real noisy image denoising. The code of our TSP-RDANet is available at https://github.com/WenCongWu/TSP-RDANet.
Authors: Zijun Long, Richard McCreadie, Muhammad Imran
In times of emergency, crisis response agencies need to quickly and accurately assess the situation on the ground in order to deploy relevant services and resources. However, authorities often have to make decisions based on limited information, as data on affected regions can be scarce until local response services can provide first-hand reports. Fortunately, the widespread availability of smartphones with high-quality cameras has made citizen journalism through social media a valuable source of information for crisis responders. However, analyzing the large volume of images posted by citizens requires more time and effort than is typically available. To address this issue, this paper proposes the use of state-of-the-art deep neural models for automatic image classification/tagging, specifically by adapting transformer-based architectures for crisis image classification (CrisisViT). We leverage the new Incidents1M crisis image dataset to develop a range of new transformer-based image classification models. Through experimentation over the standard Crisis image benchmark dataset, we demonstrate that the CrisisViT models significantly outperform previous approaches in emergency type, image relevance, humanitarian category, and damage severity classification. Additionally, we show that the new Incidents1M dataset can further augment the CrisisViT models resulting in an additional 1.25% absolute accuracy gain.
Authors: Qi An, Mengshi Qi, Huadong Ma
In recent years, there has been growing interest in the video-based action quality assessment (AQA). Most existing methods typically solve AQA problem by considering the entire video yet overlooking the inherent stage-level characteristics of actions. To address this issue, we design a novel Multi-stage Contrastive Regression (MCoRe) framework for the AQA task. This approach allows us to efficiently extract spatial-temporal information, while simultaneously reducing computational costs by segmenting the input video into multiple stages or procedures. Inspired by the graph contrastive learning, we propose a new stage-wise contrastive learning loss function to enhance performance. As a result, MCoRe demonstrates the state-of-the-art result so far on the widely-adopted fine-grained AQA dataset.
Authors: Yang Zhou, Rongjun Xiao, Dani Lischinski, Daniel Cohen-Or, Hui Huang
This paper addresses the challenge of example-based non-stationary texture synthesis. We introduce a novel twostep approach wherein users first modify a reference texture using standard image editing tools, yielding an initial rough target for the synthesis. Subsequently, our proposed method, termed "self-rectification", automatically refines this target into a coherent, seamless texture, while faithfully preserving the distinct visual characteristics of the reference exemplar. Our method leverages a pre-trained diffusion network, and uses self-attention mechanisms, to gradually align the synthesized texture with the reference, ensuring the retention of the structures in the provided target. Through experimental validation, our approach exhibits exceptional proficiency in handling non-stationary textures, demonstrating significant advancements in texture synthesis when compared to existing state-of-the-art techniques. Code is available at https://github.com/xiaorongjun000/Self-Rectification
Authors: Marta Gomez-Barrero, Javier Galbally
With the widespread use of biometric recognition, several issues related to the privacy and security provided by this technology have been recently raised and analysed. As a result, the early common belief among the biometrics community of templates irreversibility has been proven wrong. It is now an accepted fact that it is possible to reconstruct from an unprotected template a synthetic sample that matches the bona fide one. This reverse engineering process, commonly referred to as \textit{inverse biometrics}, constitutes a severe threat for biometric systems from two different angles: on the one hand, sensitive personal data (i.e., biometric data) can be derived from compromised unprotected templates; on the other hand, other powerful attacks can be launched building upon these reconstructed samples. Given its important implications, biometric stakeholders have produced over the last fifteen years numerous works analysing the different aspects related to inverse biometrics: development of reconstruction algorithms for different characteristics; proposal of methodologies to assess the vulnerabilities of biometric systems to the aforementioned algorithms; development of countermeasures to reduce the possible effects of attacks. The present article is an effort to condense all this information in one comprehensive review of: the problem itself, the evaluation of the problem, and the mitigation of the problem. The present article is an effort to condense all this information in one comprehensive review of: the problem itself, the evaluation of the problem, and the mitigation of the problem.
Authors: Renjie Pi, Tianyang Han, Yueqi Xie, Rui Pan, Qing Lian, Hanze Dong, Jipeng Zhang, Tong Zhang
The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. We delve into the novel challenge of defending MLLMs against such attacks. We discovered that images act as a "foreign language" that is not considered during alignment, which can make MLLMs prone to producing harmful responses. Unfortunately, unlike the discrete tokens considered in text-based LLMs, the continuous nature of image signals presents significant alignment challenges, which poses difficulty to thoroughly cover the possible scenarios. This vulnerability is exacerbated by the fact that open-source MLLMs are predominantly fine-tuned on limited image-text pairs that is much less than the extensive text-based pretraining corpus, which makes the MLLMs more prone to catastrophic forgetting of their original abilities during explicit alignment tuning. To tackle these challenges, we introduce MLLM-Protector, a plug-and-play strategy combining a lightweight harm detector and a response detoxifier. The harm detector's role is to identify potentially harmful outputs from the MLLM, while the detoxifier corrects these outputs to ensure the response stipulates to the safety standards. This approach effectively mitigates the risks posed by malicious visual inputs without compromising the model's overall performance. Our results demonstrate that MLLM-Protector offers a robust solution to a previously unaddressed aspect of MLLM security.
Authors: Yuxin Yang, Pengfei Zhu, Mengshi Qi, Huadong Ma
Human trajectory forecasting is a critical challenge in fields such as robotics and autonomous driving. Due to the inherent uncertainty of human actions and intentions in real-world scenarios, various unexpected occurrences may arise. To uncover latent motion patterns in human behavior, we introduce a novel memory-based method, named Motion Pattern Priors Memory Network. Our method involves constructing a memory bank derived from clustered prior knowledge of motion patterns observed in the training set trajectories. We introduce an addressing mechanism to retrieve the matched pattern and the potential target distributions for each prediction from the memory bank, which enables the identification and retrieval of natural motion patterns exhibited by agents, subsequently using the target priors memory token to guide the diffusion model to generate predictions. Extensive experiments validate the effectiveness of our approach, achieving state-of-the-art trajectory prediction accuracy. The code will be made publicly available.
Authors: Jieru Mei, Liang-Chieh Chen, Alan Yuille, Cihang Xie
In this work, we introduce SPFormer, a novel Vision Transformer enhanced by superpixel representation. Addressing the limitations of traditional Vision Transformers' fixed-size, non-adaptive patch partitioning, SPFormer employs superpixels that adapt to the image's content. This approach divides the image into irregular, semantically coherent regions, effectively capturing intricate details and applicable at both initial and intermediate feature levels.
SPFormer, trainable end-to-end, exhibits superior performance across various benchmarks. Notably, it exhibits significant improvements on the challenging ImageNet benchmark, achieving a 1.4% increase over DeiT-T and 1.1% over DeiT-S respectively. A standout feature of SPFormer is its inherent explainability. The superpixel structure offers a window into the model's internal processes, providing valuable insights that enhance the model's interpretability. This level of clarity significantly improves SPFormer's robustness, particularly in challenging scenarios such as image rotations and occlusions, demonstrating its adaptability and resilience.
Authors: Michail Tarasiou, Rolandos Alexandros Potamias, Eimear O'Sullivan, Stylianos Ploumpis, Stefanos Zafeiriou
We present the Locally Adaptive Morphable Model (LAMM), a highly flexible Auto-Encoder (AE) framework for learning to generate and manipulate 3D meshes. We train our architecture following a simple self-supervised training scheme in which input displacements over a set of sparse control vertices are used to overwrite the encoded geometry in order to transform one training sample into another. During inference, our model produces a dense output that adheres locally to the specified sparse geometry while maintaining the overall appearance of the encoded object. This approach results in state-of-the-art performance in both disentangling manipulated geometry and 3D mesh reconstruction. To the best of our knowledge LAMM is the first end-to-end framework that enables direct local control of 3D vertex geometry in a single forward pass. A very efficient computational graph allows our network to train with only a fraction of the memory required by previous methods and run faster during inference, generating 12k vertex meshes at $>$60fps on a single CPU thread. We further leverage local geometry control as a primitive for higher level editing operations and present a set of derivative capabilities such as swapping and sampling object parts. Code and pretrained models can be found at https://github.com/michaeltrs/LAMM.
Authors: Navapat Nananukul, Hamid Soltanian-zadeh, Mohammad Rostami
Automatic semantic segmentation of magnetic resonance imaging (MRI) images using deep neural networks greatly assists in evaluating and planning treatments for various clinical applications. However, training these models is conditioned on the availability of abundant annotated data to implement the end-to-end supervised learning procedure. Even if we annotate enough data, MRI images display considerable variability due to factors such as differences in patients, MRI scanners, and imaging protocols. This variability necessitates retraining neural networks for each specific application domain, which, in turn, requires manual annotation by expert radiologists for all new domains. To relax the need for persistent data annotation, we develop a method for unsupervised federated domain adaptation using multiple annotated source domains. Our approach enables the transfer of knowledge from several annotated source domains to adapt a model for effective use in an unannotated target domain. Initially, we ensure that the target domain data shares similar representations with each source domain in a latent embedding space, modeled as the output of a deep encoder, by minimizing the pair-wise distances of the distributions for the target domain and the source domains. We then employ an ensemble approach to leverage the knowledge obtained from all domains. We provide theoretical analysis and perform experiments on the MICCAI 2016 multi-site dataset to demonstrate our method is effective.
Authors: Haobo Yuan, Xiangtai Li, Chong Zhou, Yining Li, Kai Chen, Chen Change Loy
The CLIP and Segment Anything Model (SAM) are remarkable vision foundation models (VFMs). SAM excels in segmentation tasks across diverse domains, while CLIP is renowned for its zero-shot recognition capabilities. This paper presents an in-depth exploration of integrating these two models into a unified framework. Specifically, we introduce the Open-Vocabulary SAM, a SAM-inspired model designed for simultaneous interactive segmentation and recognition, leveraging two unique knowledge transfer modules: SAM2CLIP and CLIP2SAM. The former adapts SAM's knowledge into the CLIP via distillation and learnable transformer adapters, while the latter transfers CLIP knowledge into SAM, enhancing its recognition capabilities. Extensive experiments on various datasets and detectors show the effectiveness of Open-Vocabulary SAM in both segmentation and recognition tasks, significantly outperforming the naive baselines of simply combining SAM and CLIP. Furthermore, aided with image classification data training, our method can segment and recognize approximately 22,000 classes.
Authors: Jiawei Yang, Katie Z Luo, Jiefeng Li, Kilian Q Weinberger, Yonglong Tian, Yue Wang
We delve into a nuanced but significant challenge inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which detrimentally hurt the performance of ViTs in downstream tasks. Our investigations trace this fundamental issue down to the positional embeddings at the input stage. To address this, we propose a novel noise model, which is universally applicable to all ViTs. Specifically, the noise model dissects ViT outputs into three components: a semantics term free from noise artifacts and two artifact-related terms that are conditioned on pixel locations. Such a decomposition is achieved by enforcing cross-view feature consistency with neural fields in a per-image basis. This per-image optimization process extracts artifact-free features from raw ViT outputs, providing clean features for offline applications. Expanding the scope of our solution to support online functionality, we introduce a learnable denoiser to predict artifact-free features directly from unprocessed ViT outputs, which shows remarkable generalization capabilities to novel data without the need for per-image optimization. Our two-stage approach, termed Denoising Vision Transformers (DVT), does not require re-training existing pre-trained ViTs and is immediately applicable to any Transformer-based architecture. We evaluate our method on a variety of representative ViTs (DINO, MAE, DeiT-III, EVA02, CLIP, DINOv2, DINOv2-reg). Extensive evaluations demonstrate that our DVT consistently and significantly improves existing state-of-the-art general-purpose models in semantic and geometric tasks across multiple datasets (e.g., +3.84 mIoU). We hope our study will encourage a re-evaluation of ViT design, especially regarding the naive use of positional embeddings.
Authors: Sean I. Young, Adrian V. Dalca, Enzo Ferrante, Polina Golland, Christopher A. Metzler, Bruce Fischl, Juan Eugenio Iglesias
Learning-based image reconstruction models, such as those based on the U-Net, require a large set of labeled images if good generalization is to be guaranteed. In some imaging domains, however, labeled data with pixel- or voxel-level label accuracy are scarce due to the cost of acquiring them. This problem is exacerbated further in domains like medical imaging, where there is no single ground truth label, resulting in large amounts of repeat variability in the labels. Therefore, training reconstruction networks to generalize better by learning from both labeled and unlabeled examples (called semi-supervised learning) is problem of practical and theoretical interest. However, traditional semi-supervised learning methods for image reconstruction often necessitate handcrafting a differentiable regularizer specific to some given imaging problem, which can be extremely time-consuming. In this work, we propose "supervision by denoising" (SUD), a framework that enables us to supervise reconstruction models using their own denoised output as soft labels. SUD unifies stochastic averaging and spatial denoising techniques under a spatio-temporal denoising framework and alternates denoising and model weight update steps in an optimization framework for semi-supervision. As example applications, we apply SUD to two problems arising from biomedical imaging -- anatomical brain reconstruction (3D) and cortical parcellation (2D) -- to demonstrate a significant improvement in the image reconstructions over supervised-only and stochastic averaging baselines.
Authors: Ranran Huang, Jiancheng Cai, Chao Li, Zhuoyuan Wu, Xinmin Liu, Zhenhua Chai
The performance of local feature descriptors degrades in the presence of large rotation variations. To address this issue, we present an efficient approach to learning rotation invariant descriptors. Specifically, we propose Rotated Kernel Fusion (RKF) which imposes rotations on the convolution kernel to improve the inherent nature of CNN. Since RKF can be processed by the subsequent re-parameterization, no extra computational costs will be introduced in the inference stage. Moreover, we present Multi-oriented Feature Aggregation (MOFA) which aggregates features extracted from multiple rotated versions of the input image and can provide auxiliary knowledge for the training of RKF by leveraging the distillation strategy. We refer to the distilled RKF model as DRKF. Besides the evaluation on a rotation-augmented version of the public dataset HPatches, we also contribute a new dataset named DiverseBEV which is collected during the drone's flight and consists of bird's eye view images with large viewpoint changes and camera rotations. Extensive experiments show that our method can outperform other state-of-the-art techniques when exposed to large rotation variations.
Authors: Andong Deng, Taojiannan Yang, Chen Chen, Qian Chen, Leslie Neely, Sakiko Oyama
Correctly recognizing the behaviors of children with Autism Spectrum Disorder (ASD) is of vital importance for the diagnosis of Autism and timely early intervention. However, the observation and recording during the treatment from the parents of autistic children may not be accurate and objective. In such cases, automatic recognition systems based on computer vision and machine learning (in particular deep learning) technology can alleviate this issue to a large extent. Existing human action recognition models can now achieve persuasive performance on challenging activity datasets, e.g. daily activity, and sports activity. However, problem behaviors in children with ASD are very different from these general activities, and recognizing these problem behaviors via computer vision is less studied. In this paper, we first evaluate a strong baseline for action recognition, i.e. Video Swin Transformer, on two autism behaviors datasets (SSBD and ESBD) and show that it can achieve high accuracy and outperform the previous methods by a large margin, demonstrating the feasibility of vision-based problem behaviors recognition. Moreover, we propose language-assisted training to further enhance the action recognition performance. Specifically, we develop a two-branch multimodal deep learning framework by incorporating the "freely available" language description for each type of problem behavior. Experimental results demonstrate that incorporating additional language supervision can bring an obvious performance boost for the autism problem behaviors recognition task as compared to using the video information only (i.e. 3.49% improvement on ESBD and 1.46% on SSBD).
Authors: Yunjie Tian, Lingxi Xie, Jihao Qiu, Jianbin Jiao, Yaowei Wang, Qi Tian, Qixiang Ye
We propose integrally pre-trained transformer pyramid network (iTPN), towards jointly optimizing the network backbone and the neck, so that transfer gap between representation models and downstream tasks is minimal. iTPN is born with two elaborated designs: 1) The first pre-trained feature pyramid upon vision transformer (ViT). 2) Multi-stage supervision to the feature pyramid using masked feature modeling (MFM). iTPN is updated to Fast-iTPN, reducing computational memory overhead and accelerating inference through two flexible designs. 1) Token migration: dropping redundant tokens of the backbone while replenishing them in the feature pyramid without attention operations. 2) Token gathering: reducing computation cost caused by global attention by introducing few gathering tokens. The base/large-level Fast-iTPN achieve 88.75%/89.5% top-1 accuracy on ImageNet-1K. With 1x training schedule using DINO, the base/large-level Fast-iTPN achieves 58.4%/58.8% box AP on COCO object detection, and a 57.5%/58.7% mIoU on ADE20K semantic segmentation using MaskDINO. Fast-iTPN can accelerate the inference procedure by up to 70%, with negligible performance loss, demonstrating the potential to be a powerful backbone for downstream vision tasks. The code is available at: github.com/sunsmarterjie/iTPN.
Authors: Pranav Kulkarni, Adway Kanhere, Paul H. Yi, Vishwa S. Parekh
The release of numerous chest x-ray datasets has spearheaded the development of deep learning models with expert-level performance. However, they have limited interoperability due to class-heterogeneity -- a result of inconsistent labeling schemes and partial annotations. Therefore, it is challenging to leverage these datasets in aggregate to train models with a complete representation of abnormalities that may occur within the thorax. In this work, we propose surgical aggregation, a federated learning framework for aggregating knowledge from class-heterogeneous datasets and learn a model that can simultaneously predict the presence of all disease labels present across the datasets. We evaluate our method using simulated and real-world class-heterogeneous datasets across both independent and identically distributed (iid) and non-iid settings. Our results show that surgical aggregation outperforms current methods, has better generalizability, and is a crucial first step towards tackling class-heterogeneity in federated learning to facilitate the development of clinically-useful models using previously non-interoperable chest x-ray datasets.
Authors: Junkai Fan, Fei Guo, Jianjun Qian, Xiang Li, Jun Li, Jian Yang
Removing haze from real-world images is challenging due to unpredictable weather conditions, resulting in the misalignment of hazy and clear image pairs. In this paper, we propose an innovative dehazing framework that operates under non-aligned supervision. This framework is grounded in the atmospheric scattering model, and consists of three interconnected networks: dehazing, airlight, and transmission networks. In particular, we explore a non-alignment scenario that a clear reference image, unaligned with the input hazy image, is utilized to supervise the dehazing network. To implement this, we present a multi-scale reference loss that compares the feature representations between the referred image and the dehazed output. Our scenario makes it easier to collect hazy/clear image pairs in real-world environments, even under conditions of misalignment and shift views. To showcase the effectiveness of our scenario, we have collected a new hazy dataset including 415 image pairs captured by mobile Phone in both rural and urban areas, called "Phone-Hazy". Furthermore, we introduce a self-attention network based on mean and variance for modeling real infinite airlight, using the dark channel prior as positional guidance. Additionally, a channel attention network is employed to estimate the three-channel transmission. Experimental results demonstrate the superior performance of our framework over existing state-of-the-art techniques in the real-world image dehazing task. Phone-Hazy and code will be available at https://fanjunkai1.github.io/projectpage/NSDNet/index.html.
Authors: Julian McGinnis, Suprosanna Shit, Hongwei Bran Li, Vasiliki Sideri-Lampretsa, Robert Graf, Maik Dannecker, Jiazhen Pan, Nil Stolt Ansó, Mark Mühlau, Jan S. Kirschke, Daniel Rueckert, Benedikt Wiestler
Clinical routine and retrospective cohorts commonly include multi-parametric Magnetic Resonance Imaging; however, they are mostly acquired in different anisotropic 2D views due to signal-to-noise-ratio and scan-time constraints. Thus acquired views suffer from poor out-of-plane resolution and affect downstream volumetric image analysis that typically requires isotropic 3D scans. Combining different views of multi-contrast scans into high-resolution isotropic 3D scans is challenging due to the lack of a large training cohort, which calls for a subject-specific framework. This work proposes a novel solution to this problem leveraging Implicit Neural Representations (INR). Our proposed INR jointly learns two different contrasts of complementary views in a continuous spatial function and benefits from exchanging anatomical information between them. Trained within minutes on a single commodity GPU, our model provides realistic super-resolution across different pairs of contrasts in our experiments with three datasets. Using Mutual Information (MI) as a metric, we find that our model converges to an optimum MI amongst sequences, achieving anatomically faithful reconstruction. Code is available at: https://github.com/jqmcginnis/multi_contrast_inr/
Authors: Jian Sun, Hiroko H. Dodge, Mohammad H. Mahoor
Deep machine learning models including Convolutional Neural Networks (CNN) have been successful in the detection of Mild Cognitive Impairment (MCI) using medical images, questionnaires, and videos. This paper proposes a novel Multi-branch Classifier-Video Vision Transformer (MC-ViViT) model to distinguish MCI from those with normal cognition by analyzing facial features. The data comes from the I-CONECT, a behavioral intervention trial aimed at improving cognitive function by providing frequent video chats. MC-ViViT extracts spatiotemporal features of videos in one branch and augments representations by the MC module. The I-CONECT dataset is challenging as the dataset is imbalanced containing Hard-Easy and Positive-Negative samples, which impedes the performance of MC-ViViT. We propose a loss function for Hard-Easy and Positive-Negative Samples (HP Loss) by combining Focal loss and AD-CORRE loss to address the imbalanced problem. Our experimental results on the I-CONECT dataset show the great potential of MC-ViViT in predicting MCI with a high accuracy of 90.63% accuracy on some of the interview videos.
Authors: Koushik Sivarama Krishnan, P. J. Joe Nikesh, Swathi Gnanasekar, Karthik Sivarama Krishnan
An innovative two-stage methodology for categorizing blood clot origins is presented in this paper, which is important for the diagnosis and treatment of ischemic stroke. First, a background classifier based on MobileNetV3 segments big whole-slide digital pathology images into numerous tiles to detect the presence of cellular material. After that, different pre-trained image classification algorithms are fine-tuned to determine the origin of blood clots. Due to complex blood flow dynamics and limitations in conventional imaging methods such as computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound, identifying the sources of blood clots is a challenging task. Although these techniques are useful for identifying blood clots, they are not very good at determining how they originated. To address these challenges, our method makes use of robust computer vision models that have been refined using information from whole-slide digital pathology images. Out of all the models tested, the PoolFormer \cite{yu2022metaformer} performs better than the others, with 93.4\% accuracy, 93.4\% precision, 93.4\% recall, and 93.4\% F1-score. Moreover, it achieves the good weighted multi-class logarithmic loss (WMCLL) of 0.4361, which emphasizes how effective it is in this particular application. These encouraging findings suggest that our approach can successfully identify the origin of blood clots in a variety of vascular locations, potentially advancing ischemic stroke diagnosis and treatment approaches.
Authors: De Cheng, Xiaojian Huang, Nannan Wang, Lingfeng He, Zhihui Li, Xinbo Gao
Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims at learning modality-invariant features from unlabeled cross-modality dataset, which is crucial for practical applications in video surveillance systems. The key to essentially address the USL-VI-ReID task is to solve the cross-modality data association problem for further heterogeneous joint learning. To address this issue, we propose a Dual Optimal Transport Label Assignment (DOTLA) framework to simultaneously assign the generated labels from one modality to its counterpart modality. The proposed DOTLA mechanism formulates a mutual reinforcement and efficient solution to cross-modality data association, which could effectively reduce the side-effects of some insufficient and noisy label associations. Besides, we further propose a cross-modality neighbor consistency guided label refinement and regularization module, to eliminate the negative effects brought by the inaccurate supervised signals, under the assumption that the prediction or label distribution of each example should be similar to its nearest neighbors. Extensive experimental results on the public SYSU-MM01 and RegDB datasets demonstrate the effectiveness of the proposed method, surpassing existing state-of-the-art approach by a large margin of 7.76% mAP on average, which even surpasses some supervised VI-ReID methods.
Authors: Kevin Black, Michael Janner, Yilun Du, Ilya Kostrikov, Sergey Levine
Diffusion models are a class of flexible generative models trained with an approximation to the log-likelihood objective. However, most use cases of diffusion models are not concerned with likelihoods, but instead with downstream objectives such as human-perceived image quality or drug effectiveness. In this paper, we investigate reinforcement learning methods for directly optimizing diffusion models for such objectives. We describe how posing denoising as a multi-step decision-making problem enables a class of policy gradient algorithms, which we refer to as denoising diffusion policy optimization (DDPO), that are more effective than alternative reward-weighted likelihood approaches. Empirically, DDPO is able to adapt text-to-image diffusion models to objectives that are difficult to express via prompting, such as image compressibility, and those derived from human feedback, such as aesthetic quality. Finally, we show that DDPO can improve prompt-image alignment using feedback from a vision-language model without the need for additional data collection or human annotation. The project's website can be found at this http URL .
Authors: Xianwei Lv, Claudio Persello, Wangbin Li, Xiao Huang, Dongping Ming, Alfred Stein
Image segmentation aims to partition an image according to the objects in the scene and is a fundamental step in analysing very high spatial-resolution (VHR) remote sensing imagery. Current methods struggle to effectively consider land objects with diverse shapes and sizes. Additionally, the determination of segmentation scale parameters frequently adheres to a static and empirical doctrine, posing limitations on the segmentation of large-scale remote sensing images and yielding algorithms with limited interpretability. To address the above challenges, we propose a deep-learning-based region merging method dubbed DeepMerge to handle the segmentation of complete objects in large VHR images by integrating deep learning and region adjacency graph (RAG). This is the first method to use deep learning to learn the similarity and merge similar adjacent super-pixels in RAG. We propose a modified binary tree sampling method to generate shift-scale data, serving as inputs for transformer-based deep learning networks, a shift-scale attention with 3-Dimension relative position embedding to learn features across scales, and an embedding to fuse learned features with hand-crafted features. DeepMerge can achieve high segmentation accuracy in a supervised manner from large-scale remotely sensed images and provides an interpretable optimal scale parameter, which is validated using a remote sensing image of 0.55 m resolution covering an area of 5,660 km^2. The experimental results show that DeepMerge achieves the highest F value (0.9550) and the lowest total error TE (0.0895), correctly segmenting objects of different sizes and outperforming all competing segmentation methods.
Authors: Muhammad Usman Akbar, Måns Larsson, Anders Eklund
Large annotated datasets are required for training deep learning models, but in medical imaging data sharing is often complicated due to ethics, anonymization and data protection legislation. Generative AI models, such as generative adversarial networks (GANs) and diffusion models, can today produce very realistic synthetic images, and can potentially facilitate data sharing. However, in order to share synthetic medical images it must first be demonstrated that they can be used for training different networks with acceptable performance. Here, we therefore comprehensively evaluate four GANs (progressive GAN, StyleGAN 1-3) and a diffusion model for the task of brain tumor segmentation (using two segmentation networks, U-Net and a Swin transformer). Our results show that segmentation networks trained on synthetic images reach Dice scores that are 80% - 90% of Dice scores when training with real images, but that memorization of the training images can be a problem for diffusion models if the original dataset is too small. Our conclusion is that sharing synthetic medical images is a viable option to sharing real images, but that further work is required. The trained generative models and the generated synthetic images are shared on AIDA data hub
Authors: Haoran Zhang, Jianlong Yang, Jingqian Zhang, Shiqing Zhao, Aili Zhang
Nonuniform rotational distortion (NURD) correction is vital for endoscopic optical coherence tomography (OCT) imaging and its functional extensions, such as angiography and elastography. Current NURD correction methods require time-consuming feature tracking or cross-correlation calculations and thus sacrifice temporal resolution. Here we propose a cross-attention learning method for the NURD correction in OCT. Our method is inspired by the recent success of the self-attention mechanism in natural language processing and computer vision. By leveraging its ability to model long-range dependencies, we can directly obtain the correlation between OCT A-lines at any distance, thus accelerating the NURD correction. We develop an end-to-end stacked cross-attention network and design three types of optimization constraints. We compare our method with two traditional feature-based methods and a CNN-based method, on two publicly-available endoscopic OCT datasets and a private dataset collected on our home-built endoscopic OCT system. Our method achieved a $\sim3\times$ speedup to real time ($26\pm 3$ fps), and superior correction performance.
Authors: Duy-Kien Nguyen, Vaibhav Aggarwal, Yanghao Li, Martin R. Oswald, Alexander Kirillov, Cees G. M. Snoek, Xinlei Chen
In this work, we explore regions as a potential visual analogue of words for self-supervised image representation learning. Inspired by Masked Autoencoding (MAE), a generative pre-training baseline, we propose masked region autoencoding to learn from groups of pixels or regions. Specifically, we design an architecture which efficiently addresses the one-to-many mapping between images and regions, while being highly effective especially with high-quality regions. When integrated with MAE, our approach (R-MAE) demonstrates consistent improvements across various pre-training datasets and downstream detection and segmentation benchmarks, with negligible computational overheads. Beyond the quantitative evaluation, our analysis indicates the models pre-trained with masked region autoencoding unlock the potential for interactive segmentation. The code is provided at https://github.com/facebookresearch/r-mae.
Authors: Md Zahid Hasan, Jiajing Chen, Jiyang Wang, Mohammed Shaiqur Rahman, Ameya Joshi, Senem Velipasalar, Chinmay Hegde, Anuj Sharma, Soumik Sarkar
Recognizing the activities causing distraction in real-world driving scenarios is critical for ensuring the safety and reliability of both drivers and pedestrians on the roadways. Conventional computer vision techniques are typically data-intensive and require a large volume of annotated training data to detect and classify various distracted driving behaviors, thereby limiting their efficiency and scalability. We aim to develop a generalized framework that showcases robust performance with access to limited or no annotated training data. Recently, vision-language models have offered large-scale visual-textual pretraining that can be adapted to task-specific learning like distracted driving activity recognition. Vision-language pretraining models, such as CLIP, have shown significant promise in learning natural language-guided visual representations. This paper proposes a CLIP-based driver activity recognition approach that identifies driver distraction from naturalistic driving images and videos. CLIP's vision embedding offers zero-shot transfer and task-based finetuning, which can classify distracted activities from driving video data. Our results show that this framework offers state-of-the-art performance on zero-shot transfer and video-based CLIP for predicting the driver's state on two public datasets. We propose both frame-based and video-based frameworks developed on top of the CLIP's visual representation for distracted driving detection and classification tasks and report the results.
Authors: Helen H. Shang, Mohammad Sadegh Nasr, Jai Prakash Veerla, Parisa Boodaghi Malidarreh, MD Jillur Rahman Saurav, Amir Hajighasemi, Manfred Huber, Chace Moleta, Jitin Makker, Jacob M. Luber
The search and retrieval of digital histopathology slides is an important task that has yet to be solved. In this case study, we investigate the clinical readiness of three state-of-the-art histopathology slide search engines, Yottixel, SISH, and RetCCL, on three patients with solid tumors. We provide a qualitative assessment of each model's performance in providing retrieval results that are reliable and useful to pathologists. We found that all three image search engines fail to produce consistently reliable results and have difficulties in capturing granular and subtle features of malignancy, limiting their diagnostic accuracy. Based on our findings, we also propose a minimal set of requirements to further advance the development of accurate and reliable histopathology image search engines for successful clinical adoption.
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: Weichao Zhao, Hezhen Hu, Wengang Zhou, Li li, Houqiang Li
Reconstructing interacting hands from monocular RGB data is a challenging task, as it involves many interfering factors, e.g. self- and mutual occlusion and similar textures. Previous works only leverage information from a single RGB image without modeling their physically plausible relation, which leads to inferior reconstruction results. In this work, we are dedicated to explicitly exploiting spatial-temporal information to achieve better interacting hand reconstruction. On one hand, we leverage temporal context to complement insufficient information provided by the single frame, and design a novel temporal framework with a temporal constraint for interacting hand motion smoothness. On the other hand, we further propose an interpenetration detection module to produce kinetically plausible interacting hands without physical collisions. Extensive experiments are performed to validate the effectiveness of our proposed framework, which achieves new state-of-the-art performance on public benchmarks.
Authors: Soroosh Tayebi Arasteh, Leo Misera, Jakob Nikolas Kather, Daniel Truhn, Sven Nebelung
Pre-training datasets, like ImageNet, have become the gold standard in medical image analysis. However, the emergence of self-supervised learning (SSL), which leverages unlabeled data to learn robust features, presents an opportunity to bypass the intensive labeling process. In this study, we explored if SSL for pre-training on non-medical images can be applied to chest radiographs and how it compares to supervised pre-training on non-medical images and on medical images. We utilized a vision transformer and initialized its weights based on (i) SSL pre-training on natural images (DINOv2), (ii) SL pre-training on natural images (ImageNet dataset), and (iii) SL pre-training on chest radiographs from the MIMIC-CXR database. We tested our approach on over 800,000 chest radiographs from six large global datasets, diagnosing more than 20 different imaging findings. Our SSL pre-training on curated images not only outperformed ImageNet-based pre-training (P<0.001 for all datasets) but, in certain cases, also exceeded SL on the MIMIC-CXR dataset. Our findings suggest that selecting the right pre-training strategy, especially with SSL, can be pivotal for improving artificial intelligence (AI)'s diagnostic accuracy in medical imaging. By demonstrating the promise of SSL in chest radiograph analysis, we underline a transformative shift towards more efficient and accurate AI models in medical imaging.
Authors: Seokhyeon Ha, Sunbeom Jung, Jungwoo Lee
Fine-tuning pre-trained neural network models has become a widely adopted approach across various domains. However, it can lead to the distortion of pre-trained feature extractors that already possess strong generalization capabilities. Mitigating feature distortion during adaptation to new target domains is crucial. Recent studies have shown promising results in handling feature distortion by aligning the head layer on in-distribution datasets before performing fine-tuning. Nonetheless, a significant limitation arises from the treatment of batch normalization layers during fine-tuning, leading to suboptimal performance. In this paper, we propose Domain-Aware Fine-Tuning (DAFT), a novel approach that incorporates batch normalization conversion and the integration of linear probing and fine-tuning. Our batch normalization conversion method effectively mitigates feature distortion by reducing modifications to the neural network during fine-tuning. Additionally, we introduce the integration of linear probing and fine-tuning to optimize the head layer with gradual adaptation of the feature extractor. By leveraging batch normalization layers and integrating linear probing and fine-tuning, our DAFT significantly mitigates feature distortion and achieves improved model performance on both in-distribution and out-of-distribution datasets. Extensive experiments demonstrate that our method outperforms other baseline methods, demonstrating its effectiveness in not only improving performance but also mitigating feature distortion.
Authors: Ziyan Yang, Kushal Kafle, Zhe Lin, Scott Cohen, Zhihong Ding, Vicente Ordonez
We propose Subject-Conditional Relation Detection SCoRD, where conditioned on an input subject, the goal is to predict all its relations to other objects in a scene along with their locations. Based on the Open Images dataset, we propose a challenging OIv6-SCoRD benchmark such that the training and testing splits have a distribution shift in terms of the occurrence statistics of $\langle$subject, relation, object$\rangle$ triplets. To solve this problem, we propose an auto-regressive model that given a subject, it predicts its relations, objects, and object locations by casting this output as a sequence of tokens. First, we show that previous scene-graph prediction methods fail to produce as exhaustive an enumeration of relation-object pairs when conditioned on a subject on this benchmark. Particularly, we obtain a recall@3 of 83.8% for our relation-object predictions compared to the 49.75% obtained by a recent scene graph detector. Then, we show improved generalization on both relation-object and object-box predictions by leveraging during training relation-object pairs obtained automatically from textual captions and for which no object-box annotations are available. Particularly, for $\langle$subject, relation, object$\rangle$ triplets for which no object locations are available during training, we are able to obtain a recall@3 of 33.80% for relation-object pairs and 26.75% for their box locations.
Authors: Marek Rychlik, Bekir Tanriover, Yan Han
In this paper we focus on three major task: 1) discussing our methods: Our method captures a portion of the data in DCD flowsheets, kidney perfusion data, and Flowsheet data captured peri-organ recovery surgery. 2) demonstrating the result: We built a comprehensive, analyzable database from 2022 OPTN data. This dataset is by far larger than any previously available even in this preliminary phase; and 3) proving that our methods can be extended to all the past OPTN data and future data.
The scope of our study is all Organ Procurement and Transplantation Network (OPTN) data of the USA organ donors since 2008. The data was not analyzable in a large scale in the past because it was captured in PDF documents known as ``Attachments'', whereby every donor's information was recorded into dozens of PDF documents in heterogeneous formats. To make the data analyzable, one needs to convert the content inside these PDFs to an analyzable data format, such as a standard SQL database. In this paper we will focus on 2022 OPTN data, which consists of $\approx 400,000$ PDF documents spanning millions of pages. The entire OPTN data covers 15 years (2008--20022). This paper assumes that readers are familiar with the content of the OPTN data.
Authors: Xuan Liu, Yaoqin Xie, Songhui Diao, Shan Tan, Xiaokun Liang
During the process of computed tomography (CT), metallic implants often cause disruptive artifacts in the reconstructed images, impeding accurate diagnosis. Several supervised deep learning-based approaches have been proposed for reducing metal artifacts (MAR). However, these methods heavily rely on training with simulated data, as obtaining paired metal artifact CT and clean CT data in clinical settings is challenging. This limitation can lead to decreased performance when applying these methods in clinical practice. Existing unsupervised MAR methods, whether based on learning or not, typically operate within a single domain, either in the image domain or the sinogram domain. In this paper, we propose an unsupervised MAR method based on the diffusion model, a generative model with a high capacity to represent data distributions. Specifically, we first train a diffusion model using CT images without metal artifacts. Subsequently, we iteratively utilize the priors embedded within the pre-trained diffusion model in both the sinogram and image domains to restore the degraded portions caused by metal artifacts. This dual-domain processing empowers our approach to outperform existing unsupervised MAR methods, including another MAR method based on the diffusion model, which we have qualitatively and quantitatively validated using synthetic datasets. Moreover, our method demonstrates superior visual results compared to both supervised and unsupervised methods on clinical datasets.
Authors: Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu
Contrastive learning has emerged as a prevailing paradigm for high-level vision tasks, which, by introducing properly negative samples, has also been exploited for low-level vision tasks to achieve a compact optimization space to account for their ill-posed nature. However, existing methods rely on manually predefined and task-oriented negatives, which often exhibit pronounced task-specific biases. To address this challenge, our paper introduces an innovative method termed 'learning from history', which dynamically generates negative samples from the target model itself. Our approach, named Model Contrastive paradigm for Image Restoration (MCIR), rejuvenates latency models as negative models, making it compatible with diverse image restoration tasks. We propose the Self-Prior guided Negative loss (SPN) to enable it. This approach significantly enhances existing models when retrained with the proposed model contrastive paradigm. The results show significant improvements in image restoration across various tasks and architectures. For example, models retrained with SPN outperform the original FFANet and DehazeFormer by 3.41 dB and 0.57 dB on the RESIDE indoor dataset for image dehazing. Similarly, they achieve notable improvements of 0.47 dB on SPA-Data over IDT for image deraining and 0.12 dB on Manga109 for a 4x scale super-resolution over lightweight SwinIR, respectively. Code and retrained models are available at https://github.com/Aitical/MCIR.
Authors: Jonathan Henrich, Jan van Delden, Dominik Seidel, Thomas Kneib, Alexander Ecker
Laser-scanned point clouds of forests make it possible to extract valuable information for forest management. To consider single trees, a forest point cloud needs to be segmented into individual tree point clouds. Existing segmentation methods are usually based on hand-crafted algorithms, such as identifying trunks and growing trees from them, and face difficulties in dense forests with overlapping tree crowns. In this study, we propose TreeLearn, a deep learning-based approach for tree instance segmentation of forest point clouds. Unlike previous methods, TreeLearn is trained on already segmented point clouds in a data-driven manner, making it less reliant on predefined features and algorithms. Furthermore, TreeLearn is implemented as a fully automatic pipeline and does not rely on extensive hyperparameter tuning, which makes it easy to use. Additionally, we introduce a new manually segmented benchmark forest dataset containing 156 full trees, and 79 partial trees, that have been cleanly segmented by hand. The data is generated by mobile laser scanning and contributes to create a larger and more diverse data basis for model development and fine-grained instance segmentation evaluation. We trained TreeLearn on forest point clouds of 6665 trees, labeled using the Lidar360 software. An evaluation on the benchmark dataset shows that TreeLearn performs equally well or better than the algorithm used to generate its training data. Furthermore, the method's performance can be vastly improved by fine-tuning on the cleanly labeled benchmark dataset. The TreeLearn code is available from https://github.com/ecker-lab/TreeLearn. The data as well as trained models can be found at https://doi.org/10.25625/VPMPID.
Authors: Xiang Gao, Hainan Cui, Shuhan Shen
In order to further advance the accuracy and robustness of the incremental parameter estimation-based rotation averaging methods, in this paper, a new member of the Incremental Rotation Averaging (IRA) family is introduced, which is termed as IRAv4. As the most significant feature of the IRAv4, a task-specific connected dominating set is extracted to serve as a more reliable and accurate reference for rotation global alignment. In addition, to further address the limitations of the existing rotation averaging benchmark of relying on the slightly outdated Bundler camera calibration results as ground truths and focusing solely on rotation estimation accuracy, this paper presents a new COLMAP-based rotation averaging benchmark that incorporates a cross check between COLMAP and Bundler, and employ the accuracy of both rotation and downstream location estimation as evaluation metrics, which is desired to provide a more reliable and comprehensive evaluation tool for the rotation averaging research. Comprehensive comparisons between the proposed IRAv4 and other mainstream rotation averaging methods on this new benchmark demonstrate the effectiveness of our proposed approach.
Authors: Elvis Nunez, Yanzi Jin, Mohammad Rastegari, Sachin Mehta, Maxwell Horton
Over the past several years, the synchronization between audio and visual signals has been leveraged to learn richer audio-visual representations. Aided by the large availability of unlabeled videos, many unsupervised training frameworks have demonstrated impressive results in various downstream audio and video tasks. Recently, Masked Audio-Video Learners (MAViL) has emerged as a state-of-the-art audio-video pre-training framework. MAViL couples contrastive learning with masked autoencoding to jointly reconstruct audio spectrograms and video frames by fusing information from both modalities. In this paper, we study the potential synergy between diffusion models and MAViL, seeking to derive mutual benefits from these two frameworks. The incorporation of diffusion into MAViL, combined with various training efficiency methodologies that include the utilization of a masking ratio curriculum and adaptive batch sizing, results in a notable 32% reduction in pre-training Floating-Point Operations (FLOPS) and an 18% decrease in pre-training wall clock time. Crucially, this enhanced efficiency does not compromise the model's performance in downstream audio-classification tasks when compared to MAViL's performance.
Authors: Yan Scholten, Jan Schuchardt, Aleksandar Bojchevski, Stephan Günnemann
Real-world data is complex and often consists of objects that can be decomposed into multiple entities (e.g. images into pixels, graphs into interconnected nodes). Randomized smoothing is a powerful framework for making models provably robust against small changes to their inputs - by guaranteeing robustness of the majority vote when randomly adding noise before classification. Yet, certifying robustness on such complex data via randomized smoothing is challenging when adversaries do not arbitrarily perturb entire objects (e.g. images) but only a subset of their entities (e.g. pixels). As a solution, we introduce hierarchical randomized smoothing: We partially smooth objects by adding random noise only on a randomly selected subset of their entities. By adding noise in a more targeted manner than existing methods we obtain stronger robustness guarantees while maintaining high accuracy. We initialize hierarchical smoothing using different noising distributions, yielding novel robustness certificates for discrete and continuous domains. We experimentally demonstrate the importance of hierarchical smoothing in image and node classification, where it yields superior robustness-accuracy trade-offs. Overall, hierarchical smoothing is an important contribution towards models that are both - certifiably robust to perturbations and accurate.
Authors: Fabiha Bushra, Muhammad E. H. Chowdhury, Rusab Sarmun, Saidul Kabir, Menatalla Said, Sohaib Bassam Zoghoul, Adam Mushtak, Israa Al-Hashimi, Abdulrahman Alqahtani, Anwarul Hasan
The increasing reliance on Computed Tomography Pulmonary Angiography (CTPA) for Pulmonary Embolism (PE) diagnosis presents challenges and a pressing need for improved diagnostic solutions. The primary objective of this study is to leverage deep learning techniques to enhance the Computer Assisted Diagnosis (CAD) of PE. With this aim, we propose a classifier-guided detection approach that effectively leverages the classifier's probabilistic inference to direct the detection predictions, marking a novel contribution in the domain of automated PE diagnosis. Our classification system includes an Attention-Guided Convolutional Neural Network (AG-CNN) that uses local context by employing an attention mechanism. This approach emulates a human expert's attention by looking at both global appearances and local lesion regions before making a decision. The classifier demonstrates robust performance on the FUMPE dataset, achieving an AUROC of 0.927, sensitivity of 0.862, specificity of 0.879, and an F1-score of 0.805 with the Inception-v3 backbone architecture. Moreover, AG-CNN outperforms the baseline DenseNet-121 model, achieving an 8.1% AUROC gain. While previous research has mostly focused on finding PE in the main arteries, our use of cutting-edge object detection models and ensembling techniques greatly improves the accuracy of detecting small embolisms in the peripheral arteries. Finally, our proposed classifier-guided detection approach further refines the detection metrics, contributing new state-of-the-art to the community: mAP$_{50}$, sensitivity, and F1-score of 0.846, 0.901, and 0.779, respectively, outperforming the former benchmark with a significant 3.7% improvement in mAP$_{50}$. Our research aims to elevate PE patient care by integrating AI solutions into clinical workflows, highlighting the potential of human-AI collaboration in medical diagnostics.
Authors: Kirill Vishniakov, Zhiqiang Shen, Zhuang Liu
Modern computer vision offers a great variety of models to practitioners, and selecting a model from multiple options for specific applications can be challenging. Conventionally, competing model architectures and training protocols are compared by their classification accuracy on ImageNet. However, this single metric does not fully capture performance nuances critical for specialized tasks. In this work, we conduct an in-depth comparative analysis of model behaviors beyond ImageNet accuracy, for both ConvNet and Vision Transformer architectures, each across supervised and CLIP training paradigms. Although our selected models have similar ImageNet accuracies and compute requirements, we find that they differ in many other aspects: types of mistakes, output calibration, transferability, and feature invariance, among others. This diversity in model characteristics, not captured by traditional metrics, highlights the need for more nuanced analysis when choosing among different models. Our code is available at https://github.com/kirill-vish/Beyond-INet.
Authors: Chi Yan, Delin Qu, Dong Wang, Dan Xu, Zhigang Wang, Bin Zhao, Xuelong Li
In this paper, we introduce $\textbf{GS-SLAM}$ that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping (SLAM) system. It facilitates a better balance between efficiency and accuracy. Compared to recent SLAM methods employing neural implicit representations, our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization and RGB-D re-rendering. Specifically, we propose an adaptive expansion strategy that adds new or deletes noisy 3D Gaussian in order to efficiently reconstruct new observed scene geometry and improve the mapping of previously observed areas. This strategy is essential to extend 3D Gaussian representation to reconstruct the whole scene rather than synthesize a static object in existing methods. Moreover, in the pose tracking process, an effective coarse-to-fine technique is designed to select reliable 3D Gaussian representations to optimize camera pose, resulting in runtime reduction and robust estimation. Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets. The source code will be released soon.
Authors: Yu Huang, Yue Chen, Zhu Li
Since DARPA Grand Challenges (rural) in 2004/05 and Urban Challenges in 2007, autonomous driving has been the most active field of AI applications. Recently powered by large language models (LLMs), chat systems, such as chatGPT and PaLM, emerge and rapidly become a promising direction to achieve artificial general intelligence (AGI) in natural language processing (NLP). There comes a natural thinking that we could employ these abilities to reformulate autonomous driving. By combining LLM with foundation models, it is possible to utilize the human knowledge, commonsense and reasoning to rebuild autonomous driving systems from the current long-tailed AI dilemma. In this paper, we investigate the techniques of foundation models and LLMs applied for autonomous driving, categorized as simulation, world model, data annotation and planning or E2E solutions etc.
Authors: Yifan Yang, Siqin Wang, Daoyang Li, Yixian Zhang, Shuju Sun, Junzhou He
Geographic privacy or geo-privacy refers to the keeping private of one's geographic location, especially the restriction of geographical data maintained by personal electronic devices. Geo-privacy is a crucial aspect of personal security; however, it often goes unnoticed in daily activities. With the surge in the use of Large Multimodal Models (LMMs), such as GPT-4, for Open Source Intelligence (OSINT), the potential risks associated with geo-privacy breaches have intensified. This study develops a location-integrated GPT-4 based model named GeoLocator and designs four-dimensional experiments to demonstrate its capability in inferring the locational information of input imageries and/or social media contents. Our experiments reveal that GeoLocator generates specific geographic details with high accuracy and consequently embeds the risk of the model users exposing geospatial information to the public unintentionally, highlighting the thread of online data sharing, information gathering technologies and LLMs on geo-privacy. We conclude with the broader implications of GeoLocator and our findings for individuals and the community at large, by emphasizing the urgency for enhanced awareness and protective measures against geo-privacy leakage in the era of advanced AI and widespread social media usage.
Authors: Yeongtak Oh, Jooyoung Choi, Yongsung Kim, Minjun Park, Chaehun Shin, Sungroh Yoon
Recent advancements in text-to-3D generation have significantly contributed to the automation and democratization of 3D content creation. Building upon these developments, we aim to address the limitations of current methods in generating 3D models with creative geometry and styles. We introduce multi-view ControlNet, a novel depth-aware multi-view diffusion model trained on generated datasets from a carefully curated text corpus. Our multi-view ControlNet is then integrated into our two-stage pipeline, ControlDreamer, enabling text-guided generation of stylized 3D models. Additionally, we present a comprehensive benchmark for 3D style editing, encompassing a broad range of subjects, including objects, animals, and characters, to further facilitate research on diverse 3D generation. Our comparative analysis reveals that this new pipeline outperforms existing text-to-3D methods as evidenced by human evaluations and CLIP score metrics.
Authors: Ri Cheng, Ruian He, Xuhao Jiang, Shili Zhou, Weimin Tan, Bo Yan
Existing recurrent optical flow estimation networks are computationally expensive since they use a fixed large number of iterations to update the flow field for each sample. An efficient network should skip iterations when the flow improvement is limited. In this paper, we develop a Context-Aware Iteration Policy Network for efficient optical flow estimation, which determines the optimal number of iterations per sample. The policy network achieves this by learning contextual information to realize whether flow improvement is bottlenecked or minimal. On the one hand, we use iteration embedding and historical hidden cell, which include previous iterations information, to convey how flow has changed from previous iterations. On the other hand, we use the incremental loss to make the policy network implicitly perceive the magnitude of optical flow improvement in the subsequent iteration. Furthermore, the computational complexity in our dynamic network is controllable, allowing us to satisfy various resource preferences with a single trained model. Our policy network can be easily integrated into state-of-the-art optical flow networks. Extensive experiments show that our method maintains performance while reducing FLOPs by about 40%/20% for the Sintel/KITTI datasets.
Authors: Marcos Barcina-Blanco, Jesus L. Lobo, Pablo Garcia-Bringas, Javier Del Ser
In real-world scenarios classification models are often required to perform robustly when predicting samples belonging to classes that have not appeared during its training stage. Open Set Recognition addresses this issue by devising models capable of detecting unknown classes from samples arriving during the testing phase, while maintaining a good level of performance in the classification of samples belonging to known classes. This review comprehensively overviews the recent literature related to Open Set Recognition, identifying common practices, limitations, and connections of this field with other machine learning research areas, such as continual learning, out-of-distribution detection, novelty detection, and uncertainty estimation. Our work also uncovers open problems and suggests several research directions that may motivate and articulate future efforts towards more safe Artificial Intelligence methods.
Authors: Jinxiang Lai, Wenlong Wu, Bin-Bin Gao, Jun Liu, Jiawei Zhan, Congchong Nie, Yi Zeng, Chengjie Wang
Image matching and object detection are two fundamental and challenging tasks, while many related applications consider them two individual tasks (i.e. task-individual). In this paper, a collaborative framework called MatchDet (i.e. task-collaborative) is proposed for image matching and object detection to obtain mutual improvements. To achieve the collaborative learning of the two tasks, we propose three novel modules, including a Weighted Spatial Attention Module (WSAM) for Detector, and Weighted Attention Module (WAM) and Box Filter for Matcher. Specifically, the WSAM highlights the foreground regions of target image to benefit the subsequent detector, the WAM enhances the connection between the foreground regions of pair images to ensure high-quality matches, and Box Filter mitigates the impact of false matches. We evaluate the approaches on a new benchmark with two datasets called Warp-COCO and miniScanNet. Experimental results show our approaches are effective and achieve competitive improvements.
Authors: Tao Wang
Natural scene text detection is a significant challenge in computer vision, with tremendous potential applications in multilingual, diverse, and complex text scenarios. We propose a multilingual text detection model to address the issues of low accuracy and high difficulty in detecting multilingual text in natural scenes. In response to the challenges posed by multilingual text images with multiple character sets and various font styles, we introduce the SFM Swin Transformer feature extraction network to enhance the model's robustness in detecting characters and fonts across different languages. Dealing with the considerable variation in text scales and complex arrangements in natural scene text images, we present the AS-HRFPN feature fusion network by incorporating an Adaptive Spatial Feature Fusion module and a Spatial Pyramid Pooling module. The feature fusion network improvements enhance the model's ability to detect text sizes and orientations. Addressing diverse backgrounds and font variations in multilingual scene text images is a challenge for existing methods. Limited local receptive fields hinder detection performance. To overcome this, we propose a Global Semantic Segmentation Branch, extracting and preserving global features for more effective text detection, aligning with the need for comprehensive information. In this study, we collected and built a real-world multilingual natural scene text image dataset and conducted comprehensive experiments and analyses. The experimental results demonstrate that the proposed algorithm achieves an F-measure of 85.02\%, which is 4.71\% higher than the baseline model. We also conducted extensive cross-dataset validation on MSRA-TD500, ICDAR2017MLT, and ICDAR2015 datasets to verify the generality of our approach. The code and dataset can be found at https://github.com/wangmelon/CEMLT.
Authors: Shinan Zou, Chao Fan, Jianbo Xiong, Chuanfu Shen, Shiqi Yu, Jin Tang
Gait datasets are essential for gait research. However, this paper observes that present benchmarks, whether conventional constrained or emerging real-world datasets, fall short regarding covariate diversity. To bridge this gap, we undertake an arduous 20-month effort to collect a cross-covariate gait recognition (CCGR) dataset. The CCGR dataset has 970 subjects and about 1.6 million sequences; almost every subject has 33 views and 53 different covariates. Compared to existing datasets, CCGR has both population and individual-level diversity. In addition, the views and covariates are well labeled, enabling the analysis of the effects of different factors. CCGR provides multiple types of gait data, including RGB, parsing, silhouette, and pose, offering researchers a comprehensive resource for exploration. In order to delve deeper into addressing cross-covariate gait recognition, we propose parsing-based gait recognition (ParsingGait) by utilizing the newly proposed parsing data. We have conducted extensive experiments. Our main results show: 1) Cross-covariate emerges as a pivotal challenge for practical applications of gait recognition. 2) ParsingGait demonstrates remarkable potential for further advancement. 3) Alarmingly, existing SOTA methods achieve less than 43% accuracy on the CCGR, highlighting the urgency of exploring cross-covariate gait recognition. Link: https://github.com/ShinanZou/CCGR.
Authors: Liman Wang, Hanyang Zhong
Inspired by human driving focus, this research pioneers networks augmented with Focusing Sampling, Partial Field of View Evaluation, Enhanced FPN architecture and Directional IoU Loss - targeted innovations addressing obstacles to precise lane detection for autonomous driving. Experiments demonstrate our Focusing Sampling strategy, emphasizing vital distant details unlike uniform approaches, significantly boosts both benchmark and practical curved/distant lane recognition accuracy essential for safety. While FENetV1 achieves state-of-the-art conventional metric performance via enhancements isolating perspective-aware contexts mimicking driver vision, FENetV2 proves most reliable on the proposed Partial Field analysis. Hence we specifically recommend V2 for practical lane navigation despite fractional degradation on standard entire-image measures. Future directions include collecting on-road data and integrating complementary dual frameworks to further breakthroughs guided by human perception principles. The Code is available at https://github.com/HanyangZhong/FENet.
Authors: Maria Frasca, Davide La Torre, Gabriella Pravettoni, Ilaria Cutica
Parkinson's disease is a neurological condition that occurs in nearly 1% of the world's population. The disease is manifested by a drop in dopamine production, symptoms are cognitive and behavioural and include a wide range of personality changes, depressive disorders, memory problems, and emotional dysregulation, which can occur as the disease progresses. Early diagnosis and accurate staging of the disease are essential to apply the appropriate therapeutic approaches to slow cognitive and motor decline.
Currently, there is not a single blood test or biomarker available to diagnose Parkinson's disease. Magnetic resonance imaging has been used for the past three decades to diagnose and distinguish between PD and other neurological conditions. However, in recent years new possibilities have arisen: several AI algorithms have been developed to increase the precision and accuracy of differential diagnosis of PD at an early stage.
To our knowledge, no AI tools have been designed to identify the stage of progression. This paper aims to fill this gap. Using the "Parkinson's Progression Markers Initiative" dataset, which reports the patient's MRI and an indication of the disease stage, we developed a model to identify the level of progression. The images and the associated scores were used for training and assessing different deep-learning models. Our analysis distinguished four distinct disease progression levels based on a standard scale (Hoehn and Yah scale). The final architecture consists of the cascading of a 3DCNN network, adopted to reduce and extract the spatial characteristics of the RMI for efficient training of the successive LSTM layers, aiming at modelling the temporal dependencies among the data.
Our results show that the proposed 3DCNN + LSTM model achieves state-of-the-art results by classifying the elements with 91.90\% as macro averaged OVR AUC on four classes
Authors: Galib Muhammad Shahriar Himel
Traditionally, pathological analysis and diagnosis are performed by manually eyeballing glass slide specimens under a microscope by an expert. The whole slide image is the digital specimen produced from the glass slide. Whole slide image enabled specimens to be observed on a computer screen and led to computational pathology where computer vision and artificial intelligence are utilized for automated analysis and diagnosis. With the current computational advancement, the entire whole slide image can be analyzed autonomously without human supervision. However, the analysis could fail or lead to wrong diagnosis if the whole slide image is affected by tissue artifacts such as tissue fold or air bubbles depending on the severity. Existing artifact detection methods rely on experts for severity assessment to eliminate artifact affected regions from the analysis. This process is time consuming, exhausting and undermines the goal of automated analysis or removal of artifacts without evaluating their severity, which could result in the loss of diagnostically important data. Therefore, it is necessary to detect artifacts and then assess their severity automatically. In this paper, we propose a system that incorporates severity evaluation with artifact detection utilizing convolutional neural networks. The proposed system uses DoubleUNet to segment artifacts and an ensemble network of six fine tuned convolutional neural network models to determine severity. This method outperformed current state of the art in accuracy by 9 percent for artifact segmentation and achieved a strong correlation of 97 percent with the evaluation of pathologists for severity assessment. The robustness of the system was demonstrated using our proposed heterogeneous dataset and practical usability was ensured by integrating it with an automated analysis system.
Authors: Hao Sun, Mingyao Zhou, Wenjing Chen, Wei Xie
Video moment retrieval (MR) and highlight detection (HD) based on natural language queries are two highly related tasks, which aim to obtain relevant moments within videos and highlight scores of each video clip. Recently, several methods have been devoted to building DETR-based networks to solve both MR and HD jointly. These methods simply add two separate task heads after multi-modal feature extraction and feature interaction, achieving good performance. Nevertheless, these approaches underutilize the reciprocal relationship between two tasks. In this paper, we propose a task-reciprocal transformer based on DETR (TR-DETR) that focuses on exploring the inherent reciprocity between MR and HD. Specifically, a local-global multi-modal alignment module is first built to align features from diverse modalities into a shared latent space. Subsequently, a visual feature refinement is designed to eliminate query-irrelevant information from visual features for modal interaction. Finally, a task cooperation module is constructed to refine the retrieval pipeline and the highlight score prediction process by utilizing the reciprocity between MR and HD. Comprehensive experiments on QVHighlights, Charades-STA and TVSum datasets demonstrate that TR-DETR outperforms existing state-of-the-art methods. Codes are available at \url{https://github.com/mingyao1120/TR-DETR}.
Authors: Xiangyu Zhao, Yicheng Chen, Shilin Xu, Xiangtai Li, Xinjiang Wang, Yining Li, Haian Huang
Grounding-DINO is a state-of-the-art open-set detection model that tackles multiple vision tasks including Open-Vocabulary Detection (OVD), Phrase Grounding (PG), and Referring Expression Comprehension (REC). Its effectiveness has led to its widespread adoption as a mainstream architecture for various downstream applications. However, despite its significance, the original Grounding-DINO model lacks comprehensive public technical details due to the unavailability of its training code. To bridge this gap, we present MM-Grounding-DINO, an open-source, comprehensive, and user-friendly baseline, which is built with the MMDetection toolbox. It adopts abundant vision datasets for pre-training and various detection and grounding datasets for fine-tuning. We give a comprehensive analysis of each reported result and detailed settings for reproduction. The extensive experiments on the benchmarks mentioned demonstrate that our MM-Grounding-DINO-Tiny outperforms the Grounding-DINO-Tiny baseline. We release all our models to the research community. Codes and trained models are released at https://github.com/open-mmlab/mmdetection/tree/main/configs/mm_grounding_dino.
Authors: Kuangpu Guo, Yuhe Ding, Jian Liang, Ran He, Zilei Wang, Tieniu Tan
Data heterogeneity, characterized by disparities in local data distribution across clients, poses a significant challenge in federated learning. Substantial efforts have been devoted to addressing the heterogeneity in local label distribution. As minority classes suffer from worse accuracy due to overfitting on local imbalanced data, prior methods often incorporate class-balanced learning techniques during local training. Despite the improved mean accuracy across all classes, we observe that empty classes-referring to categories absent from a client's data distribution-are still not well recognized. This paper introduces FedED, a novel approach in heterogeneous federated learning that integrates both empty-class distillation and logit suppression simultaneously. Specifically, empty-class distillation leverages knowledge distillation during local training on each client to retain essential information related to empty classes from the global model. Moreover, logit suppression directly penalizes network logits for non-label classes, effectively addressing misclassifications in minority classes that may be biased toward majority classes. Extensive experiments validate the efficacy of FedED, surpassing previous state-of-the-art methods across diverse datasets with varying degrees of label distribution shift.