Authors: Pablo Luesia, Miguel Crespo, Adrian Jarabo, Albert Redo-Sanchez
Non-line-of-sight (NLOS) imaging aims to reconstruct partially or completely occluded scenes. Recent approaches have demonstrated high-quality reconstructions of complex scenes with arbitrary reflectance, occlusions, and significant multi-path effects. However, previous works focused on surface scattering only, which reduces the generality in more challenging scenarios such as scenes submerged in scattering media. In this work, we investigate current state-of-the-art NLOS imaging methods based on phasor fields to reconstruct scenes submerged in scattering media. We empirically analyze the capability of phasor fields in reconstructing complex synthetic scenes submerged in thick scattering media. We also apply the method to real scenes, showing that it performs similarly to recent diffuse optical tomography methods.
Authors: Xuelei Chen
Autonomous driving is a challenging task that has gained broad attention from both academia and industry. Current solutions using convolutional neural networks require large amounts of computational resources, leading to high power consumption. Spiking neural networks (SNNs) provide an alternative computation model to process information and make decisions. This biologically plausible model has the advantage of low latency and energy efficiency. Recent work using SNNs for autonomous driving mostly focused on simple tasks like lane keeping in simplified simulation environments. This project studies SNNs on photo-realistic driving scenes in the CARLA simulator, which is an important step toward using SNNs on real vehicles. The efficacy and generalizability of the method will be investigated.
Authors: Zhenyu Han, Yanxin Xi, Tong Xia, Yu Liu, Yong Li
Built environment supports all the daily activities and shapes our health. Leveraging informative street view imagery, previous research has established the profound correlation between the built environment and chronic, non-communicable diseases; however, predicting the exposure risk of infectious diseases remains largely unexplored. The person-to-person contacts and interactions contribute to the complexity of infectious disease, which is inherently different from non-communicable diseases. Besides, the complex relationships between street view imagery and epidemic exposure also hinder accurate predictions. To address these problems, we construct a regional mobility graph informed by the gravity model, based on which we propose a transmission-aware graph convolutional network (GCN) to capture disease transmission patterns arising from human mobility. Experiments show that the proposed model significantly outperforms baseline models by 8.54% in weighted F1, shedding light on a low-cost, scalable approach to assess epidemic exposure risks from street view imagery.
Authors: Fanxu Meng, Haotong Yang, Yiding Wang, Muhan Zhang
The human brain is naturally equipped to comprehend and interpret visual information rapidly. When confronted with complex problems or concepts, we use flowcharts, sketches, and diagrams to aid our thought process. Leveraging this inherent ability can significantly enhance logical reasoning. However, current Large Language Models (LLMs) do not utilize such visual intuition to help their thinking. Even the most advanced version language models (e.g., GPT-4V and LLaVA) merely align images into textual space, which means their reasoning processes remain purely verbal. To mitigate such limitations, we present a Chain of Images (CoI) approach, which can convert complex language reasoning problems to simple pattern recognition by generating a series of images as intermediate representations. Furthermore, we have developed a CoI evaluation dataset encompassing 15 distinct domains where images can intuitively aid problem-solving. Based on this dataset, we aim to construct a benchmark to assess the capability of future multimodal large-scale models to leverage images for reasoning. In supporting our CoI reasoning, we introduce a symbolic multimodal large language model (SyMLLM) that generates images strictly based on language instructions and accepts both text and image as input. Experiments on Geometry, Chess and Common Sense tasks sourced from the CoI evaluation dataset show that CoI improves performance significantly over the pure-language Chain of Thoughts (CoT) baselines. The code is available at https://github.com/GraphPKU/CoI.
Authors: Guy Ohayon, Tomer Michaeli, Michael Elad
We study the behavior of deterministic methods for solving inverse problems in imaging. These methods are commonly designed to achieve two goals: (1) attaining high perceptual quality, and (2) generating reconstructions that are consistent with the measurements. We provide a rigorous proof that the better a predictor satisfies these two requirements, the larger its Lipschitz constant must be, regardless of the nature of the degradation involved. In particular, to approach perfect perceptual quality and perfect consistency, the Lipschitz constant of the model must grow to infinity. This implies that such methods are necessarily more susceptible to adversarial attacks. We demonstrate our theory on single image super-resolution algorithms, addressing both noisy and noiseless settings. We also show how this undesired behavior can be leveraged to explore the posterior distribution, thereby allowing the deterministic model to imitate stochastic methods.
Authors: Jacob Tyo, Youngseog Chung, Motolani Olarinre, Zachary C. Lipton
This paper introduces the off-road motorcycle Racer number Dataset (RnD), a new challenging dataset for optical character recognition (OCR) research. RnD contains 2,411 images from professional motorsports photographers that depict motorcycle racers in off-road competitions. The images exhibit a wide variety of factors that make OCR difficult, including mud occlusions, motion blur, non-standard fonts, glare, complex backgrounds, etc. The dataset has 5,578 manually annotated bounding boxes around visible motorcycle numbers, along with transcribed digits and letters. Our experiments benchmark leading OCR algorithms and reveal an end-to-end F1 score of only 0.527 on RnD, even after fine-tuning. Analysis of performance on different occlusion types shows mud as the primary challenge, degrading accuracy substantially compared to normal conditions. But the models struggle with other factors including glare, blur, shadows, and dust. Analysis exposes substantial room for improvement and highlights failure cases of existing models. RnD represents a valuable new benchmark to drive innovation in real-world OCR capabilities. The authors hope the community will build upon this dataset and baseline experiments to make progress on the open problem of robustly recognizing text in unconstrained natural environments. The dataset is available at https://github.com/JacobTyo/SwinTextSpotter.
Authors: Yanwu Xu, Yang Zhao, Zhisheng Xiao, Tingbo Hou
Text-to-image diffusion models have demonstrated remarkable capabilities in transforming textual prompts into coherent images, yet the computational cost of their inference remains a persistent challenge. To address this issue, we present UFOGen, a novel generative model designed for ultra-fast, one-step text-to-image synthesis. In contrast to conventional approaches that focus on improving samplers or employing distillation techniques for diffusion models, UFOGen adopts a hybrid methodology, integrating diffusion models with a GAN objective. Leveraging a newly introduced diffusion-GAN objective and initialization with pre-trained diffusion models, UFOGen excels in efficiently generating high-quality images conditioned on textual descriptions in a single step. Beyond traditional text-to-image generation, UFOGen showcases versatility in applications. Notably, UFOGen stands among the pioneering models enabling one-step text-to-image generation and diverse downstream tasks, presenting a significant advancement in the landscape of efficient generative models. \blfootnote{*Work done as a student researcher of Google, $\dagger$ indicates equal contribution.
Authors: Zhongjie Duan, Chengyu Wang, Cen Chen, Weining Qian, Jun Huang, Mingyi Jin
With the emergence of diffusion models and rapid development in image processing, it has become effortless to generate fancy images in tasks such as style transfer and image editing. However, these impressive image processing approaches face consistency issues in video processing. In this paper, we propose a powerful model-free toolkit called FastBlend to address the consistency problem for video processing. Based on a patch matching algorithm, we design two inference modes, including blending and interpolation. In the blending mode, FastBlend eliminates video flicker by blending the frames within a sliding window. Moreover, we optimize both computational efficiency and video quality according to different application scenarios. In the interpolation mode, given one or more keyframes rendered by diffusion models, FastBlend can render the whole video. Since FastBlend does not modify the generation process of diffusion models, it exhibits excellent compatibility. Extensive experiments have demonstrated the effectiveness of FastBlend. In the blending mode, FastBlend outperforms existing methods for video deflickering and video synthesis. In the interpolation mode, FastBlend surpasses video interpolation and model-based video processing approaches. The source codes have been released on GitHub.
Authors: En-Te Lin, Wei-Jie Lv, Ding-Tao Huang, Long Zeng
Existing Object Pose Estimation (OPE) methods for stacked scenarios are not robust to changes in object scale. This paper proposes a new 6DoF OPE network (NormNet) for different scale objects in stacked scenarios. Specifically, each object's scale is first learned with point-wise regression. Then, all objects in the stacked scenario are normalized into the same scale through semantic segmentation and affine transformation. Finally, they are fed into a shared pose estimator to recover their 6D poses. In addition, we introduce a new Sim-to-Real transfer pipeline, combining style transfer and domain randomization. This improves the NormNet's performance on real data even if we only train it on synthetic data. Extensive experiments demonstrate that the proposed method achieves state-of-the-art performance on public benchmarks and the MultiScale dataset we constructed. The real-world experiments show that our method can robustly estimate the 6D pose of objects at different scales.
Authors: Muthukumaran Ramasubramanian, Iksha Gurung, Shubhankar Gahlot, Ronny Hänsch, Andrew L. Molthan, Manil Maskey
Accurate detection of inundated water extents during flooding events is crucial in emergency response decisions and aids in recovery efforts. Satellite Remote Sensing data provides a global framework for detecting flooding extents. Specifically, Sentinel-1 C-Band Synthetic Aperture Radar (SAR) imagery has proven to be useful in detecting water bodies due to low backscatter of water features in both co-polarized and cross-polarized SAR imagery. However, increased backscatter can be observed in certain flooded regions such as presence of infrastructure and trees - rendering simple methods such as pixel intensity thresholding and time-series differencing inadequate. Machine Learning techniques has been leveraged to precisely capture flood extents in flooded areas with bumps in backscatter but needs high amounts of labelled data to work desirably. Hence, we created a labeled known water body extent and flooded area extents during known flooding events covering about 36,000 sq. kilometers of regions within mainland U.S and Bangladesh. Further, We also leveraged citizen science by open-sourcing the dataset and hosting an open competition based on the dataset to rapidly prototype flood extent detection using community generated models. In this paper we present the information about the dataset, the data processing pipeline, a baseline model and the details about the competition, along with discussion on winning approaches. We believe the dataset adds to already existing datasets based on Sentinel-1C SAR data and leads to more robust modeling of flood extents. We also hope the results from the competition pushes the research in flood extent detection further.
Authors: Tao Sun, Yan Hao, Shengyu Huang, Silvio Savarese, Konrad Schindler, Marc Pollefeys, Iro Armeni
Building 3D geometric maps of man-made spaces is a well-established and active field that is fundamental to computer vision and robotics. However, considering the evolving nature of built environments, it is essential to question the capabilities of current mapping efforts in handling temporal changes. In addition, spatiotemporal mapping holds significant potential for achieving sustainability and circularity goals. Existing mapping approaches focus on small changes, such as object relocation or self-driving car operation; in all cases where the main structure of the scene remains fixed. Consequently, these approaches fail to address more radical changes in the structure of the built environment, such as geometry and topology. To this end, we introduce the Nothing Stands Still (NSS) benchmark, which focuses on the spatiotemporal registration of 3D scenes undergoing large spatial and temporal change, ultimately creating one coherent spatiotemporal map. Specifically, the benchmark involves registering two or more partial 3D point clouds (fragments) from the same scene but captured from different spatiotemporal views. In addition to the standard pairwise registration, we assess the multi-way registration of multiple fragments that belong to any temporal stage. As part of NSS, we introduce a dataset of 3D point clouds recurrently captured in large-scale building indoor environments that are under construction or renovation. The NSS benchmark presents three scenarios of increasing difficulty, to quantify the generalization ability of point cloud registration methods over space (within one building and across buildings) and time. We conduct extensive evaluations of state-of-the-art methods on NSS. The results demonstrate the necessity for novel methods specifically designed to handle large spatiotemporal changes. The homepage of our benchmark is at this http URL
Authors: Thomas Cilloni, Charles Fleming, Charles Walter
This paper introduces a novel approach to membership inference attacks (MIA) targeting stable diffusion computer vision models, specifically focusing on the highly sophisticated Stable Diffusion V2 by StabilityAI. MIAs aim to extract sensitive information about a model's training data, posing significant privacy concerns. Despite its advancements in image synthesis, our research reveals privacy vulnerabilities in the stable diffusion models' outputs. Exploiting this information, we devise a black-box MIA that only needs to query the victim model repeatedly. Our methodology involves observing the output of a stable diffusion model at different generative epochs and training a classification model to distinguish when a series of intermediates originated from a training sample or not. We propose numerous ways to measure the membership features and discuss what works best. The attack's efficacy is assessed using the ROC AUC method, demonstrating a 60\% success rate in inferring membership information. This paper contributes to the growing body of research on privacy and security in machine learning, highlighting the need for robust defenses against MIAs. Our findings prompt a reevaluation of the privacy implications of stable diffusion models, urging practitioners and developers to implement enhanced security measures to safeguard against such attacks.
Authors: James A. D. Gardner, Bernhard Egger, William A. P. Smith
Inverse rendering is an ill-posed problem. Previous work has sought to resolve this by focussing on priors for object or scene shape or appearance. In this work, we instead focus on a prior for natural illuminations. Current methods rely on spherical harmonic lighting or other generic representations and, at best, a simplistic prior on the parameters. This results in limitations for the inverse setting in terms of the expressivity of the illumination conditions, especially when taking specular reflections into account. We propose a conditional neural field representation based on a variational auto-decoder and a transformer decoder. We extend Vector Neurons to build equivariance directly into our architecture, and leveraging insights from depth estimation through a scale-invariant loss function, we enable the accurate representation of High Dynamic Range (HDR) images. The result is a compact, rotation-equivariant HDR neural illumination model capable of capturing complex, high-frequency features in natural environment maps. Training our model on a curated dataset of 1.6K HDR environment maps of natural scenes, we compare it against traditional representations, demonstrate its applicability for an inverse rendering task and show environment map completion from partial observations. We share our PyTorch implementation, dataset and trained models at https://github.com/JADGardner/ns_reni
Authors: Yuwen Chen, Helen Zhou, Zachary C. Lipton
Medical imaging data is often siloed within hospitals, limiting the amount of data available for specialized model development. With limited in-domain data, one might hope to leverage larger datasets from related domains. In this paper, we analyze the benefit of transferring self-supervised contrastive representations from moment contrast (MoCo) pretraining on out-of-distribution data to settings with limited data. We consider two X-ray datasets which image different parts of the body, and compare transferring from each other to transferring from ImageNet. We find that depending on quantity of labeled and unlabeled data, contrastive pretraining on larger out-of-distribution datasets can perform nearly as well or better than MoCo pretraining in-domain, and pretraining on related domains leads to higher performance than if one were to use the ImageNet pretrained weights. Finally, we provide a preliminary way of quantifying similarity between datasets.
Authors: Bardia Khosravi, Frank Li, Theo Dapamede, Pouria Rouzrokh, Cooper U. Gamble, Hari M. Trivedi, Cody C. Wyles, Andrew B. Sellergren, Saptarshi Purkayastha, Bradley J. Erickson, Judy W. Gichoya
Chest X-rays (CXR) are the most common medical imaging study and are used to diagnose multiple medical conditions. This study examines the impact of synthetic data supplementation, using diffusion models, on the performance of deep learning (DL) classifiers for CXR analysis. We employed three datasets: CheXpert, MIMIC-CXR, and Emory Chest X-ray, training conditional denoising diffusion probabilistic models (DDPMs) to generate synthetic frontal radiographs. Our approach ensured that synthetic images mirrored the demographic and pathological traits of the original data. Evaluating the classifiers' performance on internal and external datasets revealed that synthetic data supplementation enhances model accuracy, particularly in detecting less prevalent pathologies. Furthermore, models trained on synthetic data alone approached the performance of those trained on real data. This suggests that synthetic data can potentially compensate for real data shortages in training robust DL models. However, despite promising outcomes, the superiority of real data persists.
Authors: Amir Jamaludin, Timor Kadir, Emma Clark, Andrew Zisserman
Our objective in this paper is to estimate spine curvature in DXA scans. To this end we first train a neural network to predict the middle spine curve in the scan, and then use an integral-based method to determine the curvature along the spine curve. We use the curvature to compare to the standard angle scoliosis measure obtained using the DXA Scoliosis Method (DSM). The performance improves over the prior work of Jamaludin et al. 2018. We show that the maximum curvature can be used as a scoring function for ordering the severity of spinal deformation.
Authors: Xiaoyan Li, Gang Zhang, Boyue Wang, Yongli Hu, Baocai Yin
LiDAR panoptic segmentation facilitates an autonomous vehicle to comprehensively understand the surrounding objects and scenes and is required to run in real time. The recent proposal-free methods accelerate the algorithm, but their effectiveness and efficiency are still limited owing to the difficulty of modeling non-existent instance centers and the costly center-based clustering modules. To achieve accurate and real-time LiDAR panoptic segmentation, a novel center focusing network (CFNet) is introduced. Specifically, the center focusing feature encoding (CFFE) is proposed to explicitly understand the relationships between the original LiDAR points and virtual instance centers by shifting the LiDAR points and filling in the center points. Moreover, to leverage the redundantly detected centers, a fast center deduplication module (CDM) is proposed to select only one center for each instance. Experiments on the SemanticKITTI and nuScenes panoptic segmentation benchmarks demonstrate that our CFNet outperforms all existing methods by a large margin and is 1.6 times faster than the most efficient method. The code is available at https://github.com/GangZhang842/CFNet.
Authors: Yangzheng Wu, Michael Greenspan
This paper addresses the simulation-to-real domain gap in 6DoF PE, and proposes a novel self-supervised keypoint radial voting-based 6DoF PE framework, effectively narrowing this gap using a learnable kernel in RKHS. We formulate this domain gap as a distance in high-dimensional feature space, distinct from previous iterative matching methods. We propose an adapter network, which evolves the network parameters from the source domain, which has been massively trained on synthetic data with synthetic poses, to the target domain, which is trained on real data. Importantly, the real data training only uses pseudo-poses estimated by pseudo-keypoints, and thereby requires no real groundtruth data annotations. RKHSPose achieves state-of-the-art performance on three commonly used 6DoF PE datasets including LINEMOD (+4.2%), Occlusion LINEMOD (+2%), and YCB-Video (+3%). It also compares favorably to fully supervised methods on all six applicable BOP core datasets, achieving within -10.8% to -0.3% of the top fully supervised results.
Authors: Daixun Li, Weiying Xie, Jiaqing Zhang, Yunsong Li
High-dimensional images, known for their rich semantic information, are widely applied in remote sensing and other fields. The spatial information in these images reflects the object's texture features, while the spectral information reveals the potential spectral representations across different bands. Currently, the understanding of high-dimensional images remains limited to a single-domain perspective with performance degradation. Motivated by the masking texture effect observed in the human visual system, we present a multi-domain diffusion-driven feature learning network (MDFL) , a scheme to redefine the effective information domain that the model really focuses on. This method employs diffusion-based posterior sampling to explicitly consider joint information interactions between the high-dimensional manifold structures in the spectral, spatial, and frequency domains, thereby eliminating the influence of masking texture effects in visual models. Additionally, we introduce a feature reuse mechanism to gather deep and raw features of high-dimensional data. We demonstrate that MDFL significantly improves the feature extraction performance of high-dimensional data, thereby providing a powerful aid for revealing the intrinsic patterns and structures of such data. The experimental results on three multi-modal remote sensing datasets show that MDFL reaches an average overall accuracy of 98.25%, outperforming various state-of-the-art baseline schemes. The code will be released, contributing to the computer vision community.
Authors: DaiXun Li, Weiying Xie, Yunsong Li, Leyuan Fang
Multi-satellite, multi-modality in-orbit fusion is a challenging task as it explores the fusion representation of complex high-dimensional data under limited computational resources. Deep neural networks can reveal the underlying distribution of multi-modal remote sensing data, but the in-orbit fusion of multimodal data is more difficult because of the limitations of different sensor imaging characteristics, especially when the multimodal data follows non-independent identically distribution (Non-IID) distributions. To address this problem while maintaining classification performance, this paper proposes a manifold-driven multi-modality fusion framework, FedFusion, which randomly samples local data on each client to jointly estimate the prominent manifold structure of shallow features of each client and explicitly compresses the feature matrices into a low-rank subspace through cascading and additive approaches, which is used as the feature input of the subsequent classifier. Considering the physical space limitations of the satellite constellation, we developed a multimodal federated learning module designed specifically for manifold data in a deep latent space. This module achieves iterative updating of the sub-network parameters of each client through global weighted averaging, constructing a framework that can represent compact representations of each client. The proposed framework surpasses existing methods in terms of performance on three multimodal datasets, achieving a classification average accuracy of 94.35$\%$ while compressing communication costs by a factor of 4. Furthermore, extensive numerical evaluations of real-world satellite images were conducted on the orbiting edge computing architecture based on Jetson TX2 industrial modules, which demonstrated that FedFusion significantly reduced training time by 48.4 minutes (15.18%) while optimizing accuracy.}
Authors: Ming Chen, Yan Zhou, Weihua Jian, Pengfei Wan, Zhongyuan Wang
Though significant progress in human pose and shape recovery from monocular RGB images has been made in recent years, obtaining 3D human motion with high accuracy and temporal consistency from videos remains challenging. Existing video-based methods tend to reconstruct human motion from global image features, which lack detailed representation capability and limit the reconstruction accuracy. In this paper, we propose a Temporal-Aware Refining Network (TAR), to synchronously explore temporal-aware global and local image features for accurate pose and shape recovery. First, a global transformer encoder is introduced to obtain temporal global features from static feature sequences. Second, a bidirectional ConvGRU network takes the sequence of high-resolution feature maps as input, and outputs temporal local feature maps that maintain high resolution and capture the local motion of the human body. Finally, a recurrent refinement module iteratively updates estimated SMPL parameters by leveraging both global and local temporal information to achieve accurate and smooth results. Extensive experiments demonstrate that our TAR obtains more accurate results than previous state-of-the-art methods on popular benchmarks, i.e., 3DPW, MPI-INF-3DHP, and Human3.6M.
Authors: Dale Decatur, Itai Lang, Kfir Aberman, Rana Hanocka
In this work we develop 3D Paintbrush, a technique for automatically texturing local semantic regions on meshes via text descriptions. Our method is designed to operate directly on meshes, producing texture maps which seamlessly integrate into standard graphics pipelines. We opt to simultaneously produce a localization map (to specify the edit region) and a texture map which conforms to it. This synergistic approach improves the quality of both the localization and the stylization. To enhance the details and resolution of the textured area, we leverage multiple stages of a cascaded diffusion model to supervise our local editing technique with generative priors learned from images at different resolutions. Our technique, referred to as Cascaded Score Distillation (CSD), simultaneously distills scores at multiple resolutions in a cascaded fashion, enabling control over both the granularity and global understanding of the supervision. We demonstrate the effectiveness of 3D Paintbrush to locally texture a variety of shapes within different semantic regions. Project page: https://threedle.github.io/3d-paintbrush
Authors: Vivek Shankar, Xiaoli Yang, Vrishab Krishna, Brent Tan, Oscar Silva, Rebecca Rojansky, Andrew Ng, Fabiola Valvert, Edward Briercheck, David Weinstock, Yasodha Natkunam, Sebastian Fernandez-Pol, Pranav Rajpurkar
The accurate classification of lymphoma subtypes using hematoxylin and eosin (H&E)-stained tissue is complicated by the wide range of morphological features these cancers can exhibit. We present LymphoML - an interpretable machine learning method that identifies morphologic features that correlate with lymphoma subtypes. Our method applies steps to process H&E-stained tissue microarray cores, segment nuclei and cells, compute features encompassing morphology, texture, and architecture, and train gradient-boosted models to make diagnostic predictions. LymphoML's interpretable models, developed on a limited volume of H&E-stained tissue, achieve non-inferior diagnostic accuracy to pathologists using whole-slide images and outperform black box deep-learning on a dataset of 670 cases from Guatemala spanning 8 lymphoma subtypes. Using SHapley Additive exPlanation (SHAP) analysis, we assess the impact of each feature on model prediction and find that nuclear shape features are most discriminative for DLBCL (F1-score: 78.7%) and classical Hodgkin lymphoma (F1-score: 74.5%). Finally, we provide the first demonstration that a model combining features from H&E-stained tissue with features from a standardized panel of 6 immunostains results in a similar diagnostic accuracy (85.3%) to a 46-stain panel (86.1%).
Authors: Yuxuan Shi, Jun Xu, Dinggang Shen
Cone Beam Computed Tomography (CBCT) plays a key role in dental diagnosis and surgery. However, the metal teeth implants could bring annoying metal artifacts during the CBCT imaging process, interfering diagnosis and downstream processing such as tooth segmentation. In this paper, we develop an efficient Transformer to perform metal artifacts reduction (MAR) from dental CBCT images. The proposed MAR Transformer (MARformer) reduces computation complexity in the multihead self-attention by a new Dimension-Reduced Self-Attention (DRSA) module, based on that the CBCT images have globally similar structure. A Patch-wise Perceptive Feed Forward Network (P2FFN) is also proposed to perceive local image information for fine-grained restoration. Experimental results on CBCT images with synthetic and real-world metal artifacts show that our MARformer is efficient and outperforms previous MAR methods and two restoration Transformers.
Authors: Thomas Westfechtel, Hao-Wei Yeh, Dexuan Zhang, Tatsuya Harada
Unsupervised domain adaptation (UDA) tries to overcome the need for a large labeled dataset by transferring knowledge from a source dataset, with lots of labeled data, to a target dataset, that has no labeled data. Since there are no labels in the target domain, early misalignment might propagate into the later stages and lead to an error build-up. In order to overcome this problem, we propose a gradual source domain expansion (GSDE) algorithm. GSDE trains the UDA task several times from scratch, each time reinitializing the network weights, but each time expands the source dataset with target data. In particular, the highest-scoring target data of the previous run are employed as pseudo-source samples with their respective pseudo-label. Using this strategy, the pseudo-source samples induce knowledge extracted from the previous run directly from the start of the new training. This helps align the two domains better, especially in the early training epochs. In this study, we first introduce a strong baseline network and apply our GSDE strategy to it. We conduct experiments and ablation studies on three benchmarks (Office-31, OfficeHome, and DomainNet) and outperform state-of-the-art methods. We further show that the proposed GSDE strategy can improve the accuracy of a variety of different state-of-the-art UDA approaches.
Authors: Mohammad Areeb Qazi, Mohammed Talha Alam, Ibrahim Almakky, Werner Gerhard Diehl, Leanne Bricker, Mohammad Yaqub
Precise estimation of fetal biometry parameters from ultrasound images is vital for evaluating fetal growth, monitoring health, and identifying potential complications reliably. However, the automated computerized segmentation of the fetal head, abdomen, and femur from ultrasound images, along with the subsequent measurement of fetal biometrics, remains challenging. In this work, we propose a multi-task learning approach to classify the region into head, abdomen and femur as well as estimate the associated parameters. We were able to achieve a mean absolute error (MAE) of 1.08 mm on head circumference, 1.44 mm on abdomen circumference and 1.10 mm on femur length with a classification accuracy of 99.91\% on a dataset of fetal Ultrasound images. To achieve this, we leverage a weighted joint classification and segmentation loss function to train a U-Net architecture with an added classification head. The code can be accessed through \href{https://github.com/BioMedIA-MBZUAI/Multi-Task-Learning-Approach-for-Unified-Biometric-Estimation-from-Fetal-Ultrasound-Anomaly-Scans.git}{\texttt{Github}
Authors: Wang Zhu, Alekh Agarwal, Mandar Joshi, Robin Jia, Jesse Thomason, Kristina Toutanova
Understanding visually situated language requires recognizing text and visual elements, and interpreting complex layouts. State-of-the-art methods commonly use specialized pre-processing tools, such as optical character recognition (OCR) systems, that map document image inputs to extracted information in the space of textual tokens, and sometimes also employ large language models (LLMs) to reason in text token space. However, the gains from external tools and LLMs come at the cost of increased computational and engineering complexity. In this paper, we ask whether small pretrained image-to-text models can learn selective text or layout recognition and reasoning as an intermediate inference step in an end-to-end model for pixel-level visual language understanding. We incorporate the outputs of such OCR tools, LLMs, and larger multimodal models as intermediate ``rationales'' on training data, and train a small student model to predict both rationales and answers for input questions based on those training examples. A student model based on Pix2Struct (282M parameters) achieves consistent improvements on three visual document understanding benchmarks representing infographics, scanned documents, and figures, with improvements of more than 4\% absolute over a comparable Pix2Struct model that predicts answers directly.
Authors: Shadab Ahamed, Yixi Xu, Claire Gowdy, Joo H. O, Ingrid Bloise, Don Wilson, Patrick Martineau, François Bénard, Fereshteh Yousefirizi, Rahul Dodhia, Juan M. Lavista, William B. Weeks, Carlos F. Uribe, Arman Rahmim
This study performs comprehensive evaluation of four neural network architectures (UNet, SegResNet, DynUNet, and SwinUNETR) for lymphoma lesion segmentation from PET/CT images. These networks were trained, validated, and tested on a diverse, multi-institutional dataset of 611 cases. Internal testing (88 cases; total metabolic tumor volume (TMTV) range [0.52, 2300] ml) showed SegResNet as the top performer with a median Dice similarity coefficient (DSC) of 0.76 and median false positive volume (FPV) of 4.55 ml; all networks had a median false negative volume (FNV) of 0 ml. On the unseen external test set (145 cases with TMTV range: [0.10, 2480] ml), SegResNet achieved the best median DSC of 0.68 and FPV of 21.46 ml, while UNet had the best FNV of 0.41 ml. We assessed reproducibility of six lesion measures, calculated their prediction errors, and examined DSC performance in relation to these lesion measures, offering insights into segmentation accuracy and clinical relevance. Additionally, we introduced three lesion detection criteria, addressing the clinical need for identifying lesions, counting them, and segmenting based on metabolic characteristics. We also performed expert intra-observer variability analysis revealing the challenges in segmenting ``easy'' vs. ``hard'' cases, to assist in the development of more resilient segmentation algorithms. Finally, we performed inter-observer agreement assessment underscoring the importance of a standardized ground truth segmentation protocol involving multiple expert annotators. Code is available at: https://github.com/microsoft/lymphoma-segmentation-dnn
Authors: Akash Awasthi
Accurate classification of apoptosis plays an important role in cell biology research. There are many state-of-the-art approaches which use deep CNNs to perform the apoptosis classification but these approaches do not account for the cell interaction. Our paper proposes the Attention Graph spatio-temporal graph convolutional network to classify the cell death based on the target cells in the video. This method considers the interaction of multiple target cells at each time stamp. We model the whole video sequence as a set of graphs and classify the target cell in the video as dead or alive. Our method encounters both spatial and temporal relationships.
Authors: Jiaxin Zhang, Joy Rimchala, Lalla Mouatadid, Kamalika Das, Sricharan Kumar
The performance of optical character recognition (OCR) heavily relies on document image quality, which is crucial for automatic document processing and document intelligence. However, most existing document enhancement methods require supervised data pairs, which raises concerns about data separation and privacy protection, and makes it challenging to adapt these methods to new domain pairs. To address these issues, we propose DECDM, an end-to-end document-level image translation method inspired by recent advances in diffusion models. Our method overcomes the limitations of paired training by independently training the source (noisy input) and target (clean output) models, making it possible to apply domain-specific diffusion models to other pairs. DECDM trains on one dataset at a time, eliminating the need to scan both datasets concurrently, and effectively preserving data privacy from the source or target domain. We also introduce simple data augmentation strategies to improve character-glyph conservation during translation. We compare DECDM with state-of-the-art methods on multiple synthetic data and benchmark datasets, such as document denoising and {\color{black}shadow} removal, and demonstrate the superiority of performance quantitatively and qualitatively.
Authors: Sirui Bi, Victor Fung, Jiaxin Zhang
Computational imaging plays a pivotal role in determining hidden information from sparse measurements. A robust inverse solver is crucial to fully characterize the uncertainty induced by these measurements, as it allows for the estimation of the complete posterior of unrecoverable targets. This, in turn, facilitates a probabilistic interpretation of observational data for decision-making. In this study, we propose a deep variational framework that leverages a deep generative model to learn an approximate posterior distribution to effectively quantify image reconstruction uncertainty without the need for training data. We parameterize the target posterior using a flow-based model and minimize their Kullback-Leibler (KL) divergence to achieve accurate uncertainty estimation. To bolster stability, we introduce a robust flow-based model with bi-directional regularization and enhance expressivity through gradient boosting. Additionally, we incorporate a space-filling design to achieve substantial variance reduction on both latent prior space and target posterior space. We validate our method on several benchmark tasks and two real-world applications, namely fastMRI and black hole image reconstruction. Our results indicate that our method provides reliable and high-quality image reconstruction with robust uncertainty estimation.
Authors: Haoqi Ni, Ximiao Zhang, Min Xu, Ning Lang, Xiuzhuang Zhou
Chest X-Ray (CXR) examination is a common method for assessing thoracic diseases in clinical applications. While recent advances in deep learning have enhanced the significance of visual analysis for CXR anomaly detection, current methods often miss key cues in anomaly images crucial for identifying disease regions, as they predominantly rely on unsupervised training with normal images. This letter focuses on a more practical setup in which few-shot anomaly images with only image-level labels are available during training. For this purpose, we propose WSCXR, a weakly supervised anomaly detection framework for CXR. WSCXR firstly constructs sets of normal and anomaly image features respectively. It then refines the anomaly image features by eliminating normal region features through anomaly feature mining, thus fully leveraging the scarce yet crucial features of diseased areas. Additionally, WSCXR employs a linear mixing strategy to augment the anomaly features, facilitating the training of anomaly detector with few-shot anomaly images. Experiments on two CXR datasets demonstrate the effectiveness of our approach.
Authors: Yuya Ishikawa, Keita Takahashi, Chihiro Tsutake, Toshiaki Fujii
We propose a method for reconstructing a continuous light field of a target scene from a single observed image. Our method takes the best of two worlds: joint aperture-exposure coding for compressive light-field acquisition, and a neural radiance field (NeRF) for view synthesis. Joint aperture-exposure coding implemented in a camera enables effective embedding of 3-D scene information into an observed image, but in previous works, it was used only for reconstructing discretized light-field views. NeRF-based neural rendering enables high quality view synthesis of a 3-D scene from continuous viewpoints, but when only a single image is given as the input, it struggles to achieve satisfactory quality. Our method integrates these two techniques into an efficient and end-to-end trainable pipeline. Trained on a wide variety of scenes, our method can reconstruct continuous light fields accurately and efficiently without any test time optimization. To our knowledge, this is the first work to bridge two worlds: camera design for efficiently acquiring 3-D information and neural rendering.
Authors: Aniket Dashpute, Jiazhang Wang, James Taylor, Oliver Cossairt, Ashok Veeraraghavan, Florian Willomitzer
Event-based structured light systems have recently been introduced as an exciting alternative to conventional frame-based triangulation systems for the 3D measurements of diffuse surfaces. Important benefits include the fast capture speed and the high dynamic range provided by the event camera - albeit at the cost of lower data quality. So far, both low-accuracy event-based as well as high-accuracy frame-based 3D imaging systems are tailored to a specific surface type, such as diffuse or specular, and can not be used for a broader class of object surfaces ("mixed reflectance scenes"). In this paper, we present a novel event-based structured light system that enables fast 3D imaging of mixed reflectance scenes with high accuracy. On the captured events, we use epipolar constraints that intrinsically enable decomposing the measured reflections into diffuse, two-bounce specular, and other multi-bounce reflections. The diffuse objects in the scene are reconstructed using triangulation. Eventually, the reconstructed diffuse scene parts are used as a "display" to evaluate the specular scene parts via deflectometry. This novel procedure allows us to use the entire scene as a virtual screen, using only a scanning laser and an event camera. The resulting system achieves fast and motion-robust (14Hz) reconstructions of mixed reflectance scenes with < 500 $\mu$m accuracy. Moreover, we introduce a "superfast" capture mode (250Hz) for the 3D measurement of diffuse scenes.
Authors: Anning Li
Over the past few years, the vision transformer and its various forms have gained significance in human pose estimation. By treating image patches as tokens, transformers can capture global relationships wisely, estimate the keypoint tokens by leveraging the visual tokens, and recognize the posture of the human body. Nevertheless, global attention is computationally demanding, which poses a challenge for scaling up transformer-based methods to high-resolution features. In this paper, we introduce sparsity in both keypoint token attention and visual token attention to improve human pose estimation. Experimental results on the MPII dataset demonstrate that our model has a higher level of accuracy and proved the feasibility of the method, achieving new state-of-the-art results. The idea can also provide references for other transformer-based models.
Authors: Wentao He, Yuchen Yan, Jianfeng Ren, Ruibin Bai, Xudong Jiang
Deep neural networks have been applied to audio spectrograms for respiratory sound classification. Existing models often treat the spectrogram as a synthetic image while overlooking its physical characteristics. In this paper, a Multi-View Spectrogram Transformer (MVST) is proposed to embed different views of time-frequency characteristics into the vision transformer. Specifically, the proposed MVST splits the mel-spectrogram into different sized patches, representing the multi-view acoustic elements of a respiratory sound. These patches and positional embeddings are then fed into transformer encoders to extract the attentional information among patches through a self-attention mechanism. Finally, a gated fusion scheme is designed to automatically weigh the multi-view features to highlight the best one in a specific scenario. Experimental results on the ICBHI dataset demonstrate that the proposed MVST significantly outperforms state-of-the-art methods for classifying respiratory sounds.
Authors: Ngoc N. Tran, Lam Tran, Hoang Phan, Anh Bui, Tung Pham, Toan Tran, Dinh Phung, Trung Le
Contrastive learning (CL) is a self-supervised training paradigm that allows us to extract meaningful features without any label information. A typical CL framework is divided into two phases, where it first tries to learn the features from unlabelled data, and then uses those features to train a linear classifier with the labeled data. While a fair amount of existing theoretical works have analyzed how the unsupervised loss in the first phase can support the supervised loss in the second phase, none has examined the connection between the unsupervised loss and the robust supervised loss, which can shed light on how to construct an effective unsupervised loss for the first phase of CL. To fill this gap, our work develops rigorous theories to dissect and identify which components in the unsupervised loss can help improve the robust supervised loss and conduct proper experiments to verify our findings.
The rapid progress of Large Models (LMs) has recently revolutionized various fields of deep learning with remarkable grades, ranging from Natural Language Processing (NLP) to Computer Vision (CV). However, LMs are increasingly challenged and criticized by academia and industry due to their powerful performance but untrustworthy behavior, which urgently needs to be alleviated in reliable methods. Despite the abundance of literature on trustworthy LMs in language, a systematic survey specifically delving into the trustworthiness of LMs in vision remains absent. In order to mitigate this gap, we summarize four relevant concerns that obstruct the trustworthy usage in vision of LMs in this survey, including 1) human misuse, 2) vulnerability, 3) inherent issue and 4) interpretability. By highlighting corresponding challenge, countermeasures, and discussion in each topic, we hope this survey will facilitate readers' understanding of the field, promote alignment of LMs with human expectations and enable trustworthy LMs to serve as welfare rather than disaster for human society.
Authors: Zhenglai Li, Chang Tang, Xinwang Liu, Changdong Li, Xianju Li, Wei Zhang
Fully supervised change detection methods have achieved significant advancements in performance, yet they depend severely on acquiring costly pixel-level labels. Considering that the patch-level annotations also contain abundant information corresponding to both changed and unchanged objects in bi-temporal images, an intuitive solution is to segment the changes with patch-level annotations. How to capture the semantic variations associated with the changed and unchanged regions from the patch-level annotations to obtain promising change results is the critical challenge for the weakly supervised change detection task. In this paper, we propose a memory-supported transformer (MS-Former), a novel framework consisting of a bi-directional attention block (BAB) and a patch-level supervision scheme (PSS) tailored for weakly supervised change detection with patch-level annotations. More specifically, the BAM captures contexts associated with the changed and unchanged regions from the temporal difference features to construct informative prototypes stored in the memory bank. On the other hand, the BAM extracts useful information from the prototypes as supplementary contexts to enhance the temporal difference features, thereby better distinguishing changed and unchanged regions. After that, the PSS guides the network learning valuable knowledge from the patch-level annotations, thus further elevating the performance. Experimental results on three benchmark datasets demonstrate the effectiveness of our proposed method in the change detection task. The demo code for our work will be publicly available at \url{https://github.com/guanyuezhen/MS-Former}.
Authors: Bingnan Li, Zhitong Gao, Xuming He
Cross-modal MRI segmentation is of great value for computer-aided medical diagnosis, enabling flexible data acquisition and model generalization. However, most existing methods have difficulty in handling local variations in domain shift and typically require a significant amount of data for training, which hinders their usage in practice. To address these problems, we propose a novel adaptive domain generalization framework, which integrates a learning-free cross-domain representation based on image gradient maps and a class prior-informed test-time adaptation strategy for mitigating local domain shift. We validate our approach on two multi-modal MRI datasets with six cross-modal segmentation tasks. Across all the task settings, our method consistently outperforms competing approaches and shows a stable performance even with limited training data.
Authors: Leopold Müller, Patrick Hemmer, Moritz Queisner, Igor Sauer, Simeon Allmendinger, Johannes Jakubik, Michael Vössing, Niklas Kühl
A significant challenge in image-guided surgery is the accurate measurement task of relevant structures such as vessel segments, resection margins, or bowel lengths. While this task is an essential component of many surgeries, it involves substantial human effort and is prone to inaccuracies. In this paper, we develop a novel human-AI-based method for laparoscopic measurements utilizing stereo vision that has been guided by practicing surgeons. Based on a holistic qualitative requirements analysis, this work proposes a comprehensive measurement method, which comprises state-of-the-art machine learning architectures, such as RAFT-Stereo and YOLOv8. The developed method is assessed in various realistic experimental evaluation environments. Our results outline the potential of our method achieving high accuracies in distance measurements with errors below 1 mm. Furthermore, on-surface measurements demonstrate robustness when applied in challenging environments with textureless regions. Overall, by addressing the inherent challenges of image-guided surgery, we lay the foundation for a more robust and accurate solution for intra- and postoperative measurements, enabling more precise, safe, and efficient surgical procedures.
Authors: Aniket Roy, Maiterya Suin, Anshul Shah, Ketul Shah, Jiang Liu, Rama Chellappa
Diffusion models have advanced generative AI significantly in terms of editing and creating naturalistic images. However, efficiently improving generated image quality is still of paramount interest. In this context, we propose a generic "naturalness" preserving loss function, viz., kurtosis concentration (KC) loss, which can be readily applied to any standard diffusion model pipeline to elevate the image quality. Our motivation stems from the projected kurtosis concentration property of natural images, which states that natural images have nearly constant kurtosis values across different band-pass versions of the image. To retain the "naturalness" of the generated images, we enforce reducing the gap between the highest and lowest kurtosis values across the band-pass versions (e.g., Discrete Wavelet Transform (DWT)) of images. Note that our approach does not require any additional guidance like classifier or classifier-free guidance to improve the image quality. We validate the proposed approach for three diverse tasks, viz., (1) personalized few-shot finetuning using text guidance, (2) unconditional image generation, and (3) image super-resolution. Integrating the proposed KC loss has improved the perceptual quality across all these tasks in terms of both FID, MUSIQ score, and user evaluation.
Authors: Le Jiang, Li Yan Ma, Tie Yong Zeng, Shi Hui Ying
Partially supervised segmentation is a label-saving method based on datasets with fractional classes labeled and intersectant. However, it is still far from landing on real-world medical applications due to privacy concerns and data heterogeneity. As a remedy without privacy leakage, federated partially supervised segmentation (FPSS) is formulated in this work. The main challenges for FPSS are class heterogeneity and client drift. We propose a Unified Federated Partially-labeled Segmentation (UFPS) framework to segment pixels within all classes for partially-annotated datasets by training a totipotential global model without class collision. Our framework includes Unified Label Learning and sparsed Unified Sharpness Aware Minimization for unification of class and feature space, respectively. We find that vanilla combinations for traditional methods in partially supervised segmentation and federated learning are mainly hampered by class collision through empirical study. Our comprehensive experiments on real medical datasets demonstrate better deconflicting and generalization ability of UFPS compared with modified methods.
Authors: Chihiro Noguchi, Shun Fukuda, Masao Yamanaka
Scene Text Image Super-resolution (STISR) has recently achieved great success as a preprocessing method for scene text recognition. STISR aims to transform blurred and noisy low-resolution (LR) text images in real-world settings into clear high-resolution (HR) text images suitable for scene text recognition. In this study, we leverage text-conditional diffusion models (DMs), known for their impressive text-to-image synthesis capabilities, for STISR tasks. Our experimental results revealed that text-conditional DMs notably surpass existing STISR methods. Especially when texts from LR text images are given as input, the text-conditional DMs are able to produce superior quality super-resolution text images. Utilizing this capability, we propose a novel framework for synthesizing LR-HR paired text image datasets. This framework consists of three specialized text-conditional DMs, each dedicated to text image synthesis, super-resolution, and image degradation. These three modules are vital for synthesizing distinct LR and HR paired images, which are more suitable for training STISR methods. Our experiments confirmed that these synthesized image pairs significantly enhance the performance of STISR methods in the TextZoom evaluation.
Authors: Stefan Becker, Jens Bayer, Ronny Hug, Wolfgang Hübner, Michael Arens
Data pooling offers various advantages, such as increasing the sample size, improving generalization, reducing sampling bias, and addressing data sparsity and quality, but it is not straightforward and may even be counterproductive. Assessing the effectiveness of pooling datasets in a principled manner is challenging due to the difficulty in estimating the overall information content of individual datasets. Towards this end, we propose incorporating a data source prediction module into standard object detection pipelines. The module runs with minimal overhead during inference time, providing additional information about the data source assigned to individual detections. We show the benefits of the so-called dataset affinity score by automatically selecting samples from a heterogeneous pool of vehicle datasets. The results show that object detectors can be trained on a significantly sparser set of training samples without losing detection accuracy.
Authors: Jan Roßbach (Heinrich-Heine-Universität Düsseldorf), Michael Leuschel (Heinrich-Heine-Universität Düsseldorf)
There is considerable industrial interest in integrating AI techniques into railway systems, notably for fully autonomous train systems. The KI-LOK research project is involved in developing new methods for certifying such AI-based systems. Here we explore the utility of a certified control architecture for a runtime monitor that prevents false positive detection of traffic signs in an AI-based perception system. The monitor uses classical computer vision algorithms to check if the signs -- detected by an AI object detection model -- fit predefined specifications. We provide such specifications for some critical signs and integrate a Python prototype of the monitor with a popular object detection model to measure relevant performance metrics on generated data. Our initial results are promising, achieving considerable precision gains with only minor recall reduction; however, further investigation into generalization possibilities will be necessary.
Authors: Jingnan Gao, Zhuo Chen, Yichao Yan, Bowen Pan, Zhe Wang, Jiangjing Lyu, Xiaokang Yang
Reconstructing real-world 3D objects has numerous applications in computer vision, such as virtual reality, video games, and animations. Ideally, 3D reconstruction methods should generate high-fidelity results with 3D consistency in real-time. Traditional methods match pixels between images using photo-consistency constraints or learned features, while differentiable rendering methods like Neural Radiance Fields (NeRF) use surface-based representations or differentiable volume rendering to generate high-fidelity scenes. However, these methods require excessive runtime for rendering, making them impractical for daily applications. To address these challenges, we present $\textbf{EvaSurf}$, an $\textbf{E}$fficient $\textbf{V}$iew-$\textbf{A}$ware Implicit Textured $\textbf{Surf}$ace Reconstruction method on Mobile Devices. In our method, we first employ an efficient surface-based model with a multi-view supervision module to ensure accurate mesh creation. To enable high-fidelity rendering, we learn an implicit texture embedded with a set of Gaussian lobes to capture view-dependent information. Furthermore, With the explicit geometry and the implicit texture, we can employ a lightweight neural shader to reduce the expense of computation and further support real-time rendering on common mobile devices. Extensive experiments demonstrate that our method can reconstruct high-quality appearance and accurate mesh on both synthetic and real-world datasets. Moreover, our method can be trained in just 1-2 hours using a single GPU and run on mobile devices at over 40FPS (Frames Per Second), with a final package required for rendering taking up only 40-50 MB.
Authors: Liulei Li, Jianan Wei, Wenguan Wang, Yi Yang
The interaction decoder utilized in prevalent Transformer-based HOI detectors typically accepts pre-composed human-object pairs as inputs. Though achieving remarkable performance, such paradigm lacks feasibility and cannot explore novel combinations over entities during decoding. We present L OGIC HOI, a new HOI detector that leverages neural-logic reasoning and Transformer to infer feasible interactions between entities. Specifically, we modify the self-attention mechanism in vanilla Transformer, enabling it to reason over the <human, action, object> triplet and constitute novel interactions. Meanwhile, such reasoning process is guided by two crucial properties for understanding HOI: affordances (the potential actions an object can facilitate) and proxemics (the spatial relations between humans and objects). We formulate these two properties in first-order logic and ground them into continuous space to constrain the learning process of our approach, leading to improved performance and zero-shot generalization capabilities. We evaluate L OGIC HOI on V-COCO and HICO-DET under both normal and zero-shot setups, achieving significant improvements over existing methods.
Authors: Zhen Sun, Huan Xu, Jinlin Wu, Zhen Chen, Zhen Lei, Hongbin Liu
In surgical procedures, correct instrument counting is essential. Instance segmentation is a location method that locates not only an object's bounding box but also each pixel's specific details. However, obtaining mask-level annotations is labor-intensive in instance segmentation. To address this issue, we propose a novel yet effective weakly-supervised surgical instrument instance segmentation approach, named Point-based Weakly-supervised Instance Segmentation (PWISeg). PWISeg adopts an FCN-based architecture with point-to-box and point-to-mask branches to model the relationships between feature points and bounding boxes, as well as feature points and segmentation masks on FPN, accomplishing instrument detection and segmentation jointly in a single model. Since mask level annotations are hard to available in the real world, for point-to-mask training, we introduce an unsupervised projection loss, utilizing the projected relation between predicted masks and bboxes as supervision signal. On the other hand, we annotate a few pixels as the key pixel for each instrument. Based on this, we further propose a key pixel association loss and a key pixel distribution loss, driving the point-to-mask branch to generate more accurate segmentation predictions. To comprehensively evaluate this task, we unveil a novel surgical instrument dataset with manual annotations, setting up a benchmark for further research. Our comprehensive research trial validated the superior performance of our PWISeg. The results show that the accuracy of surgical instrument segmentation is improved, surpassing most methods of instance segmentation via weakly supervised bounding boxes. This improvement is consistently observed in our proposed dataset and when applied to the public HOSPI-Tools dataset.
Authors: Ricardo Montoya-del-Angel, Karla Sam-Millan, Joan C Vilanova, Robert Martí
Generative models are used as an alternative data augmentation technique to alleviate the data scarcity problem faced in the medical imaging field. Diffusion models have gathered special attention due to their innovative generation approach, the high quality of the generated images and their relatively less complex training process compared with Generative Adversarial Networks. Still, the implementation of such models in the medical domain remains at early stages. In this work, we propose exploring the use of diffusion models for the generation of high quality full-field digital mammograms using state-of-the-art conditional diffusion pipelines. Additionally, we propose using stable diffusion models for the inpainting of synthetic lesions on healthy mammograms. We introduce MAM-E, a pipeline of generative models for high quality mammography synthesis controlled by a text prompt and capable of generating synthetic lesions on specific regions of the breast. Finally, we provide quantitative and qualitative assessment of the generated images and easy-to-use graphical user interfaces for mammography synthesis.
Authors: Ardavan Modarres, Erfan Ebrahim Esfahani, Mahsa Bahrami
Diagnosis of breast cancer malignancy at the early stages is a crucial step for controlling its side effects. Histopathological analysis provides a unique opportunity for malignant breast cancer detection. However, such a task would be tedious and time-consuming for the histopathologists. Deep Neural Networks enable us to learn informative features directly from raw histopathological images without manual feature extraction. Although Convolutional Neural Networks (CNNs) have been the dominant architectures in the computer vision realm, Transformer-based architectures have shown promising results in different computer vision tasks. Although harnessing the capability of Transformer-based architectures for medical image analysis seems interesting, these architectures are large, have a significant number of trainable parameters, and require large datasets to be trained on, which are usually rare in the medical domain. It has been claimed and empirically proved that at least part of the superior performance of Transformer-based architectures in Computer Vision domain originates from patch embedding operation. In this paper, we borrowed the previously introduced idea of integrating a fully Convolutional Neural Network architecture with Patch Embedding operation and presented an efficient CNN architecture for breast cancer malignancy detection from histopathological images. Despite the number of parameters that is significantly smaller than other methods, the accuracy performance metrics achieved 97.65%, 98.92%, 99.21%, and 98.01% for 40x, 100x, 200x, and 400x magnifications respectively. We took a step forward and modified the architecture using Group Convolution and Channel Shuffling ideas and reduced the number of trainable parameters even more with a negligible decline in performance and achieved 95.42%, 98.16%, 96.05%, and 97.92% accuracy for the mentioned magnifications respectively.
Authors: Raphael Schäfer, Till Nicke, Henning Höfener, Annkristin Lange, Dorit Merhof, Friedrich Feuerhake, Volkmar Schulz, Johannes Lotz, Fabian Kiessling
Foundational models, pretrained on a large scale, have demonstrated substantial success across non-medical domains. However, training these models typically requires large, comprehensive datasets, which contrasts with the smaller and more heterogeneous datasets common in biomedical imaging. Here, we propose a multi-task learning strategy that decouples the number of training tasks from memory requirements. We trained a Universal bioMedical PreTrained model (UMedPT) on a multi-task database including tomographic, microscopic, and X-ray images, with various labelling strategies such as classification, segmentation, and object detection. The UMedPT foundational model outperformed ImageNet pretraining and the previous state-of-the-art models. For tasks related to the pretraining database, it maintained its performance with only 1% of the original training data and without fine-tuning. For out-of-domain tasks it required not more than 50% of the original training data. In an external independent validation imaging features extracted using UMedPT proved to be a new standard for cross-center transferability.
Authors: Dao Duy Tung, Ho Xuan Hung
This study addresses the challenge of accurately seg-menting rusted areas on painted construction surfaces. A method leveraging digital image processing is explored to calculate the percentage of rust present on painted coatings. The proposed segmentation approach is based on the HSV color model. To equalize luminosity and mitigate the influence of illumination, a fundamental model of single-scale Retinex is applied specifically to the saturation component.
Subsequently, the image undergoes further processing, involv-ing manual color filtering. This step is crucial for refining the identification of rusted regions. To enhance precision and filter out noise, the pixel areas selected through color filtering are subjected to the DBScan algorithm. This multi-step process aims to achieve a robust segmentation of rusted areas on painted construction surfaces, providing a valuable contribution to the field of corrosion detection and analysis.
Authors: Abubakr Shafique, Saghir Alfasly, Areej Alsaafin, Peyman Nejat, Jibran A. Khan, H.R.Tizhoosh
Whole slide images (WSIs) are massive digital pathology files illustrating intricate tissue structures. Selecting a small, representative subset of patches from each WSI is essential yet challenging. Therefore, following the "Divide & Conquer" approach becomes essential to facilitate WSI analysis including the classification and the WSI matching in computational pathology. To this end, we propose a novel method termed "Selection of Distinct Morphologies" (SDM) to choose a subset of WSI patches. The aim is to encompass all inherent morphological variations within a given WSI while simultaneously minimizing the number of selected patches to represent these variations, ensuring a compact yet comprehensive set of patches. This systematically curated patch set forms what we term a "montage". We assess the representativeness of the SDM montage across various public and private histopathology datasets. This is conducted by using the leave-one-out WSI search and matching evaluation method, comparing it with the state-of-the-art Yottixel's mosaic. SDM demonstrates remarkable efficacy across all datasets during its evaluation. Furthermore, SDM eliminates the necessity for empirical parameterization, a crucial aspect of Yottixel's mosaic, by inherently optimizing the selection process to capture the distinct morphological features within the WSI.
Authors: Yuan Shi, Bin Xia, Rui Zhu, Qingmin Liao, Wenming Yang
Color-guided depth map super-resolution (CDSR) improve the spatial resolution of a low-quality depth map with the corresponding high-quality color map, benefiting various applications such as 3D reconstruction, virtual reality, and augmented reality. While conventional CDSR methods typically rely on convolutional neural networks or transformers, diffusion models (DMs) have demonstrated notable effectiveness in high-level vision tasks. In this work, we present a novel CDSR paradigm that utilizes a diffusion model within the latent space to generate guidance for depth map super-resolution. The proposed method comprises a guidance generation network (GGN), a depth map super-resolution network (DSRN), and a guidance recovery network (GRN). The GGN is specifically designed to generate the guidance while managing its compactness. Additionally, we integrate a simple but effective feature fusion module and a transformer-style feature extraction module into the DSRN, enabling it to leverage guided priors in the extraction, fusion, and reconstruction of multi-model images. Taking into account both accuracy and efficiency, our proposed method has shown superior performance in extensive experiments when compared to state-of-the-art methods. Our codes will be made available at https://github.com/shiyuan7/DSR-Diff.
Authors: Stefanos-Iordanis Papadopoulos, Christos Koutlis, Symeon Papadopoulos, Panagiotis C. Petrantonakis
Online misinformation is often multimodal in nature, i.e., it is caused by misleading associations between texts and accompanying images. To support the fact-checking process, researchers have been recently developing automatic multimodal methods that gather and analyze external information, evidence, related to the image-text pairs under examination. However, prior works assumed all collected evidence to be relevant. In this study, we introduce a "Relevant Evidence Detection" (RED) module to discern whether each piece of evidence is relevant, to support or refute the claim. Specifically, we develop the "Relevant Evidence Detection Directed Transformer" (RED-DOT) and explore multiple architectural variants (e.g., single or dual-stage) and mechanisms (e.g., "guided attention"). Extensive ablation and comparative experiments demonstrate that RED-DOT achieves significant improvements over the state-of-the-art on the VERITE benchmark by up to 28.5%. Furthermore, our evidence re-ranking and element-wise modality fusion led to RED-DOT achieving competitive and even improved performance on NewsCLIPings+, without the need for numerous evidence or multiple backbone encoders. Finally, our qualitative analysis demonstrates that the proposed "guided attention" module has the potential to enhance the architecture's interpretability. We release our code at: https://github.com/stevejpapad/relevant-evidence-detection
Authors: Amine Bechar, Youssef Elmir, Rafik Medjoudj, Yassine Himeur, Abbes Amira
This paper discusses the role of Transfer Learning (TL) and transformers in cancer detection based on image analysis. With the enormous evolution of cancer patients, the identification of cancer cells in a patient's body has emerged as a trend in the field of Artificial Intelligence (AI). This process involves analyzing medical images, such as Computed Tomography (CT) scans and Magnetic Resonance Imaging (MRIs), to identify abnormal growths that may help in cancer detection. Many techniques and methods have been realized to improve the quality and performance of cancer classification and detection, such as TL, which allows the transfer of knowledge from one task to another with the same task or domain. TL englobes many methods, particularly those used in image analysis, such as transformers and Convolutional Neural Network (CNN) models trained on the ImageNet dataset. This paper analyzes and criticizes each method of TL based on image analysis and compares the results of each method, showing that transformers have achieved the best results with an accuracy of 97.41% for colon cancer detection and 94.71% for Histopathological Lung cancer. Future directions for cancer detection based on image analysis are also discussed.
Authors: Li Kevin Wenliang, Ben Moran
How do score-based generative models (SBMs) learn the data distribution supported on a low-dimensional manifold? We investigate the score model of a trained SBM through its linear approximations and subspaces spanned by local feature vectors. During diffusion as the noise decreases, the local dimensionality increases and becomes more varied between different sample sequences. Importantly, we find that the learned vector field mixes samples by a non-conservative field within the manifold, although it denoises with normal projections as if there is an energy function in off-manifold directions. At each noise level, the subspace spanned by the local features overlap with an effective density function. These observations suggest that SBMs can flexibly mix samples with the learned score field while carefully maintaining a manifold-like structure of the data distribution.
Authors: Geoff Klein, Michael Hardisty, Cari Whyne, Anne L. Martel
Vertebral detection and segmentation are critical steps for treatment planning in spine surgery and radiation therapy. Accurate identification and segmentation are complicated in imaging that does not include the full spine, in cases with variations in anatomy (T13 and/or L6 vertebrae), and in the presence of fracture or hardware. This paper proposes VertDetect, a fully automated end-to-end 3D vertebral instance segmentation Convolutional Neural Network (CNN) model to predict vertebral level labels and segmentations for all vertebrae present in a CT scan. The utilization of a shared CNN backbone provides the detection and segmentation branches of the network with feature maps containing both spinal and vertebral level information. A Graph Convolutional Network (GCN) layer is used to improve vertebral labelling by using the known structure of the spine. This model achieved a Dice Similarity Coefficient (DSC) of 0.883 (95% CI, 0.843-0.906) and 0.882 (95% CI, 0.835-0.909) in the VerSe 2019 and 0.868 (95\% CI, 0.834-0.890) and 0.869 (95\% CI, 0.832-0.891) in the VerSe 2020 public and hidden test sets, respectively. This model achieved state-of-the-art performance for an end-to-end architecture, whose design facilitates the extraction of features that can be subsequently used for downstream tasks.
Authors: Xingjian Luo, You Pang, Zhen Chen, Jinlin Wu, Zongmin Zhang, Zhen Lei, Hongbin Liu
Surgical phase recognition is crucial to providing surgery understanding in smart operating rooms. Despite great progress in automatic surgical phase recognition, most existing methods are still restricted by two problems. First, these methods cannot capture discriminative visual features for each frame and motion information with simple 2D networks. Second, the frame-by-frame recognition paradigm degrades the performance due to unstable predictions within each phase, termed as phase shaking. To address these two challenges, we propose a Surgical Phase LocAlization Network, named SurgPLAN, to facilitate a more accurate and stable surgical phase recognition with the principle of temporal detection. Specifically, we first devise a Pyramid SlowFast (PSF) architecture to serve as the visual backbone to capture multi-scale spatial and temporal features by two branches with different frame sampling rates. Moreover, we propose a Temporal Phase Localization (TPL) module to generate the phase prediction based on temporal region proposals, which ensures accurate and consistent predictions within each surgical phase. Extensive experiments confirm the significant advantages of our SurgPLAN over frame-by-frame approaches in terms of both accuracy and stability.
Authors: Jiansong Zhang, Peizhong Liu
In recent years, self-supervised contrastive learning has emerged as a distinguished paradigm in the artificial intelligence landscape. It facilitates unsupervised feature learning through contrastive delineations at the instance level. However, crafting an effective self-supervised paradigm remains a pivotal challenge within this field. This paper delves into two crucial factors impacting self-supervised contrastive learning-bach size and pretext tasks, and from a data processing standpoint, proposes an adaptive technique of batch fusion. The proposed method, via dimensionality reduction and reconstruction of batch data, enables formerly isolated individual data to partake in intra-batch communication through the Embedding Layer. Moreover, it adaptively amplifies the self-supervised feature encoding capability as the training progresses. We conducted a linear classification test of this method based on the classic contrastive learning framework on ImageNet-1k. The empirical findings illustrate that our approach achieves state-of-the-art performance under equitable comparisons. Benefiting from its "plug-and-play" characteristics, we further explored other contrastive learning methods. On the ImageNet-100, compared to the original performance, the top1 has seen a maximum increase of 1.25%. We suggest that the proposed method may contribute to the advancement of data-driven self-supervised learning research, bringing a fresh perspective to this community.
Authors: Atul Kumar Sinha, Francois Fleuret
The Earth Mover's Distance (EMD) is the measure of choice between point clouds. However the computational cost to compute it makes it prohibitive as a training loss, and the standard approach is to use a surrogate such as the Chamfer distance. We propose an attention-based model to compute an accurate approximation of the EMD that can be used as a training loss for generative models. To get the necessary accurate estimation of the gradients we train our model to explicitly compute the matching between point clouds instead of EMD itself. We cast this new objective as the estimation of an attention matrix that approximates the ground truth matching matrix. Experiments show that this model provides an accurate estimate of the EMD and its gradient with a wall clock speed-up of more than two orders of magnitude with respect to the exact Hungarian matching algorithm and one order of magnitude with respect to the standard approximate Sinkhorn algorithm, allowing in particular to train a point cloud VAE with the EMD itself. Extensive evaluation show the remarkable behaviour of this model when operating out-of-distribution, a key requirement for a distance surrogate. Finally, the model generalizes very well to point clouds during inference several times larger than during training.
Authors: Matic Fučka, Vitjan Zavrtanik, Danijel Skočaj
Surface anomaly detection is a vital component in manufacturing inspection. Reconstructive anomaly detection methods restore the normal appearance of an object, ideally modifying only the anomalous regions. Due to the limitations of commonly used reconstruction architectures, the produced reconstructions are often poor and either still contain anomalies or lack details in anomaly-free regions. Recent reconstructive methods adopt diffusion models, however with the standard diffusion process the problems are not adequately addressed. We propose a novel transparency-based diffusion process, where the transparency of anomalous regions is progressively increased, restoring their normal appearance accurately and maintaining the appearance of anomaly-free regions without loss of detail. We propose TRANSparency DifFUSION (TransFusion), a discriminative anomaly detection method that implements the proposed diffusion process, enabling accurate downstream anomaly detection. TransFusion achieves state-of-the-art performance on both the VisA and the MVTec AD datasets, with an image-level AUROC of 98.5% and 99.2%, respectively.
Authors: Kevin Bui, Yifei Lou, Fredrick Park, Jack Xin
In this paper, we design an efficient, multi-stage image segmentation framework that incorporates a weighted difference of anisotropic and isotropic total variation (AITV). The segmentation framework generally consists of two stages: smoothing and thresholding, thus referred to as SaT. In the first stage, a smoothed image is obtained by an AITV-regularized Mumford-Shah (MS) model, which can be solved efficiently by the alternating direction method of multipliers (ADMM) with a closed-form solution of a proximal operator of the $\ell_1 -\alpha \ell_2$ regularizer. Convergence of the ADMM algorithm is analyzed. In the second stage, we threshold the smoothed image by $K$-means clustering to obtain the final segmentation result. Numerical experiments demonstrate that the proposed segmentation framework is versatile for both grayscale and color images, efficient in producing high-quality segmentation results within a few seconds, and robust to input images that are corrupted with noise, blur, or both. We compare the AITV method with its original convex TV and nonconvex TV$^p (0<p<1)$ counterparts, showcasing the qualitative and quantitative advantages of our proposed method.
Authors: Hao Quan, Xingyu Li, Weixing Chen, Qun Bai, Mingchen Zou, Ruijie Yang, Tingting Zheng, Ruiqun Qi, Xinghua Gao, Xiaoyu Cui
Based on digital pathology slice scanning technology, artificial intelligence algorithms represented by deep learning have achieved remarkable results in the field of computational pathology. Compared to other medical images, pathology images are more difficult to annotate, and thus, there is an extreme lack of available datasets for conducting supervised learning to train robust deep learning models. In this paper, we propose a self-supervised learning (SSL) model, the global contrast-masked autoencoder (GCMAE), which can train the encoder to have the ability to represent local-global features of pathological images, also significantly improve the performance of transfer learning across data sets. In this study, the ability of the GCMAE to learn migratable representations was demonstrated through extensive experiments using a total of three different disease-specific hematoxylin and eosin (HE)-stained pathology datasets: Camelyon16, NCTCRC and BreakHis. In addition, this study designed an effective automated pathology diagnosis process based on the GCMAE for clinical applications. The source code of this paper is publicly available at https://github.com/StarUniversus/gcmae.
Authors: Xiaodong Guo, Longhui Li, Dingyue Chang, Peng He, Peng Feng, Hengyong Yu, Weiwen Wu
Spectral computed tomography based on a photon-counting detector (PCD) attracts more and more attentions since it has the capability to provide more accurate identification and quantitative analysis for biomedical materials. The limited number of photons within narrow energy bins leads to imaging results of low signal-noise ratio. The existing supervised deep reconstruction networks for CT reconstruction are difficult to address these challenges because it is usually impossible to acquire noise-free clinical images with clear structures as references. In this paper, we propose an iterative deep reconstruction network to synergize unsupervised method and data priors into a unified framework, named as Spectral2Spectral. Our Spectral2Spectral employs an unsupervised deep training strategy to obtain high-quality images from noisy data in an end-to-end fashion. The structural similarity prior within image-spectral domain is refined as a regularization term to further constrain the network training. The weights of neural network are automatically updated to capture image features and structures within the iterative process. Three large-scale preclinical datasets experiments demonstrate that the Spectral2spectral reconstructs better image quality than other the state-of-the-art methods.
Authors: Biling Wang, Michael Dohopolski, Ti Bai, Junjie Wu, Raquibul Hannan, Neil Desai, Aurelie Garant, Daniel Yang, Dan Nguyen, Mu-Han Lin, Robert Timmerman, Xinlei Wang, Steve Jiang
We evaluated the temporal performance of a deep learning (DL) based artificial intelligence (AI) model for auto segmentation in prostate radiotherapy, seeking to correlate its efficacy with changes in clinical landscapes. Our study involved 1328 prostate cancer patients who underwent definitive radiotherapy from January 2006 to August 2022 at the University of Texas Southwestern Medical Center. We trained a UNet based segmentation model on data from 2006 to 2011 and tested it on data from 2012 to 2022 to simulate real world clinical deployment. We measured the model performance using the Dice similarity coefficient (DSC), visualized the trends in contour quality using exponentially weighted moving average (EMA) curves. Additionally, we performed Wilcoxon Rank Sum Test to analyze the differences in DSC distributions across distinct periods, and multiple linear regression to investigate the impact of various clinical factors. The model exhibited peak performance in the initial phase (from 2012 to 2014) for segmenting the prostate, rectum, and bladder. However, we observed a notable decline in performance for the prostate and rectum after 2015, while bladder contour quality remained stable. Key factors that impacted the prostate contour quality included physician contouring styles, the use of various hydrogel spacer, CT scan slice thickness, MRI-guided contouring, and using intravenous (IV) contrast. Rectum contour quality was influenced by factors such as slice thickness, physician contouring styles, and the use of various hydrogel spacers. The bladder contour quality was primarily affected by using IV contrast. This study highlights the challenges in maintaining AI model performance consistency in a dynamic clinical setting. It underscores the need for continuous monitoring and updating of AI models to ensure their ongoing effectiveness and relevance in patient care.
Authors: Nalini M. Singh, Neel Dey, Malte Hoffmann, Bruce Fischl, Elfar Adalsteinsson, Robert Frost, Adrian V. Dalca, Polina Golland
Motion artifacts are a pervasive problem in MRI, leading to misdiagnosis or mischaracterization in population-level imaging studies. Current retrospective rigid intra-slice motion correction techniques jointly optimize estimates of the image and the motion parameters. In this paper, we use a deep network to reduce the joint image-motion parameter search to a search over rigid motion parameters alone. Our network produces a reconstruction as a function of two inputs: corrupted k-space data and motion parameters. We train the network using simulated, motion-corrupted k-space data generated with known motion parameters. At test-time, we estimate unknown motion parameters by minimizing a data consistency loss between the motion parameters, the network-based image reconstruction given those parameters, and the acquired measurements. Intra-slice motion correction experiments on simulated and realistic 2D fast spin echo brain MRI achieve high reconstruction fidelity while providing the benefits of explicit data consistency optimization. Our code is publicly available at https://www.github.com/nalinimsingh/neuroMoCo.
Authors: Jiahua Dong, Hongliu Li, Yang Cong, Gan Sun, Yulun Zhang, Luc Van Gool
Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data categories of FL framework are known and fixed in advance. Moreover, some new local clients that collect novel categories unseen by other clients may be introduced to FL training irregularly. These issues render global model to undergo catastrophic forgetting on old categories, when local clients receive new categories consecutively under limited memory of storing old categories. To tackle the above issues, we propose a novel Local-Global Anti-forgetting (LGA) model. It ensures no local clients are left behind as they learn new classes continually, by addressing local and global catastrophic forgetting. Specifically, considering tackling class imbalance of local client to surmount local forgetting, we develop a category-balanced gradient-adaptive compensation loss and a category gradient-induced semantic distillation loss. They can balance heterogeneous forgetting speeds of hard-to-forget and easy-to-forget old categories, while ensure consistent class-relations within different tasks. Moreover, a proxy server is designed to tackle global forgetting caused by Non-IID class imbalance between different clients. It augments perturbed prototype images of new categories collected from local clients via self-supervised prototype augmentation, thus improving robustness to choose the best old global model for local-side semantic distillation loss. Experiments on representative datasets verify superior performance of our model against comparison methods. The code is available at https://github.com/JiahuaDong/LGA.
Authors: Erdi Kara, George Zhang, Joseph J. Williams, Gonzalo Ferrandez-Quinto, Leviticus J. Rhoden, Maximilian Kim, J. Nathan Kutz, Aminur Rahman
We present a deep-learning based tracking objects of interest in walking droplet and granular intruder experiments. In a typical walking droplet experiment, a liquid droplet, known as \textit{walker}, propels itself laterally on the free surface of a vibrating bath of the same liquid. This motion is the result of the interaction between the droplets and the surface waves generated by the droplet itself after each successive bounce. A walker can exhibit a highly irregular trajectory over the course of its motion, including rapid acceleration and complex interactions with the other walkers present in the same bath. In analogy with the hydrodynamic experiments, the granular matter experiments consist of a vibrating bath of very small solid particles and a larger solid \textit{intruder}. Like the fluid droplets, the intruder interacts with and travels the domain due to the waves of the bath but tends to move much slower and much less smoothly than the droplets. When multiple intruders are introduced, they also exhibit complex interactions with each other. We leverage the state-of-art object detection model YOLO and the Hungarian Algorithm to accurately extract the trajectory of a walker or intruder in real-time. Our proposed methodology is capable of tracking individual walker(s) or intruder(s) in digital images acquired from a broad spectrum of experimental settings and does not suffer from any identity-switch issues. Thus, the deep learning approach developed in this work could be used to automatize the efficient, fast and accurate extraction of observables of interests in walking droplet and granular flow experiments. Such extraction capabilities are critically enabling for downstream tasks such as building data-driven dynamical models for the coarse-grained dynamics and interactions of the objects of interest.
Authors: Tiago Cortinhal, Eren Erdal Aksoy
This work presents a new depth- and semantics-aware conditional generative model, named TITAN-Next, for cross-domain image-to-image translation in a multi-modal setup between LiDAR and camera sensors. The proposed model leverages scene semantics as a mid-level representation and is able to translate raw LiDAR point clouds to RGB-D camera images by solely relying on semantic scene segments. We claim that this is the first framework of its kind and it has practical applications in autonomous vehicles such as providing a fail-safe mechanism and augmenting available data in the target image domain. The proposed model is evaluated on the large-scale and challenging Semantic-KITTI dataset, and experimental findings show that it considerably outperforms the original TITAN-Net and other strong baselines by 23.7$\%$ margin in terms of IoU.
Authors: Ruiqi Xian, Xijun Wang, Dinesh Manocha
We present a novel approach for action recognition in UAV videos. Our formulation is designed to handle occlusion and viewpoint changes caused by the movement of a UAV. We use the concept of mutual information to compute and align the regions corresponding to human action or motion in the temporal domain. This enables our recognition model to learn from the key features associated with the motion. We also propose a novel frame sampling method that uses joint mutual information to acquire the most informative frame sequence in UAV videos. We have integrated our approach with X3D and evaluated the performance on multiple datasets. In practice, we achieve 18.9% improvement in Top-1 accuracy over current state-of-the-art methods on UAV-Human(Li et al., 2021), 7.3% improvement on Drone-Action(Perera et al., 2019), and 7.16% improvement on NEC Drones(Choi et al., 2020).
Authors: Nanqing Liu, Xun Xu, Turgay Celik, Zongxin Gan, Heng-Chao Li
Object detection in remote sensing images relies on a large amount of labeled data for training. However, the increasing number of new categories and class imbalance make exhaustive annotation impractical. Few-shot object detection (FSOD) addresses this issue by leveraging meta-learning on seen base classes and fine-tuning on novel classes with limited labeled samples. Nonetheless, the substantial scale and orientation variations of objects in remote sensing images pose significant challenges to existing few-shot object detection methods. To overcome these challenges, we propose integrating a feature pyramid network and utilizing prototype features to enhance query features, thereby improving existing FSOD methods. We refer to this modified FSOD approach as a Strong Baseline, which has demonstrated significant performance improvements compared to the original baselines. Furthermore, we tackle the issue of spatial misalignment caused by orientation variations between the query and support images by introducing a Transformation-Invariant Network (TINet). TINet ensures geometric invariance and explicitly aligns the features of the query and support branches, resulting in additional performance gains while maintaining the same inference speed as the Strong Baseline. Extensive experiments on three widely used remote sensing object detection datasets, i.e., NWPU VHR-10.v2, DIOR, and HRRSD demonstrated the effectiveness of the proposed method.
Authors: Yanchen Wang, Adam Turnbull, Yunlong Xu, Kathi Heffner, Feng Vankee Lin, Ehsan Adeli
Computerized cognitive training (CCT) is a scalable, well-tolerated intervention that has promise for slowing cognitive decline. Outcomes from CCT are limited by a lack of effective engagement, which is decreased by factors such as mental fatigue, particularly in older adults at risk for dementia. There is a need for scalable, automated measures that can monitor mental fatigue during CCT. Here, we develop and validate a novel Recurrent Video Transformer (RVT) method for monitoring real-time mental fatigue in older adults with mild cognitive impairment from video-recorded facial gestures during CCT. The RVT model achieved the highest balanced accuracy(78%) and precision (0.82) compared to the prior state-of-the-art models for binary and multi-class classification of mental fatigue and was additionally validated via significant association (p=0.023) with CCT reaction time. By leveraging dynamic temporal information, the RVT model demonstrates the potential to accurately measure real-time mental fatigue, laying the foundation for future personalized CCT that increase effective engagement.
Authors: Georg Siedel, Weijia Shao, Silvia Vock, Andrey Morozov
Robustness is a fundamental property of machine learning classifiers to achieve safety and reliability. In the fields of adversarial robustness and formal robustness verification of image classification models, robustness is commonly defined as the stability to all input variations within an Lp-norm distance. However, robustness to random corruptions is usually improved and evaluated using variations observed in the real-world, while mathematically defined Lp-norm corruptions are rarely considered. This study investigates the use of random Lp-norm corruptions to augment the training and test data of image classifiers. We adapt an approach from the field of adversarial robustness to assess the model robustness to imperceptible random corruptions. We empirically and theoretically investigate whether robustness is transferable across different Lp-norms and derive conclusions on which Lp-norm corruptions a model should be trained and evaluated on. We find that training data augmentation with L0-norm corruptions improves corruption robustness while maintaining accuracy compared to standard training and when applied on top of selected state-of-the-art data augmentation techniques.
Authors: Tong Xu, Micol Spitale, Hao Tang, Lu Liu, Hatice Gunes, Siyang Song
Generating facial reactions in a human-human dyadic interaction is complex and highly dependent on the context since more than one facial reactions can be appropriate for the speaker's behaviour. This has challenged existing machine learning (ML) methods, whose training strategies enforce models to reproduce a specific (not multiple) facial reaction from each input speaker behaviour. This paper proposes the first multiple appropriate facial reaction generation framework that re-formulates the one-to-many mapping facial reaction generation problem as a one-to-one mapping problem. This means that we approach this problem by considering the generation of a distribution of the listener's appropriate facial reactions instead of multiple different appropriate facial reactions, i.e., 'many' appropriate facial reaction labels are summarised as 'one' distribution label during training. Our model consists of a perceptual processor, a cognitive processor, and a motor processor. The motor processor is implemented with a novel Reversible Multi-dimensional Edge Graph Neural Network (REGNN). This allows us to obtain a distribution of appropriate real facial reactions during the training process, enabling the cognitive processor to be trained to predict the appropriate facial reaction distribution. At the inference stage, the REGNN decodes an appropriate facial reaction by using this distribution as input. Experimental results demonstrate that our approach outperforms existing models in generating more appropriate, realistic, and synchronized facial reactions. The improved performance is largely attributed to the proposed appropriate facial reaction distribution learning strategy and the use of a REGNN. The code is available at https://github.com/TongXu-05/REGNN-Multiple-Appropriate-Facial-Reaction-Generation.
Authors: Noam Rotstein, David Bensaid, Shaked Brody, Roy Ganz, Ron Kimmel
The advent of vision-language pre-training techniques enhanced substantial progress in the development of models for image captioning. However, these models frequently produce generic captions and may omit semantically important image details. This limitation can be traced back to the image-text datasets; while their captions typically offer a general description of image content, they frequently omit salient details. Considering the magnitude of these datasets, manual reannotation is impractical, emphasizing the need for an automated approach. To address this challenge, we leverage existing captions and explore augmenting them with visual details using "frozen" vision experts including an object detector, an attribute recognizer, and an Optical Character Recognizer (OCR). Our proposed method, FuseCap, fuses the outputs of such vision experts with the original captions using a large language model (LLM), yielding comprehensive image descriptions. We automatically curate a training set of 12M image-enriched caption pairs. These pairs undergo extensive evaluation through both quantitative and qualitative analyses. Subsequently, this data is utilized to train a captioning generation BLIP-based model. This model outperforms current state-of-the-art approaches, producing more precise and detailed descriptions, demonstrating the effectiveness of the proposed data-centric approach. We release this large-scale dataset of enriched image-caption pairs for the community.
Authors: Zhen Xiang, Zidi Xiong, Bo Li
Backdoor (Trojan) attack is a common threat to deep neural networks, where samples from one or more source classes embedded with a backdoor trigger will be misclassified to adversarial target classes. Existing methods for detecting whether a classifier is backdoor attacked are mostly designed for attacks with a single adversarial target (e.g., all-to-one attack). To the best of our knowledge, without supervision, no existing methods can effectively address the more general X2X attack with an arbitrary number of source classes, each paired with an arbitrary target class. In this paper, we propose UMD, the first Unsupervised Model Detection method that effectively detects X2X backdoor attacks via a joint inference of the adversarial (source, target) class pairs. In particular, we first define a novel transferability statistic to measure and select a subset of putative backdoor class pairs based on a proposed clustering approach. Then, these selected class pairs are jointly assessed based on an aggregation of their reverse-engineered trigger size for detection inference, using a robust and unsupervised anomaly detector we proposed. We conduct comprehensive evaluations on CIFAR-10, GTSRB, and Imagenette dataset, and show that our unsupervised UMD outperforms SOTA detectors (even with supervision) by 17%, 4%, and 8%, respectively, in terms of the detection accuracy against diverse X2X attacks. We also show the strong detection performance of UMD against several strong adaptive attacks.
Authors: Ilya Kaufman, Omri Azencot
Deep neural networks have been demonstrated to achieve phenomenal success in many domains, and yet their inner mechanisms are not well understood. In this paper, we investigate the curvature of image manifolds, i.e., the manifold deviation from being flat in its principal directions. We find that state-of-the-art trained convolutional neural networks for image classification have a characteristic curvature profile along layers: an initial steep increase, followed by a long phase of a plateau, and followed by another increase. In contrast, this behavior does not appear in untrained networks in which the curvature flattens. We also show that the curvature gap between the last two layers has a strong correlation with the generalization capability of the network. Moreover, we find that the intrinsic dimension of latent codes is not necessarily indicative of curvature. Finally, we observe that common regularization methods such as mixup yield flatter representations when compared to other methods. Our experiments show consistent results over a variety of deep learning architectures and multiple data sets. Our code is publicly available at https://github.com/azencot-group/CRLM
Authors: Tengjin Weng, Yang Shen, Kai Jin, Zhiming Cheng, Yunxiang Li, Gewen Zhang, Shuai Wang, Yaqi Wang
Automatic segmentation of fluid in Optical Coherence Tomography (OCT) images is beneficial for ophthalmologists to make an accurate diagnosis. Although semi-supervised OCT fluid segmentation networks enhance their performance by introducing additional unlabeled data, the performance enhancement is limited. To address this, we propose Superpixel and Confident Learning Guide Point Annotations Network (SCLGPA-Net) based on the teacher-student architecture, which can learn OCT fluid segmentation from limited fully-annotated data and abundant point-annotated data. Specifically, we use points to annotate fluid regions in unlabeled OCT images and the Superpixel-Guided Pseudo-Label Generation (SGPLG) module generates pseudo-labels and pixel-level label trust maps from the point annotations. The label trust maps provide an indication of the reliability of the pseudo-labels. Furthermore, we propose the Confident Learning Guided Label Refinement (CLGLR) module identifies error information in the pseudo-labels and leads to further refinement. Experiments on the RETOUCH dataset show that we are able to reduce the need for fully-annotated data by 94.22\%, closing the gap with the best fully supervised baselines to a mean IoU of only 2\%. Furthermore, We constructed a private 2D OCT fluid segmentation dataset for evaluation. Compared with other methods, comprehensive experimental results demonstrate that the proposed method can achieve excellent performance in OCT fluid segmentation.
Authors: Jan Dubiński, Antoni Kowalczuk, Stanisław Pawlak, Przemysław Rokita, Tomasz Trzciński, Paweł Morawiecki
Generative diffusion models, including Stable Diffusion and Midjourney, can generate visually appealing, diverse, and high-resolution images for various applications. These models are trained on billions of internet-sourced images, raising significant concerns about the potential unauthorized use of copyright-protected images. In this paper, we examine whether it is possible to determine if a specific image was used in the training set, a problem known in the cybersecurity community and referred to as a membership inference attack. Our focus is on Stable Diffusion, and we address the challenge of designing a fair evaluation framework to answer this membership question. We propose a methodology to establish a fair evaluation setup and apply it to Stable Diffusion, enabling potential extensions to other generative models. Utilizing this evaluation setup, we execute membership attacks (both known and newly introduced). Our research reveals that previously proposed evaluation setups do not provide a full understanding of the effectiveness of membership inference attacks. We conclude that the membership inference attack remains a significant challenge for large diffusion models (often deployed as black-box systems), indicating that related privacy and copyright issues will persist in the foreseeable future.
Authors: Wenhui Lei, Xu Wei, Xiaofan Zhang, Kang Li, Shaoting Zhang
The Segment Anything Model (SAM) has recently emerged as a groundbreaking model in the field of image segmentation. Nevertheless, both the original SAM and its medical adaptations necessitate slice-by-slice annotations, which directly increase the annotation workload with the size of the dataset. We propose MedLSAM to address this issue, ensuring a constant annotation workload irrespective of dataset size and thereby simplifying the annotation process. Our model introduces a 3D localization foundation model capable of localizing any target anatomical part within the body. To achieve this, we develop a Localize Anything Model for 3D Medical Images (MedLAM), utilizing two self-supervision tasks: unified anatomical mapping (UAM) and multi-scale similarity (MSS) across a comprehensive dataset of 14,012 CT scans. We then establish a methodology for accurate segmentation by integrating MedLAM with SAM. By annotating several extreme points across three directions on a few templates, our model can autonomously identify the target anatomical region on all data scheduled for annotation. This allows our framework to generate a 2D bbox for every slice of the image, which is then leveraged by SAM to carry out segmentation. We carried out comprehensive experiments on two 3D datasets encompassing 38 distinct organs. Our findings are twofold: 1) MedLAM is capable of directly localizing any anatomical structure using just a few template scans, yet its performance surpasses that of fully supervised models; 2) MedLSAM not only aligns closely with the performance of SAM and its specialized medical adaptations with manual prompts but achieves this with minimal reliance on extreme point annotations across the entire dataset. Furthermore, MedLAM has the potential to be seamlessly integrated with future 3D SAM models, paving the way for enhanced performance.
Authors: Muhammad Osama Khan, Yi Fang
Despite the rapid progress in self-supervised learning (SSL), end-to-end fine-tuning still remains the dominant fine-tuning strategy for medical imaging analysis. However, it remains unclear whether this approach is truly optimal for effectively utilizing the pre-trained knowledge, especially considering the diverse categories of SSL that capture different types of features. In this paper, we present the first comprehensive study that discovers effective fine-tuning strategies for self-supervised learning in medical imaging. After developing strong contrastive and restorative SSL baselines that outperform SOTA methods across four diverse downstream tasks, we conduct an extensive fine-tuning analysis across multiple pre-training and fine-tuning datasets, as well as various fine-tuning dataset sizes. Contrary to the conventional wisdom of fine-tuning only the last few layers of a pre-trained network, we show that fine-tuning intermediate layers is more effective, with fine-tuning the second quarter (25-50%) of the network being optimal for contrastive SSL whereas fine-tuning the third quarter (50-75%) of the network being optimal for restorative SSL. Compared to the de-facto standard of end-to-end fine-tuning, our best fine-tuning strategy, which fine-tunes a shallower network consisting of the first three quarters (0-75%) of the pre-trained network, yields improvements of as much as 5.48%. Additionally, using these insights, we propose a simple yet effective method to leverage the complementary strengths of multiple SSL models, resulting in enhancements of up to 3.57% compared to using the best model alone. Hence, our fine-tuning strategies not only enhance the performance of individual SSL models, but also enable effective utilization of the complementary strengths offered by multiple SSL models, leading to significant improvements in self-supervised medical imaging analysis.
Authors: Qingren Yao, Yuan Zhou, Chang Tang, Wei Xiang
For hyperspectral image change detection (HSI-CD), one key challenge is to reduce band redundancy, as only a few bands are crucial for change detection while other bands may be adverse to it. However, most existing HSI-CD methods directly extract change feature from full-dimensional HSIs, suffering from a degradation of feature discrimination. To address this issue, we propose an end-to-end hyperspectral image change detection network with band selection (ECDBS), which effectively retains the critical bands to promote change detection. The main ingredients of the network are a deep learning based band selection module and cascading band-specific spatial attention (BSA) blocks. The band selection module can be seamlessly integrated with subsequent CD models for joint optimization and end-to-end reasoning, rather than as a step separate from change detection. The BSA block extracts features from each band using a tailored strategy. Unlike the typically used feature extraction strategy that uniformly processes all bands, the BSA blocks considers the differences in feature distributions among widely spaced bands, thereupon extracting more sufficient change feature. Experimental evaluations conducted on three widely used HSI-CD datasets demonstrate the effectiveness and superiority of our proposed method over other state-of-the-art techniques.
Authors: Chaoyi Wu, Xiaoman Zhang, Ya Zhang, Yanfeng Wang, Weidi Xie
In this study, we aim to initiate the development of Radiology Foundation Model, termed as RadFM. We consider the construction of foundational models from three perspectives, namely, dataset construction, model design, and thorough evaluation. Our contribution can be concluded as follows: (i), we construct a large-scale Medical Multi-modal Dataset, MedMD, which consists of 16M 2D and 3D medical scans with high-quality text descriptions or reports across various data formats, modalities, and tasks, covering over 5000 distinct diseases. To the best of our knowledge, this is the first large-scale, high-quality, medical visual-language dataset, with both 2D and 3D scans; (ii), we propose an architecture that enables visually conditioned generative pre-training, i.e., allowing for integration of text input with 2D or 3D medical scans, and generate responses for diverse radiologic tasks. The model was initially pre-trained on MedMD and subsequently fine-tuned on the domain-specific dataset, which is a radiologic cleaned version of MedMD, containing 3M radiologic visual-language pairs, termed as RadMD; (iii), we propose a new evaluation benchmark, RadBench, that comprises five tasks, including modality recognition, disease diagnosis, visual question answering, report generation and rationale diagnosis, aiming to comprehensively assess the capability of foundation models in handling practical clinical problems. We conduct both automatic and human evaluation on RadBench, in both cases, RadFM outperforms existing multi-modal foundation models, that are publicaly accessible, including Openflamingo, MedFlamingo, MedVInT and GPT-4V. Additionally, we also adapt RadFM for different public benchmarks, surpassing existing SOTAs on diverse datasets. All codes, data, and model checkpoint will all be made publicly available to promote further research and development in the field.
Authors: Alhasan Abdellatif, Ahmed H. Elsheikh
In this paper, we introduce a novel approach for generating texture images of infinite resolutions using Generative Adversarial Networks (GANs) based on a patch-by-patch paradigm. Existing texture synthesis techniques often rely on generating a large-scale texture using a one-forward pass to the generating model, this limits the scalability and flexibility of the generated images. In contrast, the proposed approach trains GANs models on a single texture image to generate relatively small patches that are locally correlated and can be seamlessly concatenated to form a larger image while using a constant GPU memory footprint. Our method learns the local texture structure and is able to generate arbitrary-size textures, while also maintaining coherence and diversity. The proposed method relies on local padding in the generator to ensure consistency between patches and utilizes spatial stochastic modulation to allow for local variations and diversity within the large-scale image. Experimental results demonstrate superior scalability compared to existing approaches while maintaining visual coherence of generated textures.
Authors: Wentao Liu, Tong Tian, Weijin Xu, Lemeng Wang, Haoyuan Li, Huihua Yang
Abdominal organ and tumour segmentation has many important clinical applications, such as organ quantification, surgical planning, and disease diagnosis. However, manual assessment is inherently subjective with considerable inter- and intra-expert variability. In the paper, we propose a hybrid supervised framework, StMt, that integrates self-training and mean teacher for the segmentation of abdominal organs and tumors using partially labeled and unlabeled data. We introduce a two-stage segmentation pipeline and whole-volume-based input strategy to maximize segmentation accuracy while meeting the requirements of inference time and GPU memory usage. Experiments on the validation set of FLARE2023 demonstrate that our method achieves excellent segmentation performance as well as fast and low-resource model inference. Our method achieved an average DSC score of 89.79\% and 45.55 \% for the organs and lesions on the validation set and the average running time and area under GPU memory-time cure are 11.25s and 9627.82MB, respectively.
Authors: Christoph Reich, Biplob Debnath, Deep Patel, Srimat Chakradhar
JPEG remains one of the most widespread lossy image coding methods. However, the non-differentiable nature of JPEG restricts the application in deep learning pipelines. Several differentiable approximations of JPEG have recently been proposed to address this issue. This paper conducts a comprehensive review of existing diff. JPEG approaches and identifies critical details that have been missed by previous methods. To this end, we propose a novel diff. JPEG approach, overcoming previous limitations. Our approach is differentiable w.r.t. the input image, the JPEG quality, the quantization tables, and the color conversion parameters. We evaluate the forward and backward performance of our diff. JPEG approach against existing methods. Additionally, extensive ablations are performed to evaluate crucial design choices. Our proposed diff. JPEG resembles the (non-diff.) reference implementation best, significantly surpassing the recent-best diff. approach by $3.47$dB (PSNR) on average. For strong compression rates, we can even improve PSNR by $9.51$dB. Strong adversarial attack results are yielded by our diff. JPEG, demonstrating the effective gradient approximation. Our code is available at https://github.com/necla-ml/Diff-JPEG.
Authors: Erfan Darzi, Yiqing Shen, Yangming Ou, Nanna M. Sijtsema, P.M.A van Ooijen
Optimization-based regularization methods have been effective in addressing the challenges posed by data heterogeneity in medical federated learning, particularly in improving the performance of underrepresented clients. However, these methods often lead to lower overall model accuracy and slower convergence rates. In this paper, we demonstrate that using Vision Transformers can substantially improve the performance of underrepresented clients without a significant trade-off in overall accuracy. This improvement is attributed to the Vision transformer's ability to capture long-range dependencies within the input data.
Authors: Hariharan Ravishankar, Rohan Patil, Vikram Melapudi, Harsh Suthar, Stephan Anzengruber, Parminder Bhatia, Kass-Hout Taha, Pavan Annangi
In this paper, we present SonoSAMTrack - that combines a promptable foundational model for segmenting objects of interest on ultrasound images called SonoSAM, with a state-of-the art contour tracking model to propagate segmentations on 2D+t and 3D ultrasound datasets. Fine-tuned and tested exclusively on a rich, diverse set of objects from $\approx200$k ultrasound image-mask pairs, SonoSAM demonstrates state-of-the-art performance on 7 unseen ultrasound data-sets, outperforming competing methods by a significant margin. We also extend SonoSAM to 2-D +t applications and demonstrate superior performance making it a valuable tool for generating dense annotations and segmentation of anatomical structures in clinical workflows. Further, to increase practical utility of the work, we propose a two-step process of fine-tuning followed by knowledge distillation to a smaller footprint model without comprising the performance. We present detailed qualitative and quantitative comparisons of SonoSAM with state-of-the-art methods showcasing efficacy of the method. This is followed by demonstrating the reduction in number of clicks in a dense video annotation problem of adult cardiac ultrasound chamber segmentation using SonoSAMTrack.
Authors: Hao Wang, Euijoon Ahn, Lei Bi, Jinman Kim
The clinical diagnosis of skin lesion involves the analysis of dermoscopic and clinical modalities. Dermoscopic images provide a detailed view of the surface structures whereas clinical images offer a complementary macroscopic information. The visual diagnosis of melanoma is also based on seven-point checklist which involves identifying different visual attributes. Recently, supervised learning approaches such as convolutional neural networks (CNNs) have shown great performances using both dermoscopic and clinical modalities (Multi-modality). The seven different visual attributes in the checklist are also used to further improve the the diagnosis. The performances of these approaches, however, are still reliant on the availability of large-scaled labeled data. The acquisition of annotated dataset is an expensive and time-consuming task, more so with annotating multi-attributes. To overcome this limitation, we propose a self-supervised learning (SSL) algorithm for multi-modality skin lesion classification. Our algorithm enables the multi-modality learning by maximizing the similarities between paired dermoscopic and clinical images from different views. In addition, we generate surrogate pseudo-multi-labels that represent seven attributes via clustering analysis. We also propose a label-relation-aware module to refine each pseudo-label embedding and capture the interrelationships between pseudo-multi-labels. We validated the effectiveness of our algorithm using well-benchmarked seven-point skin lesion dataset. Our results show that our algorithm achieved better performances than other state-of-the-art SSL counterparts.
Authors: Preetam Prabhu Srikar Dammu, Chirag Shah
Often machine learning models tend to automatically learn associations present in the training data without questioning their validity or appropriateness. This undesirable property is the root cause of the manifestation of spurious correlations, which render models unreliable and prone to failure in the presence of distribution shifts. Research shows that most methods attempting to remedy spurious correlations are only effective for a model's known spurious associations. Current spurious correlation detection algorithms either rely on extensive human annotations or are too restrictive in their formulation. Moreover, they rely on strict definitions of visual artifacts that may not apply to data produced by generative models, as they are known to hallucinate contents that do not conform to standard specifications. In this work, we introduce a general-purpose method that efficiently detects potential spurious correlations, and requires significantly less human interference in comparison to the prior art. Additionally, the proposed method provides intuitive explanations while eliminating the need for pixel-level annotations. We demonstrate the proposed method's tolerance to the peculiarity of AI-generated images, which is a considerably challenging task, one where most of the existing methods fall short. Consequently, our method is also suitable for detecting spurious correlations that may propagate to downstream applications originating from generative models.
Authors: Xin Yuan, Jie Guo, Weidong Qiu, Zheng Huang, Shujun Li
Mis- and disinformation online have become a major societal problem as major sources of online harms of different kinds. One common form of mis- and disinformation is out-of-context (OOC) information, where different pieces of information are falsely associated, e.g., a real image combined with a false textual caption or a misleading textual description. Although some past studies have attempted to defend against OOC mis- and disinformation through external evidence, they tend to disregard the role of different pieces of evidence with different stances. Motivated by the intuition that the stance of evidence represents a bias towards different detection results, we propose a stance extraction network (SEN) that can extract the stances of different pieces of multi-modal evidence in a unified framework. Moreover, we introduce a support-refutation score calculated based on the co-occurrence relations of named entities into the textual SEN. Extensive experiments on a public large-scale dataset demonstrated that our proposed method outperformed the state-of-the-art baselines, with the best model achieving a performance gain of 3.2% in accuracy.
Authors: Yunkang Cao, Xiaohao Xu, Chen Sun, Xiaonan Huang, Weiming Shen
Anomaly detection is a crucial task across different domains and data types. However, existing anomaly detection models are often designed for specific domains and modalities. This study explores the use of GPT-4V(ision), a powerful visual-linguistic model, to address anomaly detection tasks in a generic manner. We investigate the application of GPT-4V in multi-modality, multi-domain anomaly detection tasks, including image, video, point cloud, and time series data, across multiple application areas, such as industrial, medical, logical, video, 3D anomaly detection, and localization tasks. To enhance GPT-4V's performance, we incorporate different kinds of additional cues such as class information, human expertise, and reference images as prompts.Based on our experiments, GPT-4V proves to be highly effective in detecting and explaining global and fine-grained semantic patterns in zero/one-shot anomaly detection. This enables accurate differentiation between normal and abnormal instances. Although we conducted extensive evaluations in this study, there is still room for future evaluation to further exploit GPT-4V's generic anomaly detection capacity from different aspects. These include exploring quantitative metrics, expanding evaluation benchmarks, incorporating multi-round interactions, and incorporating human feedback loops. Nevertheless, GPT-4V exhibits promising performance in generic anomaly detection and understanding, thus opening up a new avenue for anomaly detection.
Authors: Siao Tang, Xin Wang, Hong Chen, Chaoyu Guan, Yansong Tang, Wenwu zhu
Diffusion models have recently shown remarkable generation ability, achieving state-of-the-art performance in many tasks. However, the high computational cost is still a troubling problem for diffusion models. To tackle this problem, we propose to automatically remove the structural redundancy in diffusion models with our proposed Diffusion Distillation-based Block-wise Neural Architecture Search (DiffNAS). Specifically, given a larger pretrained teacher, we leverage DiffNAS to search for the smallest architecture which can achieve on-par or even better performance than the teacher. Considering current diffusion models are based on UNet which naturally has a block-wise structure, we perform neural architecture search independently in each block, which largely reduces the search space. Different from previous block-wise NAS methods, DiffNAS contains a block-wise local search strategy and a retraining strategy with a joint dynamic loss. Concretely, during the search process, we block-wisely select the best subnet to avoid the unfairness brought by the global search strategy used in previous works. When retraining the searched architecture, we adopt a dynamic joint loss to maintain the consistency between supernet training and subnet retraining, which also provides informative objectives for each block and shortens the paths of gradient propagation. We demonstrate this joint loss can effectively improve model performance. We also prove the necessity of the dynamic adjustment of this loss. The experiments show that our method can achieve significant computational reduction, especially on latent diffusion models with about 50\% MACs and Parameter reduction.
Authors: Shuhei Tarashima, Muhammad Abdul Haq, Yushan Wang, Norio Tagawa
In this work, we present a novel Sports Ball Detection and Tracking (SBDT) method that can be applied to various sports categories. Our approach is composed of (1) high-resolution feature extraction, (2) position-aware model training, and (3) inference considering temporal consistency, all of which are put together as a new SBDT baseline. Besides, to validate the wide-applicability of our approach, we compare our baseline with 6 state-of-the-art SBDT methods on 5 datasets from different sports categories. We achieve this by newly introducing two SBDT datasets, providing new ball annotations for two datasets, and re-implementing all the methods to ease extensive comparison. Experimental results demonstrate that our approach is substantially superior to existing methods on all the sports categories covered by the datasets. We believe our proposed method can play as a Widely Applicable Strong Baseline (WASB) of SBDT, and our datasets and codebase will promote future SBDT research. Datasets and codes are available at https://github.com/nttcom/WASB-SBDT .
Authors: Yuxuan Ou, Yuzhe Zhang, Yuntang Wang, Shwetak Patel, Daniel McDuf, Yuzhe Yang, Xin Liu
Recent advances in supervised deep learning techniques have demonstrated the possibility to remotely measure human physiological vital signs (e.g., photoplethysmograph, heart rate) just from facial videos. However, the performance of these methods heavily relies on the availability and diversity of real labeled data. Yet, collecting large-scale real-world data with high-quality labels is typically challenging and resource intensive, which also raises privacy concerns when storing personal bio-metric data. Synthetic video-based datasets (e.g., SCAMPS \cite{mcduff2022scamps}) with photo-realistic synthesized avatars are introduced to alleviate the issues while providing high-quality synthetic data. However, there exists a significant gap between synthetic and real-world data, which hinders the generalization of neural models trained on these synthetic datasets. In this paper, we proposed several measures to add real-world noise to synthetic physiological signals and corresponding facial videos. We experimented with individual and combined augmentation methods and evaluated our framework on three public real-world datasets. Our results show that we were able to reduce the average MAE from 6.9 to 2.0.
Authors: Chancharik Mitra, Abrar Anwar, Rodolfo Corona, Dan Klein, Trevor Darrell, Jesse Thomason
In this work, we consider the task of resolving object referents when given a comparative language description. We present a Multi-view Approach to Grounding in Context (MAGiC) that leverages transformers to pragmatically reason over both objects given multiple image views and a language description. In contrast to past efforts that attempt to connect vision and language for this task without fully considering the resulting referential context, MAGiC makes use of the comparative information by jointly reasoning over multiple views of both object referent candidates and the referring language expression. We present an analysis demonstrating that comparative reasoning contributes to SOTA performance on the SNARE object reference task.
Authors: Ibrahim Salim, A. Ben Hamza
While graph convolution based methods have become the de-facto standard for graph representation learning, their applications to disease prediction tasks remain quite limited, particularly in the classification of neurodevelopmental and neurodegenerative brain disorders. In this paper, we introduce an aggregator normalization graph convolutional network by leveraging aggregation in graph sampling, as well as skip connections and identity mapping. The proposed model learns discriminative graph node representations by incorporating both imaging and non-imaging features into the graph nodes and edges, respectively, with the aim of augmenting predictive capabilities and providing a holistic perspective on the underlying mechanisms of brain disorders. Skip connections enable the direct flow of information from the input features to later layers of the network, while identity mapping helps maintain the structural information of the graph during feature learning. We benchmark our model against several recent baseline methods on two large datasets, Autism Brain Imaging Data Exchange (ABIDE) and Alzheimer's Disease Neuroimaging Initiative (ADNI), for the prediction of autism spectrum disorder and Alzheimer's disease, respectively. Experimental results demonstrate the competitive performance of our approach in comparison with recent baselines in terms of several evaluation metrics, achieving relative improvements of 50% and 13.56% in classification accuracy over graph convolutional networks on ABIDE and ADNI, respectively.
Authors: Junyang Chen, Hanjiang Lai
Zero-shot composed image retrieval (ZS-CIR), which aims to retrieve a target image based on textual modifications to a reference image without triplet labeling, has gained more and more attention. Current ZS-CIR research mainly relies on two unlabeled pre-trained models: the vision-language model, e.g., CLIP, and the Pic2Word/textual inversion model. However, the pre-trained models and CIR tasks have substantial discrepancies, where the pre-trained models learn the similarities between vision and language but CIR aims to learn the modifications of the image guided by text. In this paper, we introduce a novel unlabeled and pre-trained masked tuning approach to reduce the gap between the pre-trained model and the downstream CIR task. We first reformulate the pre-trained vision-language contrastive learning as the CIR task, where we randomly mask input image patches to generate $\langle$masked image, text, image$\rangle$ triple from an image-text pair. Then, we propose a masked tuning, which uses the text and the masked image to learn the modifications of the original image. With such a simple design, it can learn to capture fine-grained text-guided modifications. Extensive experimental results demonstrate the significant superiority of our approach over the baseline models on three ZS-CIR datasets, including FashionIQ, CIRR, and CIRCO.
Authors: Wenshuai Xu, Zhenhui Hu, Yu Lu, Jinzhou Meng, Qingjie Liu, Yunhong Wang
The pretraining-finetuning paradigm has gained popularity in various computer vision tasks. In this paradigm, the emergence of active finetuning arises due to the abundance of large-scale data and costly annotation requirements. Active finetuning involves selecting a subset of data from an unlabeled pool for annotation, facilitating subsequent finetuning. However, the use of a limited number of training samples can lead to a biased distribution, potentially resulting in model overfitting. In this paper, we propose a new method called ActiveDC for the active finetuning tasks. Firstly, we select samples for annotation by optimizing the distribution similarity between the subset to be selected and the entire unlabeled pool in continuous space. Secondly, we calibrate the distribution of the selected samples by exploiting implicit category information in the unlabeled pool. The feature visualization provides an intuitive sense of the effectiveness of our approach to distribution calibration. We conducted extensive experiments on three image classification datasets with different sampling ratios. The results indicate that ActiveDC consistently outperforms the baseline performance in all image classification tasks. The improvement is particularly significant when the sampling ratio is low, with performance gains of up to 10%. Our code will be released.
Authors: Mingzhao Yang, Shangchao Su, Bin Li, Xiangyang Xue
One-shot federated learning (OSFL) has gained attention in recent years due to its low communication cost. However, most of the existing methods require auxiliary datasets or training generators, which hinders their practicality in real-world scenarios. In this paper, we explore the novel opportunities that diffusion models bring to OSFL and propose FedCADO, utilizing guidance from client classifiers to generate data that complies with clients' distributions and subsequently training the aggregated model on the server. Specifically, our method involves targeted optimizations in two aspects. On one hand, we conditionally edit the randomly sampled initial noises, embedding them with specified semantics and distributions, resulting in a significant improvement in both the quality and stability of generation. On the other hand, we employ the BN statistics from the classifiers to provide detailed guidance during generation. These tailored optimizations enable us to limitlessly generate datasets, which closely resemble the distribution and quality of the original client dataset. Our method effectively handles the heterogeneous client models and the problems of non-IID features or labels. In terms of privacy protection, our method avoids training any generator or transferring any auxiliary information on clients, eliminating any additional privacy leakage risks. Leveraging the extensive knowledge stored in the pre-trained diffusion model, the synthetic datasets can assist us in surpassing the knowledge limitations of the client samples, resulting in aggregation models that even outperform the performance ceiling of centralized training in some cases, which is convincingly demonstrated in the sufficient quantification and visualization experiments conducted on three large-scale multi-domain image datasets.
Authors: Xingshuai Dong, Massimiliano L. Cappuccio
Autonomous vehicle refers to a vehicle capable of perceiving its surrounding environment and driving with little or no human driver input. The perception system is a fundamental component which enables the autonomous vehicle to collect data and extract relevant information from the environment to drive safely. Benefit from the recent advances in computer vision, the perception task can be achieved by using sensors, such as camera, LiDAR, radar, and ultrasonic sensor. This paper reviews publications on computer vision and autonomous driving that are published during the last ten years. In particular, we first investigate the development of autonomous driving systems and summarize these systems that are developed by the major automotive manufacturers from different countries. Second, we investigate the sensors and benchmark data sets that are commonly utilized for autonomous driving. Then, a comprehensive overview of computer vision applications for autonomous driving such as depth estimation, object detection, lane detection, and traffic sign recognition are discussed. Additionally, we review public opinions and concerns on autonomous vehicles. Based on the discussion, we analyze the current technological challenges that autonomous vehicles meet with. Finally, we present our insights and point out some promising directions for future research. This paper will help the reader to understand autonomous vehicles from the perspectives of academia and industry.
Authors: Thomas Cilloni, Wei Wang, Charles Walter, Charles Fleming
Facial recognition tools are becoming exceptionally accurate in identifying people from images. However, this comes at the cost of privacy for users of online services with photo management (e.g. social media platforms). Particularly troubling is the ability to leverage unsupervised learning to recognize faces even when the user has not labeled their images. In this paper we propose Ulixes, a strategy to generate visually non-invasive facial noise masks that yield adversarial examples, preventing the formation of identifiable user clusters in the embedding space of facial encoders. This is applicable even when a user is unmasked and labeled images are available online. We demonstrate the effectiveness of Ulixes by showing that various classification and clustering methods cannot reliably label the adversarial examples we generate. We also study the effects of Ulixes in various black-box settings and compare it to the current state of the art in adversarial machine learning. Finally, we challenge the effectiveness of Ulixes against adversarially trained models and show that it is robust to countermeasures.
Authors: Jielin Qiu, Jiacheng Zhu, William Han, Aditesh Kumar, Karthik Mittal, Claire Jin, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Bo Li, Ding Zhao, Lijuan Wang
Multimodal summarization with multimodal output (MSMO) has emerged as a promising research direction. Nonetheless, numerous limitations exist within existing public MSMO datasets, including insufficient upkeep, data inaccessibility, limited size, and the absence of proper categorization, which pose significant challenges to effective research. To address these challenges and provide a comprehensive dataset for this new direction, we have meticulously curated the MultiSum dataset. Our new dataset features (1) Human-validated summaries for both video and textual content, providing superior human instruction and labels for multimodal learning. (2) Comprehensively and meticulously arranged categorization, spanning 17 principal categories and 170 subcategories to encapsulate a diverse array of real-world scenarios. (3) Benchmark tests performed on the proposed dataset to assess varied tasks and methods, including video temporal segmentation, video summarization, text summarization, and multimodal summarization. To champion accessibility and collaboration, we release the MultiSum dataset and the data collection tool as fully open-source resources, fostering transparency and accelerating future developments. Our project website can be found at https://multisum-dataset.github.io/.
Authors: Fei Wu, Pablo Marquez-Neila, Mingyi Zheng, Hedyeh Rafii-Tari, Raphael Sznitman
Semantic segmentation is a complex task that relies heavily on large amounts of annotated image data. However, annotating such data can be time-consuming and resource-intensive, especially in the medical domain. Active Learning (AL) is a popular approach that can help to reduce this burden by iteratively selecting images for annotation to improve the model performance. In the case of video data, it is important to consider the model uncertainty and the temporal nature of the sequences when selecting images for annotation. This work proposes a novel AL strategy for surgery video segmentation, \COALSamp{}, COrrelation-aWare Active Learning. Our approach involves projecting images into a latent space that has been fine-tuned using contrastive learning and then selecting a fixed number of representative images from local clusters of video frames. We demonstrate the effectiveness of this approach on two video datasets of surgical instruments and three real-world video datasets. The datasets and code will be made publicly available upon receiving necessary approvals.