Authors: Archit Kambhamettu, Samantha Snyder, Maliheh Fakhar, Samuel Audia, Ross Miller, Jae Kun Shim, Aniket Bera
Abstract: Understanding internal joint loading is critical for diagnosing gait-related diseases such as knee osteoarthritis; however, current methods of measuring joint risk factors are time-consuming, expensive, and restricted to lab settings. In this paper, we enable the large-scale, cost-effective biomechanical analysis of joint loading via three key contributions: the development and deployment of novel instrumented insoles, the creation of a large multimodal biomechanics dataset (VidSole), and a baseline deep learning pipeline to predict internal joint loading factors. Our novel instrumented insole measures the tri-axial forces and moments across five high-pressure points under the foot. VidSole consists of the forces and moments measured by these insoles along with corresponding RGB video from two viewpoints, 3D body motion capture, and force plate data for over 2,600 trials of 52 diverse participants performing four fundamental activities of daily living (sit-to-stand, stand-to-sit, walking, and running). We feed the insole data and kinematic parameters extractable from video (i.e., pose, knee angle) into a deep learning pipeline consisting of an ensemble Gated Recurrent Unit (GRU) activity classifier followed by activity-specific Long Short Term Memory (LSTM) regression networks to estimate knee adduction moment (KAM), a biomechanical risk factor for knee osteoarthritis. The successful classification of activities at an accuracy of 99.02 percent and KAM estimation with mean absolute error (MAE) less than 0.5 percent*body weight*height, the current threshold for accurately detecting knee osteoarthritis with KAM, illustrates the usefulness of our dataset for future research and clinical settings.
Authors: Jingkun Chen, Guang Yang, Xiao Zhang, Jingchao Peng, Tianlu Zhang, Jianguo Zhang, Jungong Han, Vicente Grau
Abstract: Detecting novel anomalies in medical imaging is challenging due to the limited availability of labeled data for rare abnormalities, which often display high variability and subtlety. This challenge is further compounded when small abnormal regions are embedded within larger normal areas, as whole-image predictions frequently overlook these subtle deviations. To address these issues, we propose an unsupervised Patch-GAN framework designed to detect and localize anomalies by capturing both local detail and global structure. Our framework first reconstructs masked images to learn fine-grained, normal-specific features, allowing for enhanced sensitivity to minor deviations from normality. By dividing these reconstructed images into patches and assessing the authenticity of each patch, our approach identifies anomalies at a more granular level, overcoming the limitations of whole-image evaluation. Additionally, a patch-ranking mechanism prioritizes regions with higher abnormal scores, reinforcing the alignment between local patch discrepancies and the global image context. Experimental results on the ISIC 2016 skin lesion and BraTS 2019 brain tumor datasets validate our framework's effectiveness, achieving AUCs of 95.79% and 96.05%, respectively, and outperforming three state-of-the-art baselines.
Authors: Lei Cheng, Siyang Cao
Abstract: Despite significant advancements in environment perception capabilities for autonomous driving and intelligent robotics, cameras and LiDARs remain notoriously unreliable in low-light conditions and adverse weather, which limits their effectiveness. Radar serves as a reliable and low-cost sensor that can effectively complement these limitations. However, radar-based object detection has been underexplored due to the inherent weaknesses of radar data, such as low resolution, high noise, and lack of visual information. In this paper, we present TransRAD, a novel 3D radar object detection model designed to address these challenges by leveraging the Retentive Vision Transformer (RMT) to more effectively learn features from information-dense radar Range-Azimuth-Doppler (RAD) data. Our approach leverages the Retentive Manhattan Self-Attention (MaSA) mechanism provided by RMT to incorporate explicit spatial priors, thereby enabling more accurate alignment with the spatial saliency characteristics of radar targets in RAD data and achieving precise 3D radar detection across Range-Azimuth-Doppler dimensions. Furthermore, we propose Location-Aware NMS to effectively mitigate the common issue of duplicate bounding boxes in deep radar object detection. The experimental results demonstrate that TransRAD outperforms state-of-the-art methods in both 2D and 3D radar detection tasks, achieving higher accuracy, faster inference speed, and reduced computational complexity. Code is available at https://github.com/radar-lab/TransRAD
Authors: Nowak Mateusz, Jarosz Wojciech, Chin Peter
Abstract: Reconstructing a 3D scene from images is challenging due to the different ways light interacts with surfaces depending on the viewer's position and the surface's material. In classical computer graphics, materials can be classified as diffuse or specular, interacting with light differently. The standard 3D Gaussian Splatting model struggles to represent view-dependent content, since it cannot differentiate an object within the scene from the light interacting with its specular surfaces, which produce highlights or reflections. In this paper, we propose to extend the 3D Gaussian Splatting model by introducing an additional symmetric matrix to enhance the opacity representation of each 3D Gaussian. This improvement allows certain Gaussians to be suppressed based on the viewer's perspective, resulting in a more accurate representation of view-dependent reflections and specular highlights without compromising the scene's integrity. By allowing the opacity to be view dependent, our enhanced model achieves state-of-the-art performance on Mip-Nerf, Tanks\&Temples, Deep Blending, and Nerf-Synthetic datasets without a significant loss in rendering speed, achieving >60FPS, and only incurring a minimal increase in memory used.
Authors: Xudong Wang, Chaomin Shen, Yaxin Peng
Abstract: Object detection in unmanned aerial vehicle (UAV) remote sensing images poses significant challenges due to unstable image quality, small object sizes, complex backgrounds, and environmental occlusions. Small objects, in particular, occupy minimal portions of images, making their accurate detection highly difficult. Existing multi-scale feature fusion methods address these challenges to some extent by aggregating features across different resolutions. However, these methods often fail to effectively balance classification and localization performance for small objects, primarily due to insufficient feature representation and imbalanced network information flow. In this paper, we propose a novel feature fusion framework specifically designed for UAV object detection tasks to enhance both localization accuracy and classification performance. The proposed framework integrates hybrid upsampling and downsampling modules, enabling feature maps from different network depths to be flexibly adjusted to arbitrary resolutions. This design facilitates cross-layer connections and multi-scale feature fusion, ensuring improved representation of small objects. Our approach leverages hybrid downsampling to enhance fine-grained feature representation, improving spatial localization of small targets, even under complex conditions. Simultaneously, the upsampling module aggregates global contextual information, optimizing feature consistency across scales and enhancing classification robustness in cluttered scenes. Experimental results on two public UAV datasets demonstrate the effectiveness of the proposed framework. Integrated into the YOLO-V10 model, our method achieves a 2\% improvement in average precision (AP) compared to the baseline YOLO-V10 model, while maintaining the same number of parameters. These results highlight the potential of our framework for accurate and efficient UAV object detection.
Authors: Renato F. Miotto, William R. Wolf, Fernando Zigunov
Abstract: This work presents a novel approach for pressure field reconstruction from image velocimetry data using SIREN (Sinusoidal Representation Network), emphasizing its effectiveness as an implicit neural representation in noisy environments and its mesh-free nature. While we briefly assess two recently proposed methods - one-shot matrix-omnidirectional integration (OS-MODI) and Green's function integral (GFI) - the primary focus is on the advantages of the SIREN approach. The OS-MODI technique performs well in noise-free conditions and with structured meshes but struggles when applied to unstructured meshes with high aspect ratio. Similarly, the GFI method encounters difficulties due to singularities inherent from the Newtonian kernel. In contrast, the proposed SIREN approach is a mesh-free method that directly reconstructs the pressure field, bypassing the need for an intrinsic grid connectivity and, hence, avoiding the challenges associated with ill-conditioned cells and unstructured meshes. This provides a distinct advantage over traditional mesh-based methods. Moreover, it is shown that changes in the architecture of the SIREN can be used to filter out inherent noise from velocimetry data. This work positions SIREN as a robust and versatile solution for pressure reconstruction, particularly in noisy environments characterized by the absence of mesh structure, opening new avenues for innovative applications in this field.
Authors: Gary Sarwin, Alessandro Carretta, Victor Staartjes, Matteo Zoli, Diego Mazzatenta, Luca Regli, Carlo Serra, Ender Konukoglu
Abstract: Surgical guidance can be delivered in various ways. In neurosurgery, spatial guidance and orientation are predominantly achieved through neuronavigation systems that reference pre-operative MRI scans. Recently, there has been growing interest in providing live guidance by analyzing video feeds from tools such as endoscopes. Existing approaches, including anatomy detection, orientation feedback, phase recognition, and visual question-answering, primarily focus on aiding surgeons in assessing the current surgical scene. This work aims to provide guidance on a finer scale, aiming to provide guidance by forecasting the trajectory of the surgical instrument, essentially addressing the question of what to do next. To address this task, we propose a model that not only leverages the historical locations of surgical instruments but also integrates anatomical features. Importantly, our work does not rely on explicit ground truth labels for instrument trajectories. Instead, the ground truth is generated by a detection model trained to detect both anatomical structures and instruments within surgical videos of a comprehensive dataset containing pituitary surgery videos. By analyzing the interaction between anatomy and instrument movements in these videos and forecasting future instrument movements, we show that anatomical features are a valuable asset in addressing this challenging task. To the best of our knowledge, this work is the first attempt to address this task for manually operated surgeries.
Authors: Fouad Bousetouane
Abstract: Generative AI is transforming image synthesis, enabling the creation of high-quality, diverse, and photorealistic visuals across industries like design, media, healthcare, and autonomous systems. Advances in techniques such as image-to-image translation, text-to-image generation, domain transfer, and multimodal alignment have broadened the scope of automated visual content creation, supporting a wide spectrum of applications. These advancements are driven by models like Generative Adversarial Networks (GANs), conditional frameworks, and diffusion-based approaches such as Stable Diffusion. This work presents a structured classification of image generation techniques based on the nature of the input, organizing methods by input modalities like noisy vectors, latent representations, and conditional inputs. We explore the principles behind these models, highlight key frameworks including DALL-E, ControlNet, and DeepSeek Janus-Pro, and address challenges such as computational costs, data biases, and output alignment with user intent. By offering this input-centric perspective, this study bridges technical depth with practical insights, providing researchers and practitioners with a comprehensive resource to harness generative AI for real-world applications.
Authors: Kumar Ashutosh, Yossi Gandelsman, Xinlei Chen, Ishan Misra, Rohit Girdhar
Abstract: We present MILS: Multimodal Iterative LLM Solver, a surprisingly simple, training-free approach, to imbue multimodal capabilities into your favorite LLM. Leveraging their innate ability to perform multi-step reasoning, MILS prompts the LLM to generate candidate outputs, each of which are scored and fed back iteratively, eventually generating a solution to the task. This enables various applications that typically require training specialized models on task-specific data. In particular, we establish a new state-of-the-art on emergent zero-shot image, video and audio captioning. MILS seamlessly applies to media generation as well, discovering prompt rewrites to improve text-to-image generation, and even edit prompts for style transfer! Finally, being a gradient-free optimization approach, MILS can invert multimodal embeddings into text, enabling applications like cross-modal arithmetic.
Authors: Ramchandran Muthukumar, Ambar Pal, Jeremias Sulam, Rene Vidal
Abstract: State-of-the-art machine learning systems are vulnerable to small perturbations to their input, where ``small'' is defined according to a threat model that assigns a positive threat to each perturbation. Most prior works define a task-agnostic, isotropic, and global threat, like the $\ell_p$ norm, where the magnitude of the perturbation fully determines the degree of the threat and neither the direction of the attack nor its position in space matter. However, common corruptions in computer vision, such as blur, compression, or occlusions, are not well captured by such threat models. This paper proposes a novel threat model called \texttt{Projected Displacement} (PD) to study robustness beyond existing isotropic and global threat models. The proposed threat model measures the threat of a perturbation via its alignment with \textit{unsafe directions}, defined as directions in the input space along which a perturbation of sufficient magnitude changes the ground truth class label. Unsafe directions are identified locally for each input based on observed training data. In this way, the PD threat model exhibits anisotropy and locality. Experiments on Imagenet-1k data indicate that, for any input, the set of perturbations with small PD threat includes \textit{safe} perturbations of large $\ell_p$ norm that preserve the true label, such as noise, blur and compression, while simultaneously excluding \textit{unsafe} perturbations that alter the true label. Unlike perceptual threat models based on embeddings of large-vision models, the PD threat model can be readily computed for arbitrary classification tasks without pre-training or finetuning. Further additional task annotation such as sensitivity to image regions or concept hierarchies can be easily integrated into the assessment of threat and thus the PD threat model presents practitioners with a flexible, task-driven threat specification.
Authors: Siyuan Jiang, Yihan Hu, Wenjie Li, Pengcheng Zeng
Abstract: Functional data analysis (FDA) is essential for analyzing continuous, high-dimensional data, yet existing methods often decouple functional registration and classification, limiting their efficiency and performance. We present DeepFRC, an end-to-end deep learning framework that unifies these tasks within a single model. Our approach incorporates an alignment module that learns time warping functions via elastic function registration and a learnable basis representation module for dimensionality reduction on aligned data. This integration enhances both alignment accuracy and predictive performance. Theoretical analysis establishes that DeepFRC achieves low misalignment and generalization error, while simulations elucidate the progression of registration, reconstruction, and classification during training. Experiments on real-world datasets demonstrate that DeepFRC consistently outperforms state-of-the-art methods, particularly in addressing complex registration challenges. Code is available at: https://github.com/Drivergo-93589/DeepFRC.
Authors: Liangjing Shao, Benshuang Chen, Shuting Zhao, Xinrong Chen
Abstract: Real-time ego-motion tracking for endoscope is a significant task for efficient navigation and robotic automation of endoscopy. In this paper, a novel framework is proposed to perform real-time ego-motion tracking for endoscope. Firstly, a multi-modal visual feature learning network is proposed to perform relative pose prediction, in which the motion feature from the optical flow, the scene features and the joint feature from two adjacent observations are all extracted for prediction. Due to more correlation information in the channel dimension of the concatenated image, a novel feature extractor is designed based on an attention mechanism to integrate multi-dimensional information from the concatenation of two continuous frames. To extract more complete feature representation from the fused features, a novel pose decoder is proposed to predict the pose transformation from the concatenated feature map at the end of the framework. At last, the absolute pose of endoscope is calculated based on relative poses. The experiment is conducted on three datasets of various endoscopic scenes and the results demonstrate that the proposed method outperforms state-of-the-art methods. Besides, the inference speed of the proposed method is over 30 frames per second, which meets the real-time requirement. The project page is here: \href{https://remote-bmxs.netlify.app}{remote-bmxs.netlify.app}
Authors: Zhe Wang, Xiaoliang Huo, Siqi Fan, Jingjing Liu, Ya-Qin Zhang, Yan Wang
Abstract: In autonomous driving, The perception capabilities of the ego-vehicle can be improved with roadside sensors, which can provide a holistic view of the environment. However, existing monocular detection methods designed for vehicle cameras are not suitable for roadside cameras due to viewpoint domain gaps. To bridge this gap and Improve ROAdside Monocular 3D object detection, we propose IROAM, a semantic-geometry decoupled contrastive learning framework, which takes vehicle-side and roadside data as input simultaneously. IROAM has two significant modules. In-Domain Query Interaction module utilizes a transformer to learn content and depth information for each domain and outputs object queries. Cross-Domain Query Enhancement To learn better feature representations from two domains, Cross-Domain Query Enhancement decouples queries into semantic and geometry parts and only the former is used for contrastive learning. Experiments demonstrate the effectiveness of IROAM in improving roadside detector's performance. The results validate that IROAM has the capabilities to learn cross-domain information.
Authors: Angus Man Ho Kwok, Jiaee Cheong, Sinan Kalkan, Hatice Gunes
Abstract: This paper presents the very first attempt to evaluate machine learning fairness for depression detection using electroencephalogram (EEG) data. We conduct experiments using different deep learning architectures such as Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, and Gated Recurrent Unit (GRU) networks across three EEG datasets: Mumtaz, MODMA and Rest. We employ five different bias mitigation strategies at the pre-, in- and post-processing stages and evaluate their effectiveness. Our experimental results show that bias exists in existing EEG datasets and algorithms for depression detection, and different bias mitigation methods address bias at different levels across different fairness measures.
Authors: Wenshuo Chen, Haozhe Jia, Songning Lai, Keming Wu, Hongru Xiao, Lijie Hu, Yutao Yue
Abstract: Rapid progress in text-to-motion generation has been largely driven by diffusion models. However, existing methods focus solely on temporal modeling, thereby overlooking frequency-domain analysis. We identify two key phases in motion denoising: the **semantic planning stage** and the **fine-grained improving stage**. To address these phases effectively, we propose **Fre**quency **e**nhanced **t**ext-**to**-**m**otion diffusion model (**Free-T2M**), incorporating stage-specific consistency losses that enhance the robustness of static features and improve fine-grained accuracy. Extensive experiments demonstrate the effectiveness of our method. Specifically, on StableMoFusion, our method reduces the FID from **0.189** to **0.051**, establishing a new SOTA performance within the diffusion architecture. These findings highlight the importance of incorporating frequency-domain insights into text-to-motion generation for more precise and robust results.
Authors: Malte T\"olle, Mohamad Scharaf, Samantha Fischer, Christoph Reich, Silav Zeid, Christoph Dieterich, Benjamin Meder, Norbert Frey, Philipp Wild, Sandy Engelhardt
Abstract: A patient undergoes multiple examinations in each hospital stay, where each provides different facets of the health status. These assessments include temporal data with varying sampling rates, discrete single-point measurements, therapeutic interventions such as medication administration, and images. While physicians are able to process and integrate diverse modalities intuitively, neural networks need specific modeling for each modality complicating the training procedure. We demonstrate that this complexity can be significantly reduced by visualizing all information as images along with unstructured text and subsequently training a conventional vision-text transformer. Our approach, Vision Transformer for irregular sampled Multi-modal Measurements (ViTiMM), not only simplifies data preprocessing and modeling but also outperforms current state-of-the-art methods in predicting in-hospital mortality and phenotyping, as evaluated on 6,175 patients from the MIMIC-IV dataset. The modalities include patient's clinical measurements, medications, X-ray images, and electrocardiography scans. We hope our work inspires advancements in multi-modal medical AI by reducing the training complexity to (visual) prompt engineering, thus lowering entry barriers and enabling no-code solutions for training. The source code will be made publicly available.
Authors: Kevin Qiu, Dimitri Bulatov, Dorota Iwaszczuk
Abstract: This paper presents an analysis of utilizing elevation data to aid outdoor point cloud semantic segmentation through existing machine-learning networks in remote sensing, specifically in urban, built-up areas. In dense outdoor point clouds, the receptive field of a machine learning model may be too small to accurately determine the surroundings and context of a point. By computing Digital Terrain Models (DTMs) from the point clouds, we extract the relative elevation feature, which is the vertical distance from the terrain to a point. RandLA-Net is employed for efficient semantic segmentation of large-scale point clouds. We assess its performance across three diverse outdoor datasets captured with varying sensor technologies and sensor locations. Integration of relative elevation data leads to consistent performance improvements across all three datasets, most notably in the Hessigheim dataset, with an increase of 3.7 percentage points in average F1 score from 72.35% to 76.01%, by establishing long-range dependencies between ground and objects. We also explore additional local features such as planarity, normal vectors, and 2D features, but their efficacy varied based on the characteristics of the point cloud. Ultimately, this study underscores the important role of the non-local relative elevation feature for semantic segmentation of point clouds in remote sensing applications.
Authors: Sangho Lee, Il Yong Chun, Hogun Park
Abstract: Multi-modal transformers are rapidly gaining attention in video captioning tasks. Existing multi-modal video captioning methods typically extract a fixed number of frames, which raises critical challenges. When a limited number of frames are extracted, important frames with essential information for caption generation may be missed. Conversely, extracting an excessive number of frames includes consecutive frames, potentially causing redundancy in visual tokens extracted from consecutive video frames. To extract an appropriate number of frames for each video, this paper proposes the first model-agnostic module selection framework in video captioning that has two main functions: (1) selecting a caption generation module with an appropriate size based on visual tokens extracted from video frames, and (2) constructing subsets of visual tokens for the selected caption generation module. Furthermore, we propose a new adaptive attention masking scheme that enhances attention on important visual tokens. Our experiments on three different benchmark datasets demonstrate that the proposed framework significantly improves the performance of three recent video captioning models.
Authors: Shayli Farshchiha, Salman Asoudeh, Maryam Shavali Kuhshuri, Mehrshad Eisaeid, Mohamadreza Azadie, Saba Hesaraki
Abstract: Lung cancer is a major issue in worldwide public health, requiring early diagnosis using stable techniques. This work begins a thorough investigation of the use of machine learning (ML) methods for precise classification of lung cancer stages. A cautious analysis is performed to overcome overfitting issues in model performance, taking into account minimum child weight and learning rate. A set of machine learning (ML) models including XGBoost (XGB), LGBM, Adaboost, Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), CatBoost, and k-Nearest Neighbor (k-NN) are run methodically and contrasted. Furthermore, the correlation between features and targets is examined using the deep neural network (DNN) model and thus their capability in detecting complex patternsis established. It is argued that several ML models can be capable of classifying lung cancer stages with great accuracy. In spite of the complexity of DNN architectures, traditional ML models like XGBoost, LGBM, and Logistic Regression excel with superior performance. The models perform better than the others in lung cancer prediction on the complete set of comparative metrics like accuracy, precision, recall, and F-1 score
Authors: Katja Schladitz, Claudia Redenbach, Tin Barisin, Christian Jung, Natascha Jeziorski, Lovro Bosnar, Juraj Fulir, Petra Gospodneti\'c
Abstract: Machine learning offers attractive solutions to challenging image processing tasks. Tedious development and parametrization of algorithmic solutions can be replaced by training a convolutional neural network or a random forest with a high potential to generalize. However, machine learning methods rely on huge amounts of representative image data along with a ground truth, usually obtained by manual annotation. Thus, limited availability of training data is a critical bottleneck. We discuss two use cases: optical quality control in industrial production and segmenting crack structures in 3D images of concrete. For optical quality control, all defect types have to be trained but are typically not evenly represented in the training data. Additionally, manual annotation is costly and often inconsistent. It is nearly impossible in the second case: segmentation of crack systems in 3D images of concrete. Synthetic images, generated based on realizations of stochastic geometry models, offer an elegant way out. A wide variety of structure types can be generated. The within structure variation is naturally captured by the stochastic nature of the models and the ground truth is for free. Many new questions arise. In particular, which characteristics of the real image data have to be met to which degree of fidelity.
Authors: Matteo Dalle Vedove, Matteo Bonetto, Edoardo Lamon, Luigi Palopoli, Matteo Saveriano, Daniele Fontanelli
Abstract: This paper presents a CAD-based approach for automated surface defect detection. We leverage the a-priori knowledge embedded in a CAD model and integrate it with point cloud data acquired from commercially available stereo and depth cameras. The proposed method first transforms the CAD model into a high-density polygonal mesh, where each vertex represents a state variable in 3D space. Subsequently, a weighted least squares algorithm is employed to iteratively estimate the state of the scanned workpiece based on the captured point cloud measurements. This framework offers the potential to incorporate information from diverse sensors into the CAD domain, facilitating a more comprehensive analysis. Preliminary results demonstrate promising performance, with the algorithm achieving convergence to a sub-millimeter standard deviation in the region of interest using only approximately 50 point cloud samples. This highlights the potential of utilising commercially available stereo cameras for high-precision quality control applications.
Authors: Wiradee Imrattanatrai, Masaki Asada, Kimihiro Hasegawa, Zhi-Qi Cheng, Ken Fukuda, Teruko Mitamura
Abstract: This paper presents VDAct, a dataset for a Video-grounded Dialogue on Event-driven Activities, alongside VDEval, a session-based context evaluation metric specially designed for the task. Unlike existing datasets, VDAct includes longer and more complex video sequences that depict a variety of event-driven activities that require advanced contextual understanding for accurate response generation. The dataset comprises 3,000 dialogues with over 30,000 question-and-answer pairs, derived from 1,000 videos with diverse activity scenarios. VDAct displays a notably challenging characteristic due to its broad spectrum of activity scenarios and wide range of question types. Empirical studies on state-of-the-art vision foundation models highlight their limitations in addressing certain question types on our dataset. Furthermore, VDEval, which integrates dialogue session history and video content summaries extracted from our supplementary Knowledge Graphs to evaluate individual responses, demonstrates a significantly higher correlation with human assessments on the VDAct dataset than existing evaluation metrics that rely solely on the context of single dialogue turns.
Authors: Yicheng Wu, Tao Song, Zhonghua Wu, Zongyuan Ge, Zhaolin Chen, Jianfei Cai
Abstract: MRI imputation aims to synthesize the missing modality from one or more available ones, which is highly desirable since it reduces scanning costs and delivers comprehensive MRI information to enhance clinical diagnosis. In this paper, we propose a unified model, CodeBrain, designed to adapt to various brain MRI imputation scenarios. The core design lies in casting various inter-modality transformations as a full-modality code prediction task. To this end, CodeBrain is trained in two stages: Reconstruction and Code Prediction. First, in the Reconstruction stage, we reconstruct each MRI modality, which is mapped into a shared latent space followed by a scalar quantization. Since such quantization is lossy and the code is low dimensional, another MRI modality belonging to the same subject is randomly selected to generate common features to supplement the code and boost the target reconstruction. In the second stage, we train another encoder by a customized grading loss to predict the full-modality codes from randomly masked MRI samples, supervised by the corresponding quantized codes generated from the first stage. In this way, the inter-modality transformation is achieved by mapping the instance-specific codes in a finite scalar space. We evaluated the proposed CodeBrain model on two public brain MRI datasets (i.e., IXI and BraTS 2023). Extensive experiments demonstrate that our CodeBrain model achieves superior imputation performance compared to four existing methods, establishing a new state of the art for unified brain MRI imputation. Codes will be released.
Authors: Bhargav Ghanekar, Lianne R. Johnson, Jacob L. Laughlin, Marcia K. O'Malley, Ashok Veeraraghavan
Abstract: Automated tracking of surgical tool keypoints in robotic surgery videos is an essential task for various downstream use cases such as skill assessment, expertise assessment, and the delineation of safety zones. In recent years, the explosion of deep learning for vision applications has led to many works in surgical instrument segmentation, while lesser focus has been on tracking specific tool keypoints, such as tool tips. In this work, we propose a novel, multi-frame context-driven deep learning framework to localize and track tool keypoints in surgical videos. We train and test our models on the annotated frames from the 2015 EndoVis Challenge dataset, resulting in state-of-the-art performance. By leveraging sophisticated deep learning models and multi-frame context, we achieve 90\% keypoint detection accuracy and a localization RMS error of 5.27 pixels. Results on a self-annotated JIGSAWS dataset with more challenging scenarios also show that the proposed multi-frame models can accurately track tool-tip and tool-base keypoints, with ${<}4.2$-pixel RMS error overall. Such a framework paves the way for accurately tracking surgical instrument keypoints, enabling further downstream use cases. Project and dataset webpage: https://tinyurl.com/mfc-tracker
Authors: Tin Barisin, Christian Jung, Anna Nowacka, Claudia Redenbach, Katja Schladitz
Abstract: Finding and properly segmenting cracks in images of concrete is a challenging task. Cracks are thin and rough and being air filled do yield a very weak contrast in 3D images obtained by computed tomography. Enhancing and segmenting dark lower-dimensional structures is already demanding. The heterogeneous concrete matrix and the size of the images further increase the complexity. ML methods have proven to solve difficult segmentation problems when trained on enough and well annotated data. However, so far, there is not much 3D image data of cracks available at all, let alone annotated. Interactive annotation is error-prone as humans can easily tell cats from dogs or roads without from roads with cars but have a hard time deciding whether a thin and dark structure seen in a 2D slice continues in the next one. Training networks by synthetic, simulated images is an elegant way out, bears however its own challenges. In this contribution, we describe how to generate semi-synthetic image data to train CNN like the well known 3D U-Net or random forests for segmenting cracks in 3D images of concrete. The thickness of real cracks varies widely, both, within one crack as well as from crack to crack in the same sample. The segmentation method should therefore be invariant with respect to scale changes. We introduce the so-called RieszNet, designed for exactly this purpose. Finally, we discuss how to generalize the ML crack segmentation methods to other concrete types.
Authors: Juan Wen (Zhengzhou University, ETH Zurich), Weiyan Hou (Zhengzhou University), Luc Van Gool (ETH Zurich, KU Leuven, INSAIT, Sofia University), Radu Timofte (University of Wurzburg)
Abstract: In recent years, Transformers-based models have made significant progress in the field of image restoration by leveraging their inherent ability to capture complex contextual features. Recently, Mamba models have made a splash in the field of computer vision due to their ability to handle long-range dependencies and their significant computational efficiency compared to Transformers. However, Mamba currently lags behind Transformers in contextual learning capabilities. To overcome the limitations of these two models, we propose a Mamba-Transformer hybrid image restoration model called MatIR. Specifically, MatIR cross-cycles the blocks of the Transformer layer and the Mamba layer to extract features, thereby taking full advantage of the advantages of the two architectures. In the Mamba module, we introduce the Image Inpainting State Space (IRSS) module, which traverses along four scan paths to achieve efficient processing of long sequence data. In the Transformer module, we combine triangular window-based local attention with channel-based global attention to effectively activate the attention mechanism over a wider range of image pixels. Extensive experimental results and ablation studies demonstrate the effectiveness of our approach.
Authors: Amanturdieva Akmaral, Muhammad Hamza Zafar
Abstract: This paper presents a comprehensive study and improvement of the Restormer architecture for high-resolution image motion deblurring. We introduce architectural modifications that reduce model complexity by 18.4% while maintaining or improving performance through optimized attention mechanisms. Our enhanced training pipeline incorporates additional transformations including color jitter, Gaussian blur, and perspective transforms to improve model robustness as well as a new frequency loss term. Extensive experiments on the RealBlur-R, RealBlur-J, and Ultra-High-Definition Motion blurred (UHDM) datasets demonstrate the effectiveness of our approach. The improved architecture shows better convergence behavior and reduced training time while maintaining competitive performance across challenging scenarios. We also provide detailed ablation studies analyzing the impact of our modifications on model behavior and performance. Our results suggest that thoughtful architectural simplification combined with enhanced training strategies can yield more efficient yet equally capable models for motion deblurring tasks. Code and Data Available at: https://github.com/hamzafer/image-deblurring
Authors: Enze Xie, Junsong Chen, Yuyang Zhao, Jincheng Yu, Ligeng Zhu, Yujun Lin, Zhekai Zhang, Muyang Li, Junyu Chen, Han Cai, Bingchen Liu, Daquan Zhou, Song Han
Abstract: This paper presents SANA-1.5, a linear Diffusion Transformer for efficient scaling in text-to-image generation. Building upon SANA-1.0, we introduce three key innovations: (1) Efficient Training Scaling: A depth-growth paradigm that enables scaling from 1.6B to 4.8B parameters with significantly reduced computational resources, combined with a memory-efficient 8-bit optimizer. (2) Model Depth Pruning: A block importance analysis technique for efficient model compression to arbitrary sizes with minimal quality loss. (3) Inference-time Scaling: A repeated sampling strategy that trades computation for model capacity, enabling smaller models to match larger model quality at inference time. Through these strategies, SANA-1.5 achieves a text-image alignment score of 0.72 on GenEval, which can be further improved to 0.80 through inference scaling, establishing a new SoTA on GenEval benchmark. These innovations enable efficient model scaling across different compute budgets while maintaining high quality, making high-quality image generation more accessible.
Authors: Abhinav Pratap, Sushant Kumar, Suchinton Chakravarty
Abstract: This study addresses the need for accurate and efficient object detection in assistive technologies for visually impaired individuals. We evaluate four real-time object detection algorithms YOLO, SSD, Faster R-CNN, and Mask R-CNN within the context of indoor navigation assistance. Using the Indoor Objects Detection dataset, we analyze detection accuracy, processing speed, and adaptability to indoor environments. Our findings highlight the trade-offs between precision and efficiency, offering insights into selecting optimal algorithms for realtime assistive navigation. This research advances adaptive machine learning applications, enhancing indoor navigation solutions for the visually impaired and promoting accessibility.
Authors: Wei-Lun Chen, Chia-Yeh Hsieh, Yu-Hsiang Kao, Kai-Chun Liu, Sheng-Yu Peng, Yu Tsao
Abstract: This study presents a novel approach to human keypoint detection in low-resolution thermal images using transfer learning techniques. We introduce the first application of the Timed Up and Go (TUG) test in thermal image computer vision, establishing a new paradigm for mobility assessment. Our method leverages a MobileNetV3-Small encoder and a ViTPose decoder, trained using a composite loss function that balances latent representation alignment and heatmap accuracy. The model was evaluated using the Object Keypoint Similarity (OKS) metric from the COCO Keypoint Detection Challenge. The proposed model achieves better performance with AP, AP50, and AP75 scores of 0.861, 0.942, and 0.887 respectively, outperforming traditional supervised learning approaches like Mask R-CNN and ViTPose-Base. Moreover, our model demonstrates superior computational efficiency in terms of parameter count and FLOPS. This research lays a solid foundation for future clinical applications of thermal imaging in mobility assessment and rehabilitation monitoring.
Authors: Shiho Noda, Atsuyuki Miyai, Qing Yu, Go Irie, Kiyoharu Aizawa
Abstract: Out-of-distribution (OOD) detection is a task that detects OOD samples during inference to ensure the safety of deployed models. However, conventional benchmarks have reached performance saturation, making it difficult to compare recent OOD detection methods. To address this challenge, we introduce three novel OOD detection benchmarks that enable a deeper understanding of method characteristics and reflect real-world conditions. First, we present ImageNet-X, designed to evaluate performance under challenging semantic shifts. Second, we propose ImageNet-FS-X for full-spectrum OOD detection, assessing robustness to covariate shifts (feature distribution shifts). Finally, we propose Wilds-FS-X, which extends these evaluations to real-world datasets, offering a more comprehensive testbed. Our experiments reveal that recent CLIP-based OOD detection methods struggle to varying degrees across the three proposed benchmarks, and none of them consistently outperforms the others. We hope the community goes beyond specific benchmarks and includes more challenging conditions reflecting real-world scenarios. The code is https://github.com/hoshi23/OOD-X-Banchmarks.
Authors: Chengxi Zeng, David Smithard, Alberto M Gambaruto, Tilo Burghardt
Abstract: Vision foundation models have demonstrated exceptional generalization capabilities in segmentation tasks for both generic and specialized images. However, a performance gap persists between foundation models and task-specific, specialized models. Fine-tuning foundation models on downstream datasets is often necessary to bridge this gap. Unfortunately, obtaining fully annotated ground truth for downstream datasets is both challenging and costly. To address this limitation, we propose a novel test-time training paradigm that enhances the performance of foundation models on downstream datasets without requiring full annotations. Specifically, our method employs simple point prompts to guide a test-time semi-self-supervised training task. The model learns by resolving the ambiguity of the point prompt through various augmentations. This approach directly tackles challenges in the medical imaging field, where acquiring annotations is both time-intensive and expensive. We conducted extensive experiments on our new Videofluoroscopy dataset (VFSS-5k) for the instance segmentation task, achieving an average Dice coefficient of 0.868 across 12 anatomies with a single model.
Authors: Daniel Bermuth, Alexander Poeppel, Wolfgang Reif
Abstract: In the rapidly advancing domain of computer vision, accurately estimating the poses of multiple individuals from various viewpoints remains a significant challenge, especially when reliability is a key requirement. This paper introduces a novel algorithm that excels in multi-view, multi-person pose estimation by incorporating depth information. An extensive evaluation demonstrates that the proposed algorithm not only generalizes well to unseen datasets, and shows a fast runtime performance, but also is adaptable to different keypoints. To support further research, all of the work is publicly accessible.
Authors: G\"orkay Aydemir, Xiongyi Cai, Weidi Xie, Fatma G\"uney
Abstract: In this paper, we consider the problem of long-term point tracking, which requires consistent identification of points across multiple frames in a video, despite changes in appearance, lighting, perspective, and occlusions. We target online tracking on a frame-by-frame basis, making it suitable for real-world, streaming scenarios. Specifically, we introduce Track-On, a simple transformer-based model designed for online long-term point tracking. Unlike prior methods that depend on full temporal modeling, our model processes video frames causally without access to future frames, leveraging two memory modules -- spatial memory and context memory -- to capture temporal information and maintain reliable point tracking over long time horizons. At inference time, it employs patch classification and refinement to identify correspondences and track points with high accuracy. Through extensive experiments, we demonstrate that Track-On sets a new state-of-the-art for online models and delivers superior or competitive results compared to offline approaches on seven datasets, including the TAP-Vid benchmark. Our method offers a robust and scalable solution for real-time tracking in diverse applications. Project page: https://kuis-ai.github.io/track_on
Authors: Parth Ganeriwala, Amy Alvarez, Abdullah AlQahtani, Siddhartha Bhattacharyya, Mohammed Abdul Hafeez Khan, Natasha Neogi
Abstract: The increasing complexity of autonomous systems has amplified the need for accurate and reliable labeling of runway and taxiway markings to ensure operational safety. Precise detection and labeling of these markings are critical for tasks such as navigation, landing assistance, and ground control automation. Existing labeling algorithms, like the Automated Line Identification and Notation Algorithm (ALINA), have demonstrated success in identifying taxiway markings but encounter significant challenges when applied to runway markings. This limitation arises due to notable differences in line characteristics, environmental context, and interference from elements such as shadows, tire marks, and varying surface conditions. To address these challenges, we modified ALINA by adjusting color thresholds and refining region of interest (ROI) selection to better suit runway-specific contexts. While these modifications yielded limited improvements, the algorithm still struggled with consistent runway identification, often mislabeling elements such as the horizon or non-relevant background features. This highlighted the need for a more robust solution capable of adapting to diverse visual interferences. In this paper, we propose integrating a classification step using a Convolutional Neural Network (CNN) named AssistNet. By incorporating this classification step, the detection pipeline becomes more resilient to environmental variations and misclassifications. This work not only identifies the challenges but also outlines solutions, paving the way for improved automated labeling techniques essential for autonomous aviation systems.
Authors: Shi Chen, Lefei Zhang, Liangpei Zhang
Abstract: Mamba has demonstrated exceptional performance in visual tasks due to its powerful global modeling capabilities and linear computational complexity, offering considerable potential in hyperspectral image super-resolution (HSISR). However, in HSISR, Mamba faces challenges as transforming images into 1D sequences neglects the spatial-spectral structural relationships between locally adjacent pixels, and its performance is highly sensitive to input order, which affects the restoration of both spatial and spectral details. In this paper, we propose HSRMamba, a contextual spatial-spectral modeling state space model for HSISR, to address these issues both locally and globally. Specifically, a local spatial-spectral partitioning mechanism is designed to establish patch-wise causal relationships among adjacent pixels in 3D features, mitigating the local forgetting issue. Furthermore, a global spectral reordering strategy based on spectral similarity is employed to enhance the causal representation of similar pixels across both spatial and spectral dimensions. Finally, experimental results demonstrate our HSRMamba outperforms the state-of-the-art methods in quantitative quality and visual results. Code will be available soon.
Authors: Peter J. Bentley, Soo Ling Lim, Fuyuki Ishikawa
Abstract: Large Language Model (LLM) image recognition is a powerful tool for extracting data from images, but accuracy depends on providing sufficient cues in the prompt - requiring a domain expert for specialized tasks. We introduce Cue Learning using Evolution for Accurate Recognition (CLEAR), which uses a combination of LLMs and evolutionary computation to generate and optimize cues such that recognition of specialized features in images is improved. It achieves this by auto-generating a novel domain-specific representation and then using it to optimize suitable textual cues with a genetic algorithm. We apply CLEAR to the real-world task of identifying sustainability data from interior and exterior images of buildings. We investigate the effects of using a variable-length representation compared to fixed-length and show how LLM consistency can be improved by refactoring from categorical to real-valued estimates. We show that CLEAR enables higher accuracy compared to expert human recognition and human-authored prompts in every task with error rates improved by up to two orders of magnitude and an ablation study evincing solution concision.
Authors: Faegheh Sardari, Armin Mustafa, Philip J. B. Jackson, Adrian Hilton
Abstract: Dense action detection involves detecting multiple co-occurring actions in an untrimmed video while action classes are often ambiguous and represent overlapping concepts. To address this challenge task, we introduce a novel perspective inspired by how humans tackle complex tasks by breaking them into manageable sub-tasks. Instead of relying on a single network to address the entire problem, as in current approaches, we propose decomposing the problem into detecting key concepts present in action classes, specifically, detecting dense static concepts and detecting dense dynamic concepts, and assigning them to distinct, specialized networks. Furthermore, simultaneous actions in a video often exhibit interrelationships, and exploiting these relationships can improve performance. However, we argue that current networks fail to effectively learn these relationships due to their reliance on binary cross-entropy optimization, which treats each class independently. To address this limitation, we propose providing explicit supervision on co-occurring concepts during network optimization through a novel language-guided contrastive learning loss. Our extensive experiments demonstrate the superiority of our approach over state-of-the-art methods, achieving substantial relative improvements of 23.4% and 2.5% mAP on the challenging benchmark datasets, Charades and MultiTHUMOS.
Authors: Kyusu Ahn, Jinpyo Kim, Chanwoo Park, JiSoo Kim, Jaejin Lee
Abstract: Under-Display Camera (UDC) houses a digital camera lens under a display panel. However, UDC introduces complex degradations such as noise, blur, decrease in transmittance, and flare. Despite the remarkable progress, previous research on UDC mainly focuses on eliminating diffraction in the spatial domain and rarely explores its potential in the frequency domain. It is essential to consider both the spatial and frequency domains effectively. For example, degradations, such as noise and blur, can be addressed by local information (e.g., CNN kernels in the spatial domain). At the same time, tackling flares may require leveraging global information (e.g., the frequency domain). In this paper, we revisit the UDC degradations in the Fourier space and figure out intrinsic frequency priors that imply the presence of the flares. Based on this observation, we propose a novel multi-level DNN architecture called SFIM. It efficiently restores UDC-distorted images by integrating local and global (the collective contribution of all points in the image) information. The architecture exploits CNNs to capture local information and FFT-based models to capture global information. SFIM comprises a spatial domain block (SDB), a Frequency Domain Block (FDB), and an Attention-based Multi-level Integration Block (AMIB). Specifically, SDB focuses more on detailed textures such as noise and blur, FDB emphasizes irregular texture loss in extensive areas such as flare, and AMIB enables effective cross-domain interaction. SFIM's superior performance over state-of-the-art approaches is demonstrated through rigorous quantitative and qualitative assessments across three UDC benchmarks.
Authors: Yi Ding, Lijun Li, Bing Cao, Jing Shao
Abstract: Large Vision-Language Models (VLMs) have achieved remarkable performance across a wide range of tasks. However, their deployment in safety-critical domains poses significant challenges. Existing safety fine-tuning methods, which focus on textual or multimodal content, fall short in addressing challenging cases or disrupt the balance between helpfulness and harmlessness. Our evaluation highlights a safety reasoning gap: these methods lack safety visual reasoning ability, leading to such bottlenecks. To address this limitation and enhance both visual perception and reasoning in safety-critical contexts, we propose a novel dataset that integrates multi-image inputs with safety Chain-of-Thought (CoT) labels as fine-grained reasoning logic to improve model performance. Specifically, we introduce the Multi-Image Safety (MIS) dataset, an instruction-following dataset tailored for multi-image safety scenarios, consisting of training and test splits. Our experiments demonstrate that fine-tuning InternVL2.5-8B with MIS significantly outperforms both powerful open-source models and API-based models in challenging multi-image tasks requiring safety-related visual reasoning. This approach not only delivers exceptional safety performance but also preserves general capabilities without any trade-offs. Specifically, fine-tuning with MIS increases average accuracy by 0.83% across five general benchmarks and reduces the Attack Success Rate (ASR) on multiple safety benchmarks by a large margin. Data and Models are released under: \href{https://dripnowhy.github.io/MIS/}{\texttt{https://dripnowhy.github.io/MIS/}}
URLs: https://dripnowhy.github.io/MIS/, https://dripnowhy.github.io/MIS/
Authors: Amna Murtada, Omnia Abdelrhman, Tahani Abdalla Attia
Abstract: Facial Emotion Recognition has emerged as increasingly pivotal in the domain of User Experience, notably within modern usability testing, as it facilitates a deeper comprehension of user satisfaction and engagement. This study aims to extend the ResEmoteNet model by employing a knowledge distillation framework to develop Mini-ResEmoteNet models - lightweight student models - tailored for usability testing. Experiments were conducted on the FER2013 and RAF-DB datasets to assess the efficacy of three student model architectures: Student Model A, Student Model B, and Student Model C. Their development involves reducing the number of feature channels in each layer of the teacher model by approximately 50%, 75%, and 87.5%. Demonstrating exceptional performance on the FER2013 dataset, Student Model A (E1) achieved a test accuracy of 76.33%, marking a 0.21% absolute improvement over EmoNeXt. Moreover, the results exhibit absolute improvements in terms of inference speed and memory usage during inference compared to the ResEmoteNet model. The findings indicate that the proposed methods surpass other state-of-the-art approaches.
Authors: Placido Falqueto, Alberto Sanfeliu, Luigi Palopoli, Daniele Fontanelli
Abstract: A clear understanding of where humans move in a scenario, their usual paths and speeds, and where they stop, is very important for different applications, such as mobility studies in urban areas or robot navigation tasks within human-populated environments. We propose in this article, a neural architecture based on Vision Transformers (ViTs) to provide this information. This solution can arguably capture spatial correlations more effectively than Convolutional Neural Networks (CNNs). In the paper, we describe the methodology and proposed neural architecture and show the experiments' results with a standard dataset. We show that the proposed ViT architecture improves the metrics compared to a method based on a CNN.
Authors: Kyusu Ahn, JiSoo Kim, Sangik Lee, HyunGyu Lee, Byeonghyun Ko, Chanwoo Park, Jaejin Lee
Abstract: Under Display Camera (UDC) is an advanced imaging system that places a digital camera lens underneath a display panel, effectively concealing the camera. However, the display panel significantly degrades captured images or videos, introducing low transmittance, blur, noise, and flare issues. Tackling such issues is challenging because of the complex degradation of UDCs, including diverse flare patterns. Despite extensive research on UDC images and their restoration models, studies on videos have yet to be significantly explored. While two UDC video datasets exist, they primarily focus on unrealistic or synthetic UDC degradation rather than real-world UDC degradation. In this paper, we propose a real-world UDC video dataset called UDC-VIT. Unlike existing datasets, only UDC-VIT exclusively includes human motions that target facial recognition. We propose a video-capturing system to simultaneously acquire non-degraded and UDC-degraded videos of the same scene. Then, we align a pair of captured videos frame by frame, using discrete Fourier transform (DFT). We compare UDC-VIT with six representative UDC still image datasets and two existing UDC video datasets. Using six deep-learning models, we compare UDC-VIT and an existing synthetic UDC video dataset. The results indicate the ineffectiveness of models trained on earlier synthetic UDC video datasets, as they do not reflect the actual characteristics of UDC-degraded videos. We also demonstrate the importance of effective UDC restoration by evaluating face recognition accuracy concerning PSNR, SSIM, and LPIPS scores. UDC-VIT enables further exploration in the UDC video restoration and offers better insights into the challenge. UDC-VIT is available at our project site.
Authors: Ruofan Liang, Zan Gojcic, Huan Ling, Jacob Munkberg, Jon Hasselgren, Zhi-Hao Lin, Jun Gao, Alexander Keller, Nandita Vijaykumar, Sanja Fidler, Zian Wang
Abstract: Understanding and modeling lighting effects are fundamental tasks in computer vision and graphics. Classic physically-based rendering (PBR) accurately simulates the light transport, but relies on precise scene representations--explicit 3D geometry, high-quality material properties, and lighting conditions--that are often impractical to obtain in real-world scenarios. Therefore, we introduce DiffusionRenderer, a neural approach that addresses the dual problem of inverse and forward rendering within a holistic framework. Leveraging powerful video diffusion model priors, the inverse rendering model accurately estimates G-buffers from real-world videos, providing an interface for image editing tasks, and training data for the rendering model. Conversely, our rendering model generates photorealistic images from G-buffers without explicit light transport simulation. Experiments demonstrate that DiffusionRenderer effectively approximates inverse and forwards rendering, consistently outperforming the state-of-the-art. Our model enables practical applications from a single video input--including relighting, material editing, and realistic object insertion.
Authors: Hao Dong, Moru Liu, Kaiyang Zhou, Eleni Chatzi, Juho Kannala, Cyrill Stachniss, Olga Fink
Abstract: In real-world scenarios, achieving domain adaptation and generalization poses significant challenges, as models must adapt to or generalize across unknown target distributions. Extending these capabilities to unseen multimodal distributions, i.e., multimodal domain adaptation and generalization, is even more challenging due to the distinct characteristics of different modalities. Significant progress has been made over the years, with applications ranging from action recognition to semantic segmentation. Besides, the recent advent of large-scale pre-trained multimodal foundation models, such as CLIP, has inspired works leveraging these models to enhance adaptation and generalization performances or adapting them to downstream tasks. This survey provides the first comprehensive review of recent advances from traditional approaches to foundation models, covering: (1) Multimodal domain adaptation; (2) Multimodal test-time adaptation; (3) Multimodal domain generalization; (4) Domain adaptation and generalization with the help of multimodal foundation models; and (5) Adaptation of multimodal foundation models. For each topic, we formally define the problem and thoroughly review existing methods. Additionally, we analyze relevant datasets and applications, highlighting open challenges and potential future research directions. We maintain an active repository that contains up-to-date literature at https://github.com/donghao51/Awesome-Multimodal-Adaptation.
URLs: https://github.com/donghao51/Awesome-Multimodal-Adaptation.
Authors: Yinbo Chen, Rohit Girdhar, Xiaolong Wang, Sai Saketh Rambhatla, Ishan Misra
Abstract: Tokenizing images into compact visual representations is a key step in learning efficient and high-quality image generative models. We present a simple diffusion tokenizer (DiTo) that learns compact visual representations for image generation models. Our key insight is that a single learning objective, diffusion L2 loss, can be used for training scalable image tokenizers. Since diffusion is already widely used for image generation, our insight greatly simplifies training such tokenizers. In contrast, current state-of-the-art tokenizers rely on an empirically found combination of heuristics and losses, thus requiring a complex training recipe that relies on non-trivially balancing different losses and pretrained supervised models. We show design decisions, along with theoretical grounding, that enable us to scale DiTo for learning competitive image representations. Our results show that DiTo is a simpler, scalable, and self-supervised alternative to the current state-of-the-art image tokenizer which is supervised. DiTo achieves competitive or better quality than state-of-the-art in image reconstruction and downstream image generation tasks.
Authors: Vishal Thengane, Xiatian Zhu, Salim Bouzerdoum, Son Lam Phung, Yunpeng Li
Abstract: The 3D point cloud representation plays a crucial role in preserving the geometric fidelity of the physical world, enabling more accurate complex 3D environments. While humans naturally comprehend the intricate relationships between objects and variations through a multisensory system, artificial intelligence (AI) systems have yet to fully replicate this capacity. To bridge this gap, it becomes essential to incorporate multiple modalities. Models that can seamlessly integrate and reason across these modalities are known as foundation models (FMs). The development of FMs for 2D modalities, such as images and text, has seen significant progress, driven by the abundant availability of large-scale datasets. However, the 3D domain has lagged due to the scarcity of labelled data and high computational overheads. In response, recent research has begun to explore the potential of applying FMs to 3D tasks, overcoming these challenges by leveraging existing 2D knowledge. Additionally, language, with its capacity for abstract reasoning and description of the environment, offers a promising avenue for enhancing 3D understanding through large pre-trained language models (LLMs). Despite the rapid development and adoption of FMs for 3D vision tasks in recent years, there remains a gap in comprehensive and in-depth literature reviews. This article aims to address this gap by presenting a comprehensive overview of the state-of-the-art methods that utilize FMs for 3D visual understanding. We start by reviewing various strategies employed in the building of various 3D FMs. Then we categorize and summarize use of different FMs for tasks such as perception tasks. Finally, the article offers insights into future directions for research and development in this field. To help reader, we have curated list of relevant papers on the topic: https://github.com/vgthengane/Awesome-FMs-in-3D.
Authors: Julian Kaltheuner, Patrick Stotko, Reinhard Klein
Abstract: Reconstructing an object's shape and appearance in terms of a mesh textured by a spatially-varying bidirectional reflectance distribution function (SVBRDF) from a limited set of images captured under collocated light is an ill-posed problem. Previous state-of-the-art approaches either aim to reconstruct the appearance directly on the geometry or additionally use texture normals as part of the appearance features. However, this requires detailed but inefficiently large meshes, that would have to be simplified in a post-processing step, or suffers from well-known limitations of normal maps such as missing shadows or incorrect silhouettes. Another limiting factor is the fixed and typically low resolution of the texture estimation resulting in loss of important surface details. To overcome these problems, we present ROSA, an inverse rendering method that directly optimizes mesh geometry with spatially adaptive mesh resolution solely based on the image data. In particular, we refine the mesh and locally condition the surface smoothness based on the estimated normal texture and mesh curvature. In addition, we enable the reconstruction of fine appearance details in high-resolution textures through a pioneering tile-based method that operates on a single pre-trained decoder network but is not limited by the network output resolution.
Authors: Nikolaos Livathinos, Christoph Auer, Maksym Lysak, Ahmed Nassar, Michele Dolfi, Panos Vagenas, Cesar Berrospi Ramis, Matteo Omenetti, Kasper Dinkla, Yusik Kim, Shubham Gupta, Rafael Teixeira de Lima, Valery Weber, Lucas Morin, Ingmar Meijer, Viktor Kuropiatnyk, Peter W. J. Staar
Abstract: We introduce Docling, an easy-to-use, self-contained, MIT-licensed, open-source toolkit for document conversion, that can parse several types of popular document formats into a unified, richly structured representation. It is powered by state-of-the-art specialized AI models for layout analysis (DocLayNet) and table structure recognition (TableFormer), and runs efficiently on commodity hardware in a small resource budget. Docling is released as a Python package and can be used as a Python API or as a CLI tool. Docling's modular architecture and efficient document representation make it easy to implement extensions, new features, models, and customizations. Docling has been already integrated in other popular open-source frameworks (e.g., LangChain, LlamaIndex, spaCy), making it a natural fit for the processing of documents and the development of high-end applications. The open-source community has fully engaged in using, promoting, and developing for Docling, which gathered 10k stars on GitHub in less than a month and was reported as the No. 1 trending repository in GitHub worldwide in November 2024.
Authors: Yukihiro Michiwaki, Takahiro Kikuchi, Takashi Ijiri, Yoko Inamoto, Hiroshi Moriya, Takumi Ogawa, Ryota Nakatani, Yuto Masaki, Yoshito Otake, Yoshinobu Sato
Abstract: This study presents the first report on the development of an artificial intelligence (AI) for automatic region segmentation of four-dimensional computer tomography (4D-CT) images during swallowing. The material consists of 4D-CT images taken during swallowing. Additionally, data for verifying the practicality of the AI were obtained from 4D-CT images during mastication and swallowing. The ground truth data for the region segmentation for the AI were created from five 4D-CT datasets of swallowing. A 3D convolutional model of nnU-Net was used for the AI. The learning and evaluation method for the AI was leave-one-out cross-validation. The number of epochs for training the nnU-Net was 100. The Dice coefficient was used as a metric to assess the AI's region segmentation accuracy. Regions with a median Dice coefficient of 0.7 or higher included the bolus, bones, tongue, and soft palate. Regions with a Dice coefficient below 0.7 included the thyroid cartilage and epiglottis. Factors that reduced the Dice coefficient included metal artifacts caused by dental crowns in the bolus and the speed of movement for the thyroid cartilage and epiglottis. In practical verification of the AI, no significant misrecognition was observed for facial bones, jaw bones, or the tongue. However, regions such as the hyoid bone, thyroid cartilage, and epiglottis were not fully delineated during fast movement. It is expected that future research will improve the accuracy of the AI's region segmentation, though the risk of misrecognition will always exist. Therefore, the development of tools for efficiently correcting the AI's segmentation results is necessary. AI-based visualization is expected to contribute not only to the deepening of motion analysis of organs during swallowing but also to improving the accuracy of swallowing CT by clearly showing the current state of its precision.
Authors: Mohammad R. Salmanpour, Amin Mousavi, Yixi Xu, William B Weeks, Ilker Hacihaliloglu
Abstract: Purpose: This study examines the core traits of image-to-image translation (I2I) networks, focusing on their effectiveness and adaptability in everyday clinical settings. Methods: We have analyzed data from 794 patients diagnosed with prostate cancer (PCa), using ten prominent 2D/3D I2I networks to convert ultrasound (US) images into MRI scans. We also introduced a new analysis of Radiomic features (RF) via the Spearman correlation coefficient to explore whether networks with high performance (SSIM>85%) could detect subtle RFs. Our study further examined synthetic images by 7 invited physicians. As a final evaluation study, we have investigated the improvement that are achieved using the synthetic MRI data on two traditional machine learning and one deep learning method. Results: In quantitative assessment, 2D-Pix2Pix network substantially outperformed the other 7 networks, with an average SSIM~0.855. The RF analysis revealed that 76 out of 186 RFs were identified using the 2D-Pix2Pix algorithm alone, although half of the RFs were lost during the translation process. A detailed qualitative review by 7 medical doctors noted a deficiency in low-level feature recognition in I2I tasks. Furthermore, the study found that synthesized image-based classification outperformed US image-based classification with an average accuracy and AUC~0.93. Conclusion: This study showed that while 2D-Pix2Pix outperformed cutting-edge networks in low-level feature discovery and overall error and similarity metrics, it still requires improvement in low-level feature performance, as highlighted by Group 3. Further, the study found using synthetic image-based classification outperformed original US image-based methods.
Authors: Liudi Yang, Sai Manoj Prakhya, Senhua Zhu, Ziyuan Liu
Abstract: We propose a lifelong 3D mapping framework that is modular, cloud-native by design and more importantly, works for both hand-held and robot-mounted 3D LiDAR mapping systems. Our proposed framework comprises of dynamic point removal, multi-session map alignment, map change detection and map version control. First, our sensor-setup agnostic dynamic point removal algorithm works seamlessly with both hand-held and robot-mounted setups to produce clean static 3D maps. Second, the multi-session map alignment aligns these clean static maps automatically, without manual parameter fine-tuning, into a single reference frame, using a two stage approach based on feature descriptor matching and fine registration. Third, our novel map change detection identifies positive and negative changes between two aligned maps. Finally, the map version control maintains a single base map that represents the current state of the environment, and stores the detected positive and negative changes, and boundary information. Our unique map version control system can reconstruct any of the previous clean session maps and allows users to query changes between any two random mapping sessions, all without storing any input raw session maps, making it very unique. Extensive experiments are performed using hand-held commercial LiDAR mapping devices and open-source robot-mounted LiDAR SLAM algorithms to evaluate each module and the whole 3D lifelong mapping framework.
Authors: Joanna Hong, Sanjeel Parekh, Honglie Chen, Jacob Donley, Ke Tan, Buye Xu, Anurag Kumar
Abstract: Building reliable speech systems often requires combining multiple modalities, like audio and visual cues. While such multimodal solutions frequently lead to improvements in performance and may even be critical in certain cases, they come with several constraints such as increased sensory requirements, computational cost, and modality synchronization, to mention a few. These challenges constrain the direct uses of these multimodal solutions in real-world applications. In this work, we develop approaches where the learning happens with all available modalities but the deployment or inference is done with just one or reduced modalities. To do so, we propose a Multimodal Training and Unimodal Deployment (MUTUD) framework which includes a Temporally Aligned Modality feature Estimation (TAME) module that can estimate information from missing modality using modalities present during inference. This innovative approach facilitates the integration of information across different modalities, enhancing the overall inference process by leveraging the strengths of each modality to compensate for the absence of certain modalities during inference. We apply MUTUD to various audiovisual speech tasks and show that it can reduce the performance gap between the multimodal and corresponding unimodal models to a considerable extent. MUTUD can achieve this while reducing the model size and compute compared to multimodal models, in some cases by almost 80%.
Authors: Rafiul Islam, Jihad Khan Dipu, Mehedi Hasan Tusar
Abstract: With over 2 million new cases identified annually, skin cancer is the most prevalent type of cancer globally and the second most common in Bangladesh, following breast cancer. Early detection and treatment are crucial for enhancing patient outcomes; however, Bangladesh faces a shortage of dermatologists and qualified medical professionals capable of diagnosing and treating skin cancer. As a result, many cases are diagnosed only at advanced stages. Research indicates that deep learning algorithms can effectively classify skin cancer images. However, these models typically lack interpretability, making it challenging to understand their decision-making processes. This lack of clarity poses barriers to utilizing deep learning in improving skin cancer detection and treatment. In this article, we present a method aimed at enhancing the interpretability of deep learning models for skin cancer classification in Bangladesh. Our technique employs a combination of saliency maps and attention maps to visualize critical features influencing the model's diagnoses.
Authors: Ali Abdollahzadeh, Ricardo Coronado-Leija, Hong-Hsi Lee, Alejandra Sierra, Els Fieremans, Dmitry S. Novikov
Abstract: Early diagnosis and noninvasive monitoring of neurological disorders require sensitivity to elusive cellular-level alterations that occur much earlier than volumetric changes observable with the millimeter-resolution of medical imaging modalities. Morphological changes in axons, such as axonal varicosities or beadings, are observed in neurological disorders, as well as in development and aging. Here, we reveal the sensitivity of time-dependent diffusion MRI (dMRI) to axonal morphology at the micrometer scale. Scattering theory uncovers the two parameters that determine the diffusive dynamics of water in axons: the average reciprocal cross-section and the variance of long-range cross-sectional fluctuations. This theoretical development allowed us to predict dMRI metrics sensitive to axonal alterations across tens of thousands of axons in seconds rather than months of simulations in a rat model of traumatic brain injury. Our approach bridges the gap between micrometers and millimeters in resolution, offering quantitative, objective biomarkers applicable to a broad spectrum of neurological disorders.
Authors: Tatiana A. Bubba, Luca Ratti, Andrea Sebastiani
Abstract: In this paper, we revisit a supervised learning approach based on unrolling, known as $\Psi$DONet, by providing a deeper microlocal interpretation for its theoretical analysis, and extending its study to the case of sparse-angle tomography. Furthermore, we refine the implementation of the original $\Psi$DONet considering special filters whose structure is specifically inspired by the streak artifact singularities characterizing tomographic reconstructions from incomplete data. This allows to considerably lower the number of (learnable) parameters while preserving (or even slightly improving) the same quality for the reconstructions from limited-angle data and providing a proof-of-concept for the case of sparse-angle tomographic data.
Authors: Anup Saha, Joseph Adeola, Nuria Ferrera, Adam Mothershaw, Gisele Rezze, S\'eraphin Gaborit, Brian D'Alessandro, James Hudson, Gyula Szab\'o, Balazs Pataki, Hayat Rajani, Sana Nazari, Hassan Hayat, Clare Primiero, H. Peter Soyer, Josep Malvehy, Rafael Garcia
Abstract: Artificial intelligence has significantly advanced skin cancer diagnosis by enabling rapid and accurate detection of malignant lesions. In this domain, most publicly available image datasets consist of single, isolated skin lesions positioned at the center of the image. While these lesion-centric datasets have been fundamental for developing diagnostic algorithms, they lack the context of the surrounding skin, which is critical for improving lesion detection. The iToBoS dataset was created to address this challenge. It includes 16,954 images of skin regions from 100 participants, captured using 3D total body photography. Each image roughly corresponds to a $7 \times 9$ cm section of skin with all suspicious lesions annotated using bounding boxes. Additionally, the dataset provides metadata such as anatomical location, age group, and sun damage score for each image. This dataset aims to facilitate training and benchmarking of algorithms, with the goal of enabling early detection of skin cancer and deployment of this technology in non-clinical environments.
Authors: Yuqin Cao, Xiongkuo Min, Yixuan Gao, Wei Sun, Guangtao Zhai
Abstract: Many video-to-audio (VTA) methods have been proposed for dubbing silent AI-generated videos. An efficient quality assessment method for AI-generated audio-visual content (AGAV) is crucial for ensuring audio-visual quality. Existing audio-visual quality assessment methods struggle with unique distortions in AGAVs, such as unrealistic and inconsistent elements. To address this, we introduce AGAVQA, the first large-scale AGAV quality assessment dataset, comprising 3,382 AGAVs from 16 VTA methods. AGAVQA includes two subsets: AGAVQA-MOS, which provides multi-dimensional scores for audio quality, content consistency, and overall quality, and AGAVQA-Pair, designed for optimal AGAV pair selection. We further propose AGAV-Rater, a LMM-based model that can score AGAVs, as well as audio and music generated from text, across multiple dimensions, and selects the best AGAV generated by VTA methods to present to the user. AGAV-Rater achieves state-of-the-art performance on AGAVQA, Text-to-Audio, and Text-to-Music datasets. Subjective tests also confirm that AGAV-Rater enhances VTA performance and user experience. The project page is available at https://agav-rater.github.io.
Authors: Yuxin Zuo, Shang Qu, Yifei Li, Zhangren Chen, Xuekai Zhu, Ermo Hua, Kaiyan Zhang, Ning Ding, Bowen Zhou
Abstract: We introduce MedXpertQA, a highly challenging and comprehensive benchmark to evaluate expert-level medical knowledge and advanced reasoning. MedXpertQA includes 4,460 questions spanning 17 specialties and 11 body systems. It includes two subsets, Text for text evaluation and MM for multimodal evaluation. Notably, MM introduces expert-level exam questions with diverse images and rich clinical information, including patient records and examination results, setting it apart from traditional medical multimodal benchmarks with simple QA pairs generated from image captions. MedXpertQA applies rigorous filtering and augmentation to address the insufficient difficulty of existing benchmarks like MedQA, and incorporates specialty board questions to improve clinical relevance and comprehensiveness. We perform data synthesis to mitigate data leakage risk and conduct multiple rounds of expert reviews to ensure accuracy and reliability. We evaluate 16 leading models on MedXpertQA. Moreover, medicine is deeply connected to real-world decision-making, providing a rich and representative setting for assessing reasoning abilities beyond mathematics and code. To this end, we develop a reasoning-oriented subset to facilitate the assessment of o1-like models.
Authors: Donghwa Kang, Woojin Shin, Cheol-Ho Hong, Minsuk Koo, Brent ByungHoon Kang, Jinkyu Lee, Hyeongboo Baek
Abstract: Given the energy constraints in autonomous mobile agents (AMAs), such as unmanned vehicles, spiking neural networks (SNNs) are increasingly favored as a more efficient alternative to traditional artificial neural networks. AMAs employ multi-object detection (MOD) from multiple cameras to identify nearby objects while ensuring two essential objectives, (R1) timing guarantee and (R2) high accuracy for safety. In this paper, we propose RT-SNN, the first system design, aiming at achieving R1 and R2 in SNN-based MOD systems on AMAs. Leveraging the characteristic that SNNs gather feature data of input image termed as membrane potential, through iterative computation over multiple timesteps, RT-SNN provides multiple execution options with adjustable timesteps and a novel method for reusing membrane potential to support R1. Then, it captures how these execution strategies influence R2 by introducing a novel notion of mean absolute error and membrane confidence. Further, RT-SNN develops a new scheduling framework consisting of offline schedulability analysis for R1 and a run-time scheduling algorithm for R2 using the notion of membrane confidence. We deployed RT-SNN to Spiking-YOLO, the SNN-based MOD model derived from ANN-to-SNN conversion, and our experimental evaluation confirms its effectiveness in meeting the R1 and R2 requirements while providing significant energy efficiency.
Authors: Wentao Chen, Tianming Xu, Weimin Zhou
Abstract: Image denoising algorithms have been extensively investigated for medical imaging. To perform image denoising, penalized least-squares (PLS) problems can be designed and solved, in which the penalty term encodes prior knowledge of the object being imaged. Sparsity-promoting penalties, such as total variation (TV), have been a popular choice for regularizing image denoising problems. However, such hand-crafted penalties may not be able to preserve task-relevant information in measured image data and can lead to oversmoothed image appearances and patchy artifacts that degrade signal detectability. Supervised learning methods that employ convolutional neural networks (CNNs) have emerged as a popular approach to denoising medical images. However, studies have shown that CNNs trained with loss functions based on traditional image quality measures can lead to a loss of task-relevant information in images. Some previous works have investigated task-based loss functions that employ model observers for training the CNN denoising models. However, such training processes typically require a large number of noisy and ground-truth (noise-free or low-noise) image data pairs. In this work, we propose a task-based regularization strategy for use with PLS in medical image denoising. The proposed task-based regularization is associated with the likelihood of linear test statistics of noisy images for Gaussian noise models. The proposed method does not require ground-truth image data and solves an individual optimization problem for denoising each image. Computer-simulation studies are conducted that consider a multivariate-normally distributed (MVN) lumpy background and a binary texture background. It is demonstrated that the proposed regularization strategy can effectively improve signal detectability in denoised images.
Authors: David Chuan-En Lin, Hyeonsu B. Kang, Nikolas Martelaro, Aniket Kittur, Yan-Ying Chen, Matthew K. Hong
Abstract: With recent advancements in the capabilities of Text-to-Image (T2I) AI models, product designers have begun experimenting with them in their work. However, T2I models struggle to interpret abstract language and the current user experience of T2I tools can induce design fixation rather than a more iterative, exploratory process. To address these challenges, we developed Inkspire, a sketch-driven tool that supports designers in prototyping product design concepts with analogical inspirations and a complete sketch-to-design-to-sketch feedback loop. To inform the design of Inkspire, we conducted an exchange session with designers and distilled design goals for improving T2I interactions. In a within-subjects study comparing Inkspire to ControlNet, we found that Inkspire supported designers with more inspiration and exploration of design ideas, and improved aspects of the co-creative process by allowing designers to effectively grasp the current state of the AI to guide it towards novel design intentions.
Authors: Katrina Yezzi-Woodley, Jeff Calder, Mckenzie Sweno, Chloe Siewert, Peter J. Olver
Abstract: Within anthropology, the use of three-dimensional (3D) imaging has become increasingly common and widespread since it broadens the available avenues for addressing a wide range of key anthropological issues. The ease with which 3D models can be generated and shared has major impact on research, cultural heritage, education, science communication, and public engagement, as well as contributing to the preservation of the physical specimens and archiving collections in widely accessible data bases. Current scanning protocols have the ability to create the required research quality 3D models; however, they tend to be time and labor intensive and not practical when working with large collections. Here we describe a streamlined Batch Artifact Scanning Protocol to rapidly create 3D models using a medical CT scanner. While this method can be used on a variety of material types, we have, for specificity, applied our protocol to a large collection of experimentally broken ungulate limb bones. By employing the Batch Artifact Scanning Protocol, we were able to efficiently create 3D models of 2,474 bone fragments at a rate of less than 4 minutes per specimen.
Authors: Ziyi Dong, Pengxu Wei, Liang Lin
Abstract: State-of-the-arts text-to-image generation models such as Imagen and Stable Diffusion Model have succeed remarkable progresses in synthesizing high-quality, feature-rich images with high resolution guided by human text prompts. Since certain characteristics of image content \emph{e.g.}, very specific object entities or styles, are very hard to be accurately described by text, some example-based image generation approaches have been proposed, \emph{i.e.} generating new concepts based on absorbing the salient features of a few input references. Despite of acknowledged successes, these methods have struggled on accurately capturing the reference examples' characteristics while keeping diverse and high-quality image generation, particularly in the one-shot scenario (\emph{i.e.} given only one reference). To tackle this problem, we propose a simple yet effective framework, namely DreamArtist, which adopts a novel positive-negative prompt-tuning learning strategy on the pre-trained diffusion model, and it has shown to well handle the trade-off between the accurate controllability and fidelity of image generation with only one reference example. Specifically, our proposed framework incorporates both positive and negative embeddings or adapters and optimizes them in a joint manner. The positive part aggressively captures the salient characteristics of the reference image to drive diversified generation and the negative part rectifies inadequacies from the positive part. We have conducted extensive experiments and evaluated the proposed method from image similarity (fidelity) and diversity, generation controllability, and style cloning. And our DreamArtist has achieved a superior generation performance over existing methods. Besides, our additional evaluation on extended tasks, including concept compositions and prompt-guided image editing, demonstrates its effectiveness for more applications.
Authors: Konstantinos Vilouras, Pedro Sanchez, Alison Q. O'Neil, Sotirios A. Tsaftaris
Abstract: Localizing the exact pathological regions in a given medical scan is an important imaging problem that traditionally requires a large amount of bounding box ground truth annotations to be accurately solved. However, there exist alternative, potentially weaker, forms of supervision, such as accompanying free-text reports, which are readily available. The task of performing localization with textual guidance is commonly referred to as phrase grounding. In this work, we use a publicly available Foundation Model, namely the Latent Diffusion Model, to perform this challenging task. This choice is supported by the fact that the Latent Diffusion Model, despite being generative in nature, contains cross-attention mechanisms that implicitly align visual and textual features, thus leading to intermediate representations that are suitable for the task at hand. In addition, we aim to perform this task in a zero-shot manner, i.e., without any training on the target task, meaning that the model's weights remain frozen. To this end, we devise strategies to select features and also refine them via post-processing without extra learnable parameters. We compare our proposed method with state-of-the-art approaches which explicitly enforce image-text alignment in a joint embedding space via contrastive learning. Results on a popular chest X-ray benchmark indicate that our method is competitive with SOTA on different types of pathology, and even outperforms them on average in terms of two metrics (mean IoU and AUC-ROC). Source code will be released upon acceptance at https://github.com/vios-s.
Authors: Changsong Liu, Yimeng Fan, Mingyang Li, Wei Zhang, Yanyan Liu, Yuming Li, Wenlin Li, Liang Zhang
Abstract: Edge detection is a fundamental task in computer vision. It has made great progress under the development of deep convolutional neural networks (DCNNs), some of which have achieved a beyond human-level performance. However, recent top-performing edge detection methods tend to generate thick and noisy edge lines. In this work, we solve this problem from two aspects: (1) the lack of prior knowledge regarding image edges, and (2) the issue of imbalanced pixel distribution. We propose a second-order derivative-based multi-scale contextual enhancement module (SDMCM) to help the model locate true edge pixels accurately by introducing the edge prior knowledge. We also construct a hybrid focal loss function (HFL) to alleviate the imbalanced distribution issue. In addition, we employ the conditionally parameterized convolution (CondConv) to develop a novel boundary refinement module (BRM), which can further refine the final output edge maps. In the end, we propose a U-shape network named LUS-Net which is based on the SDMCM and BRM for crisp edge detection. We perform extensive experiments on three standard benchmarks, and the experiment results illustrate that our method can predict crisp and clean edge maps and achieves state-of-the-art performance on the BSDS500 dataset (ODS=0.829), NYUD-V2 dataset (ODS=0.768), and BIPED dataset (ODS=0.903).
Authors: Kailas Dayanandan, Nikhil Kumar, Anand Sinha, Brejesh Lall
Abstract: The dual thinking framework considers fast, intuitive processing and slower, logical processing. The perception of dual thinking in vision requires images where inferences from intuitive and logical processing differ. We introduce an adversarial dataset to provide evidence for the dual thinking framework in human vision, which also aids in studying the qualitative behavior of deep learning models. The evidence underscores the importance of shape in identifying instances in human vision. Our psychophysical studies show the presence of multiple inferences in rapid succession, and analysis of errors shows the early stopping of visual processing can result in missing relevant information. Our study shows that segmentation models lack an understanding of sub-structures, as indicated by errors related to the position and number of sub-components. Additionally, the similarity in errors made by models and intuitive human processing indicates that models only address intuitive thinking in human vision. In contrast, multi-modal LLMs, including open-source models, demonstrate tremendous progress on errors made in intuitive processing. The models have improved performance on images that require logical reasoning and show recognition of sub-components. However, they have not matched the performance improvements made on errors in intuitive processing.
Authors: Shuaiyi Huang, Mara Levy, Zhenyu Jiang, Anima Anandkumar, Yuke Zhu, Linxi Fan, De-An Huang, Abhinav Shrivastava
Abstract: Sequential decision-making can be formulated as a text-conditioned video generation problem, where a video planner, guided by a text-defined goal, generates future frames visualizing planned actions, from which control actions are subsequently derived. In this work, we introduce Active Region Video Diffusion for Universal Policies (ARDuP), a novel framework for video-based policy learning that emphasizes the generation of active regions, i.e. potential interaction areas, enhancing the conditional policy's focus on interactive areas critical for task execution. This innovative framework integrates active region conditioning with latent diffusion models for video planning and employs latent representations for direct action decoding during inverse dynamic modeling. By utilizing motion cues in videos for automatic active region discovery, our method eliminates the need for manual annotations of active regions. We validate ARDuP's efficacy via extensive experiments on simulator CLIPort and the real-world dataset BridgeData v2, achieving notable improvements in success rates and generating convincingly realistic video plans.
Authors: Shengbo Wang, Jingwen Zhao, Tongming Pu, Liangbing Zhao, Xiaoyu Guo, Yue Cheng, Cong Li, Weihao Ma, Chenyu Tang, Zhenyu Xu, Ningli Wang, Luigi Occhipinti, Arokia Nathan, Ravinder Dahiya, Huaqiang Wu, Li Tao, Shuo Gao
Abstract: Optical flow, inspired by the mechanisms of biological visual systems, calculates spatial motion vectors within visual scenes that are necessary for enabling robotics to excel in complex and dynamic working environments. However, current optical flow algorithms, despite human-competitive task performance on benchmark datasets, remain constrained by unacceptable time delays (~0.6 seconds per inference, 4X human processing speed) in practical deployment. Here, we introduce a neuromorphic optical flow approach that addresses delay bottlenecks by encoding temporal information directly in a synaptic transistor array to assist spatial motion analysis. Compared to conventional spatial-only optical flow methods, our spatiotemporal neuromorphic optical flow offers the spatial-temporal consistency of motion information, rapidly identifying regions of interest in as little as 1-2 ms using the temporal motion cues derived from the embedded temporal information in the two-dimensional floating gate synaptic transistors. Thus, the visual input can be selectively filtered to achieve faster velocity calculations and various task execution. At the hardware level, due to the atomically sharp interfaces between distinct functional layers in two-dimensional van der Waals heterostructures, the synaptic transistor offers high-frequency response (~100 {\mu}s), robust non-volatility (>10000 s), and excellent endurance (>8000 cycles), enabling robust visual processing. In software benchmarks, our system outperforms state-of-the-art algorithms with a 400% speedup, frequently surpassing human-level performance while maintaining or enhancing accuracy by utilizing the temporal priors provided by the embedded temporal information.
Authors: Vanshika Vats, Marzia Binta Nizam, James Davis
Abstract: Vehicle object detection benefits from both LiDAR and camera data, with LiDAR offering superior performance in many scenarios. Fusion of these modalities further enhances accuracy, but existing methods often introduce complexity or dataset-specific dependencies. In our study, we propose a model-adaptive late-fusion method, VaLID, which validates whether each predicted bounding box is acceptable or not. Our method verifies the higher-performing, yet overly optimistic LiDAR model detections using camera detections that are obtained from either specially trained, general, or open-vocabulary models. VaLID uses a simple multi-layer perceptron trained with a high recall bias to reduce the false predictions made by the LiDAR detector, while still preserving the true ones. Evaluating with multiple combinations of LiDAR and camera detectors on the KITTI dataset, we reduce false positives by an average of 63.9%, thus outperforming the individual detectors on 3D average precision (3DAP). Our approach is model-adaptive and demonstrates state-of-the-art competitive performance even when using generic camera detectors that were not trained specifically for this dataset.
Authors: Xupeng Chen, Zhixin Lai, Kangrui Ruan, Shichu Chen, Jiaxiang Liu, Zuozhu Liu
Abstract: Artificial intelligence has made significant strides in medical visual question answering (Med-VQA), yet prevalent studies often interpret images holistically, overlooking the visual regions of interest that may contain crucial information, potentially aligning with a doctor's prior knowledge that can be incorporated with minimal annotations (e.g., bounding boxes). To address this gap, this paper introduces R-LLaVA, designed to enhance biomedical VQA understanding by integrating simple medical annotations as prior knowledge directly into the image space through CLIP. These annotated visual regions of interest are then fed into the LLaVA model during training, aiming to enrich the model's understanding of biomedical queries. Experimental evaluation on four standard Med-VQA datasets demonstrates R-LLaVA's superiority over existing state-of-the-art (SoTA) methods. Additionally, to verify the model's capability in visual comprehension, a novel multiple-choice medical visual understanding dataset is introduced, confirming the positive impact of focusing on visual regions of interest in advancing biomedical VQA understanding.
Authors: Yihao Meng, Hao Ouyang, Hanlin Wang, Qiuyu Wang, Wen Wang, Ka Leong Cheng, Zhiheng Liu, Yujun Shen, Huamin Qu
Abstract: The production of 2D animation follows an industry-standard workflow, encompassing four essential stages: character design, keyframe animation, in-betweening, and coloring. Our research focuses on reducing the labor costs in the above process by harnessing the potential of increasingly powerful generative AI. Using video diffusion models as the foundation, AniDoc emerges as a video line art colorization tool, which automatically converts sketch sequences into colored animations following the reference character specification. Our model exploits correspondence matching as an explicit guidance, yielding strong robustness to the variations (e.g., posture) between the reference character and each line art frame. In addition, our model could even automate the in-betweening process, such that users can easily create a temporally consistent animation by simply providing a character image as well as the start and end sketches. Our code is available at: https://yihao-meng.github.io/AniDoc_demo.
Authors: Liyao Jiang, Negar Hassanpour, Mohammad Salameh, Mohammadreza Samadi, Jiao He, Fengyu Sun, Di Niu
Abstract: Recent research explores the potential of Diffusion Models (DMs) for consistent object editing, which aims to modify object position, size, and composition, etc., while preserving the consistency of objects and background without changing their texture and attributes. Current inference-time methods often rely on DDIM inversion, which inherently compromises efficiency and the achievable consistency of edited images. Recent methods also utilize energy guidance which iteratively updates the predicted noise and can drive the latents away from the original image, resulting in distortions. In this paper, we propose PixelMan, an inversion-free and training-free method for achieving consistent object editing via Pixel Manipulation and generation, where we directly create a duplicate copy of the source object at target location in the pixel space, and introduce an efficient sampling approach to iteratively harmonize the manipulated object into the target location and inpaint its original location, while ensuring image consistency by anchoring the edited image to be generated to the pixel-manipulated image as well as by introducing various consistency-preserving optimization techniques during inference. Experimental evaluations based on benchmark datasets as well as extensive visual comparisons show that in as few as 16 inference steps, PixelMan outperforms a range of state-of-the-art training-based and training-free methods (usually requiring 50 steps) on multiple consistent object editing tasks.
Authors: Shu Shen, Tong Zhang, C. L. Philip Chen
Abstract: Multimodal machine learning has achieved remarkable progress in many scenarios, but its reliability is undermined by varying sample quality. In this paper, we find that current multimodal classification methods lack dynamic networks for sample-specific depth and parameters to achieve reliable inference. To this end, a novel framework for multimodal reliable classification termed Multi-Level Quality-Adaptive Dynamic Multimodal Network (QADM-Net) is proposed. QADM-Net first adopts a novel approach based on noise-free prototypes and a classifier-free design to reliably estimate the quality of each sample at both modality and feature levels. It then achieves sample-specific network depth via the \textbf{\textit{Global Confidence Normalized Depth (GCND)}} mechanism. By normalizing depth across modalities and samples, \textit{\textbf{GCND}} effectively mitigates the impact of challenging modality inputs on dynamic depth reliability. Furthermore, QADM-Net provides sample-adaptive network parameters via the \textbf{\textit{Layer-wise Greedy Parameter (LGP)}} mechanism driven by feature-level quality. The cross-modality layer-wise greedy strategy in \textbf{\textit{LGP}} designs a reliable parameter prediction paradigm for multimodal networks with variable depths for the first time. Experiments conducted on four datasets demonstrate that QADM-Net significantly outperforms state-of-the-art methods in classification performance and reliability, exhibiting strong adaptability to data with diverse quality.
Authors: Huiyuan Tian, Bonan Xu, Shijian Li, Gang Pan
Abstract: Knowledge Distillation (KD) has achieved widespread success in compressing large Vision Transformers (ViTs), but a unified theoretical framework for both ViTs and KD is still lacking. In this paper, we propose SpectralKD, a novel unified analytical framework that offers deeper insights into ViTs and optimizes KD via spectral analysis. Our model-wise analysis reveals that CaiT concentrates information in their first and last few layers, informing optimal layer selection for KD. Surprisingly, our layer-wise analysis discovers that Swin Transformer and CaiT exhibit similar spectral encoding patterns despite their architectural differences, leading to feature map alignment guideline. Building on these insights, we propose a simple yet effective spectral alignment method for KD. Benefiting from the deeper understanding by above analysis results, even such a simple strategy achieves state-of-the-art performance on ImageNet-1K without introducing any trainable parameters, improving DeiT-Tiny by $+5.2\%$ and Swin-Tiny by $+1.4\%$ in top-1 accuracy. Furthermore, our post-training analysis reveals that distilled students can reproduce spectral patterns similar to their teachers, opening a new area we term ``distillation dynamics". Code and experimental logs are available in https://github.com/thy960112/SpectralKD.
Authors: Hong Zhang, Zhongjie Duan, Xingjun Wang, Yingda Chen, Yu Zhang
Abstract: Recent advancements in diffusion models have significantly advanced text-to-image generation, yet global text prompts alone remain insufficient for achieving fine-grained control over individual entities within an image. To address this limitation, we present EliGen, a novel framework for Entity-level controlled image Generation. Firstly, we put forward regional attention, a mechanism for diffusion transformers that requires no additional parameters, seamlessly integrating entity prompts and arbitrary-shaped spatial masks. By contributing a high-quality dataset with fine-grained spatial and semantic entity-level annotations, we train EliGen to achieve robust and accurate entity-level manipulation, surpassing existing methods in both spatial precision and image quality. Additionally, we propose an inpainting fusion pipeline, extending its capabilities to multi-entity image inpainting tasks. We further demonstrate its flexibility by integrating it with other open-source models such as IP-Adapter, In-Context LoRA and MLLM, unlocking new creative possibilities. The source code, model, and dataset are published at https://github.com/modelscope/DiffSynth-Studio.git.
Authors: Farina Riaz, Fakhar Zaman, Hajime Suzuki, Sharif Abuadbba, David Nguyen
Abstract: Variational Autoencoders (VAEs) are essential tools in generative modeling and image reconstruction, with their performance heavily influenced by the encoder-decoder architecture. This study aims to improve the quality of reconstructed images by enhancing their resolution and preserving finer details, particularly when working with low-resolution inputs (16x16 pixels), where traditional VAEs often yield blurred or in-accurate results. To address this, we propose a hybrid model that combines quantum computing techniques in the VAE encoder with convolutional neural networks (CNNs) in the decoder. By upscaling the resolution from 16x16 to 32x32 during the encoding process, our approach evaluates how the model reconstructs images with enhanced resolution while maintaining key features and structures. This method tests the model's robustness in handling image reconstruction and its ability to preserve essential details despite training on lower-resolution data. We evaluate our proposed down sampling filter for Quantum VAE (Q-VAE) on the MNIST and USPS datasets and compare it with classical VAEs and a variant called Classical Direct Passing VAE (CDP-VAE), which uses windowing pooling filters in the encoding process. Performance is assessed using metrics such as the Frechet Inception Distance (FID) and Mean Squared Error (MSE), which measure the fidelity of reconstructed images. Our results demonstrate that the Q-VAE consistently outperforms both the Classical VAE and CDP-VAE, achieving significantly lower FID and MSE scores. Additionally, CDP-VAE yields better performance than C-VAE. These findings highlight the potential of quantum-enhanced VAEs to improve image reconstruction quality by enhancing resolution and preserving essential features, offering a promising direction for future applications in computer vision and synthetic data generation.
Authors: Tuan Truong, Ivo M. Baltruschat, Mark Klemens, Grit Werner, Matthias Lenga
Abstract: Purpose: This study aims to evaluate different setups of an AI-based solution to detect Protected Health Information (PHI) in medical images. Materials and Methods: Text from eight PHI and eight non-PHI categories are simulated and incorporated into a curated dataset comprising 1,000 medical images across four modalities: CT, X-ray, bone scan, and MRI. The proposed PHI detection pipeline comprises three key components: text localization, extraction, and analysis. Three vision and language models, YOLOv11, EasyOCR, and GPT-4o, are benchmarked in different setups corresponding to three key components. The performance is evaluated with classification metrics, including precision, recall, F1 score, and accuracy. Results: All four setups demonstrate strong performance in detecting PHI imprints, with all metrics exceeding 0.9. The setup that utilizes YOLOv11 for text localization and GPT-4o for text extraction and analysis achieves the highest performance in PHI detection. However, this setup incurs the highest cost due to the increased number of generated tokens associated with GPT-4o model. Conversely, the setup using solely GPT-4o for the end-to-end pipeline exhibits the lowest performance but showcases the feasibility of multi-modal models in solving complex tasks. Conclusion: For optimal text localization and extraction, it is recommended to fine-tune an object detection model and utilize built-in Optical Character Recognition (OCR) software. Large language models like GPT-4o can be effectively leveraged to reason about and semantically analyze the PHI content. Although the vision capability of GPT-4o is promising for reading image crops, it remains limited for end-to-end pipeline applications with whole images.
Authors: Jos\'e Rodr\'iguez-Ortega (Nemotec, Madrid, Spain, Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain), Francisco P\'erez-Hern\'andez (Nemotec, Madrid, Spain), Siham Tabik (Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain)
Abstract: Identifying anatomical landmarks in 3D dental models is vital for orthodontic treatment, yet manual placement is complex and time-consuming. Although some machine learning approaches have been proposed for automatic tooth landmark detection in 3D Intraoral Scans (IOS), none provide a fully end-to-end solution that bypasses teeth segmentation, limiting practical applicability. We introduce CHaRNet (Conditioned Heatmap Regression Network), the first fully end-to-end deep learning framework for tooth landmark detection in 3D IOS. Unlike traditional two-stage workflows that segment teeth before detecting landmarks, CHaRNet directly operates on the input point cloud, thus reducing complexity and computational overhead. Our method integrates four modules: (1) a point cloud encoder, (2) a point cloud decoder with a heatmap regression head, (3) a teeth presence classification head, and (4) the novel Conditioned Heatmap Regression (CHaR) module. By leveraging teeth presence classification, the CHaR module dynamically adapts to missing teeth and enhances detection accuracy in complex dental models. We evaluate CHaRNet using five point cloud learning algorithms on a clinical dataset of 1,214 annotated 3D models. Both the dataset and code will be publicly released to address the lack of open datasets in orthodontics and inspire further research. CHaRNet achieves a Mean Euclidean Distance Error (MEDE) of 0.51 mm on typical dental models and 1.28 mm across all dentition types, with corresponding Mean Success Rates (MSR) of 87.06% and 82.40%, respectively. Notably, it exhibits robust performance on irregular geometries, including models with missing teeth. This end-to-end approach streamlines orthodontic workflows, enhances 3D IOS analysis precision, and supports efficient computer-assisted treatment planning.
Authors: Yongxiang Liu, Weijie Li, Li Liu, Jie Zhou, Xuying Xiong, Bowen Peng, Yafei Song, Wei Yang, Tianpeng Liu, Zhen Liu, Xiang Li
Abstract: As an indispensable sensor for Remote sensing, Synthetic Aperture Radar (SAR) has a unique capability for all-day imaging. Nevertheless, in a data-driven era, the scarcity of large-scale datasets poses a significant bottleneck to advancing SAR automatic target recognition (ATR) technology. This paper introduces NUDT4MSTAR, a large-scale SAR dataset for remote sensing target recognition in the wild, including 40 vehicle target types and various imaging conditions across 5 realistic scenes. NUDT4MSTAR represents a significant leap forward in dataset scale, containing over 190,000 images-tenfold the size of its predecessors. We meticulously annotate each image with detailed target information and imaging conditions. Besides, data in both processed magnitude images and original complex formats are provided. Then, we construct a comprehensive benchmark consisting of 7 experiments with 15 recognition methods focusing on the stable and effective ATR issues. Besides, we conduct transfer learning experiments utilizing various models training on NUDT4MSTAR and apply them to three other target datasets, demonstrating its substantial potential for the broader field of ground objects ATR. Finally, we discuss this dataset's application value and ATR's significant challenges. To the best of our knowledge, this work marks the first-ever endeavor to create a large-scale dataset benchmark for fine-grained SAR recognition in the wild, featuring an extensive collection of exhaustively annotated vehicle images. We expect that the open source of NUDT4MSTAR will facilitate the development of SAR ATR and attract a wider community of researchers.
Authors: Rui Li, Xiaohan Wang, Yuhui Zhang, Zeyu Wang, Serena Yeung-Levy
Abstract: Despite significant advancements in video large multimodal models (video-LMMs), achieving effective temporal grounding in long-form videos remains a challenge for existing models. To address this limitation, we propose Temporal Preference Optimization (TPO), a novel post-training framework designed to enhance the temporal grounding capabilities of video-LMMs through preference learning. TPO adopts a self-training approach that enables models to differentiate between well-grounded and less accurate temporal responses by leveraging curated preference datasets at two granularities: localized temporal grounding, which focuses on specific video segments, and comprehensive temporal grounding, which captures extended temporal dependencies across entire video sequences. By optimizing on these preference datasets, TPO significantly enhances temporal understanding while reducing reliance on manually annotated data. Extensive experiments on three long-form video understanding benchmarks--LongVideoBench, MLVU, and Video-MME--demonstrate the effectiveness of TPO across two state-of-the-art video-LMMs. Notably, LLaVA-Video-TPO establishes itself as the leading 7B model on the Video-MME benchmark, underscoring the potential of TPO as a scalable and efficient solution for advancing temporal reasoning in long-form video understanding. Project page: https://ruili33.github.io/tpo_website.
Authors: Lin Duan, Yanming Xiu, Maria Gorlatova
Abstract: Augmented Reality (AR) enhances the real world by integrating virtual content, yet ensuring the quality, usability, and safety of AR experiences presents significant challenges. Could Vision-Language Models (VLMs) offer a solution for the automated evaluation of AR-generated scenes? Could Vision-Language Models (VLMs) offer a solution for the automated evaluation of AR-generated scenes? In this study, we evaluate the capabilities of three state-of-the-art commercial VLMs -- GPT, Gemini, and Claude -- in identifying and describing AR scenes. For this purpose, we use DiverseAR, the first AR dataset specifically designed to assess VLMs' ability to analyze virtual content across a wide range of AR scene complexities. Our findings demonstrate that VLMs are generally capable of perceiving and describing AR scenes, achieving a True Positive Rate (TPR) of up to 93% for perception and 71% for description. While they excel at identifying obvious virtual objects, such as a glowing apple, they struggle when faced with seamlessly integrated content, such as a virtual pot with realistic shadows. Our results highlight both the strengths and the limitations of VLMs in understanding AR scenarios. We identify key factors affecting VLM performance, including virtual content placement, rendering quality, and physical plausibility. This study underscores the potential of VLMs as tools for evaluating the quality of AR experiences.
Authors: Guoxi Huang, Nantheera Anantrasirichai, Fei Ye, Zipeng Qi, RuiRui Lin, Qirui Yang, David Bull
Abstract: In image enhancement tasks, such as low-light and underwater image enhancement, a degraded image can correspond to multiple plausible target images due to dynamic photography conditions, such as variations in illumination. This naturally results in a one-to-many mapping challenge. To address this, we propose a Bayesian Enhancement Model (BEM) that incorporates Bayesian Neural Networks (BNNs) to capture data uncertainty and produce diverse outputs. To achieve real-time inference, we introduce a two-stage approach: Stage I employs a BNN to model the one-to-many mappings in the low-dimensional space, while Stage II refines fine-grained image details using a Deterministic Neural Network (DNN). To accelerate BNN training and convergence, we introduce a dynamic Momentum Prior. Extensive experiments on multiple low-light and underwater image enhancement benchmarks demonstrate the superiority of our method over deterministic models.
Authors: Daniel Panangian, Ksenia Bittner
Abstract: Publicly available satellite imagery, such as Sentinel- 2, often lacks the spatial resolution required for accurate analysis of remote sensing tasks including urban planning and disaster response. Current super-resolution techniques are typically trained on limited datasets, leading to poor generalization across diverse geographic regions. In this work, we propose a novel super-resolution framework that enhances generalization by incorporating geographic context through location embeddings. Our framework employs Generative Adversarial Networks (GANs) and incorporates techniques from diffusion models to enhance image quality. Furthermore, we address tiling artifacts by integrating information from neighboring images, enabling the generation of seamless, high-resolution outputs. We demonstrate the effectiveness of our method on the building segmentation task, showing significant improvements over state-of-the-art methods and highlighting its potential for real-world applications.
Authors: Seyyed Taghi Ataei, Parviz Mohammad Zadeh, Saeid Ataei
Abstract: This study addresses the urgent need for efficient and accurate damage detection in wind turbine structures, a crucial component of renewable energy infrastructure. Traditional inspection methods, such as manual assessments and non-destructive testing (NDT), are often costly, time-consuming, and prone to human error. To tackle these challenges, this research investigates advanced deep learning algorithms for vision-based structural health monitoring (SHM). A dataset of wind turbine surface images, featuring various damage types and pollution, was prepared and augmented for enhanced model training. Three algorithms-YOLOv7, its lightweight variant, and Faster R-CNN- were employed to detect and classify surface damage. The models were trained and evaluated on a dataset split into training, testing, and evaluation subsets (80%-10%-10%). Results indicate that YOLOv7 outperformed the others, achieving 82.4% mAP@50 and high processing speed, making it suitable for real-time inspections. By optimizing hyperparameters like learning rate and batch size, the models' accuracy and efficiency improved further. YOLOv7 demonstrated significant advancements in detection precision and execution speed, especially for real-time applications. However, challenges such as dataset limitations and environmental variability were noted, suggesting future work on segmentation methods and larger datasets. This research underscores the potential of vision-based deep learning techniques to transform SHM practices by reducing costs, enhancing safety, and improving reliability, thus contributing to the sustainable maintenance of critical infrastructure and supporting the longevity of wind energy systems.
Authors: Alicia Allmendinger, Ahmet O\u{g}uz Salt{\i}k, Gerassimos G. Peteinatos, Anthony Stein, Roland Gerhards
Abstract: Spot spraying represents an efficient and sustainable method for reducing the amount of pesticides, particularly herbicides, used in agricultural fields. To achieve this, it is of utmost importance to reliably differentiate between crops and weeds, and even between individual weed species in situ and under real-time conditions. To assess suitability for real-time application, different object detection models that are currently state-of-the-art are compared. All available models of YOLOv8, YOLOv9, YOLOv10, and RT-DETR are trained and evaluated with images from a real field situation. The images are separated into two distinct datasets: In the initial data set, each species of plants is trained individually; in the subsequent dataset, a distinction is made between monocotyledonous weeds, dicotyledonous weeds, and three chosen crops. The results demonstrate that while all models perform equally well in the metrics evaluated, the YOLOv9 models, particularly the YOLOv9s and YOLOv9e, stand out in terms of their strong recall scores (66.58 % and 72.36 %), as well as mAP50 (73.52 % and 79.86 %), and mAP50-95 (43.82 % and 47.00 %) in dataset 2. However, the RT-DETR models, especially RT-DETR-l, excel in precision with reaching 82.44 \% on dataset 1 and 81.46 % in dataset 2, making them particularly suitable for scenarios where minimizing false positives is critical. In particular, the smallest variants of the YOLO models (YOLOv8n, YOLOv9t, and YOLOv10n) achieve substantially faster inference times down to 7.58 ms for dataset 2 on the NVIDIA GeForce RTX 4090 GPU for analyzing one frame, while maintaining competitive accuracy, highlighting their potential for deployment in resource-constrained embedded computing devices as typically used in productive setups.
Authors: Akshay Modi, Ashhar Aziz, Nilanjana Chatterjee, A V Subramanyam
Abstract: Large vision-language models have revolutionized cross-modal object retrieval, but text-based person search (TBPS) remains a challenging task due to limited data and fine-grained nature of the task. Existing methods primarily focus on aligning image-text pairs into a common representation space, often disregarding the fact that real world positive image-text pairs share a varied degree of similarity in between them. This leads models to prioritize easy pairs, and in some recent approaches, challenging samples are discarded as noise during training. In this work, we introduce a boosting technique that dynamically identifies and emphasizes these challenging samples during training. Our approach is motivated from classical boosting technique and dynamically updates the weights of the weak positives, wherein, the rank-1 match does not share the identity of the query. The weight allows these misranked pairs to contribute more towards the loss and the network has to pay more attention towards such samples. Our method achieves improved performance across four pedestrian datasets, demonstrating the effectiveness of our proposed module.
Authors: Behraj Khan, Tahir Syed
Abstract: Confidence calibration is an emerging challenge in real-world decision systems based on foundations models when used for downstream vision classification tasks. Due to various reasons exposed, logit scores on the CLIP head remain large irrespective of whether the image-language pairs reconcile. It is difficult to address in data space, given the few-shot regime. We propose a penalty incorporated into loss objective that penalizes incorrect classifications whenever one is made during finetuning, by moving an amount of log-likelihood to the true class commensurate to the relative amplitudes of the two likelihoods. We refer to it as \textit{confidence misalignment penalty (CMP)}. Extensive experiments on $12$ vision datasets and $5$ domain generalization datasets supports the calibration performance of our method against stat-of-the-art. CMP outperforms the benchmarked prompt learning methods, demonstrating average improvement in Expected Calibration Error (ECE) by average $6.01$\%, $4.01$ \% at minimum and $9.72$\% at maximum.
Authors: Jingcheng Ni, Weiguang Zhao, Daniel Wang, Ziyao Zeng, Chenyu You, Alex Wong, Kaizhu Huang
Abstract: Object removal is of great significance to 3D scene understanding, essential for applications in content filtering and scene editing. Current mainstream methods primarily focus on removing individual objects, with a few methods dedicated to eliminating an entire area or all objects of a certain category. They however confront the challenge of insufficient granularity and flexibility for real-world applications, where users demand tailored excision and preservation of objects within defined zones. In addition, most of the current methods require kinds of priors when addressing multi-view inpainting, which is time-consuming. To address these limitations, we propose an efficient and user-friendly pipeline for 3D multi-object removal, enabling users to flexibly select areas and define objects for removal or preservation. Concretely, to ensure object consistency and correspondence across multiple views, we propose a novel mask matching and refinement module, which integrates homography-based warping with high-confidence anchor points for segmentation. By leveraging the IoU joint shape context distance loss, we enhance the accuracy of warped masks and improve subsequent inpainting processes. Considering the current immaturity of 3D multi-object removal, we provide a new evaluation dataset to bridge the developmental void. Experimental results demonstrate that our method significantly reduces computational costs, achieving processing speeds more than 80% faster than state-of-the-art methods while maintaining equivalent or higher reconstruction quality.
Authors: Weiwei Yao, Chen Li, Minjun Xiong, Wenbo Dong, Hao Chen, Xiong Xiao
Abstract: This paper presents Contourformer, a real-time contour-based instance segmentation algorithm. The method is fully based on the DETR paradigm and achieves end-to-end inference through iterative and progressive mechanisms to optimize contours. To improve efficiency and accuracy, we develop two novel techniques: sub-contour decoupling mechanisms and contour fine-grained distribution refinement. In the sub-contour decoupling mechanism, we propose a deformable attention-based module that adaptively selects sampling regions based on the current predicted contour, enabling more effective capturing of object boundary information. Additionally, we design a multi-stage optimization process to enhance segmentation precision by progressively refining sub-contours. The contour fine-grained distribution refinement technique aims to further improve the ability to express fine details of contours. These innovations enable Contourformer to achieve stable and precise segmentation for each instance while maintaining real-time performance. Extensive experiments demonstrate the superior performance of Contourformer on multiple benchmark datasets, including SBD, COCO, and KINS. We conduct comprehensive evaluations and comparisons with existing state-of-the-art methods, showing significant improvements in both accuracy and inference speed. This work provides a new solution for contour-based instance segmentation tasks and lays a foundation for future research, with the potential to become a strong baseline method in this field.
Authors: Aneesh Rangnekar, Nishant Nadkarni, Jue Jiang, Harini Veeraraghavan
Abstract: Medical image foundation models have shown the ability to segment organs and tumors with minimal fine-tuning. These models are typically evaluated on task-specific in-distribution (ID) datasets. However, reliable performance on ID datasets does not guarantee robust generalization on out-of-distribution (OOD) datasets. Importantly, once deployed for clinical use, it is impractical to have `ground truth' delineations to assess ongoing performance drifts, especially when images fall into the OOD category due to different imaging protocols. Hence, we introduced a comprehensive set of computationally fast metrics to evaluate the performance of multiple foundation models (Swin UNETR, SimMIM, iBOT, SMIT) trained with self-supervised learning (SSL). All models were fine-tuned on identical datasets for lung tumor segmentation from computed tomography (CT) scans. The evaluation was performed on two public lung cancer datasets (LRAD: n = 140, 5Rater: n = 21) with different image acquisitions and tumor stages compared to training data (n = 317 public resource with stage III-IV lung cancers) and a public non-cancer dataset containing volumetric CT scans of patients with pulmonary embolism (n = 120). All models produced similarly accurate tumor segmentation on the lung cancer testing datasets. SMIT produced the highest F1-score (LRAD: 0.60, 5Rater: 0.64) and lowest entropy (LRAD: 0.06, 5Rater: 0.12), indicating higher tumor detection rate and confident segmentations. In the OOD dataset, SMIT misdetected the least number of tumors, marked by a median volume occupancy of 5.67 cc compared to the best method SimMIM of 9.97 cc. Our analysis shows that additional metrics such as entropy and volume occupancy may help better understand model performance on mixed domain datasets.
Authors: Yiping Ji, Hemanth Saratchandran, Cameron Gordon, Zeyu Zhang, Simon Lucey
Abstract: Low-rank decomposition has emerged as a vital tool for enhancing parameter efficiency in neural network architectures, gaining traction across diverse applications in machine learning. These techniques significantly lower the number of parameters, striking a balance between compactness and performance. However, a common challenge has been the compromise between parameter efficiency and the accuracy of the model, where reduced parameters often lead to diminished accuracy compared to their full-rank counterparts. In this work, we propose a novel theoretical framework that integrates a sinusoidal function within the low-rank decomposition process. This approach not only preserves the benefits of the parameter efficiency characteristic of low-rank methods but also increases the decomposition's rank, thereby enhancing model performance. Our method proves to be a plug in enhancement for existing low-rank models, as evidenced by its successful application in Vision Transformers (ViT), Large Language Models (LLMs), Neural Radiance Fields (NeRF) and 3D shape modelling.
Authors: Chao Zhou, Huishuai Zhang, Jiang Bian, Weiming Zhang, Nenghai Yu
Abstract: This paper addresses the contentious issue of copyright infringement in images generated by text-to-image models, sparking debates among AI developers, content creators, and legal entities. State-of-the-art models create high-quality content without crediting original creators, causing concern in the artistic community. To mitigate this, we propose the \copyright Plug-in Authorization framework, introducing three operations: addition, extraction, and combination. Addition involves training a \copyright plug-in for specific copyright, facilitating proper credit attribution. Extraction allows creators to reclaim copyright from infringing models, and combination enables users to merge different \copyright plug-ins. These operations act as permits, incentivizing fair use and providing flexibility in authorization. We present innovative approaches,"Reverse LoRA" for extraction and "EasyMerge" for seamless combination. Experiments in artist-style replication and cartoon IP recreation demonstrate \copyright plug-ins' effectiveness, offering a valuable solution for human copyright protection in the age of generative AIs. The code is available at https://github.com/zc1023/-Plug-in-Authorization.git.
Authors: Abhishek Jha, Yogesh Rawat, Shruti Vyas
Abstract: Photovoltaic (PV) systems allow us to tap into all abundant solar energy, however they require regular maintenance for high efficiency and to prevent degradation. Traditional manual health check, using Electroluminescence (EL) imaging, is expensive and logistically challenging which makes automated defect detection essential. Current automation approaches require extensive manual expert labeling, which is time-consuming, expensive, and prone to errors. We propose PV-S3 (Photovoltaic-Semi Supervised Segmentation), a Semi-Supervised Learning approach for semantic segmentation of defects in EL images that reduces reliance on extensive labeling. PV-S3 is a Deep learning model trained using a few labeled images along with numerous unlabeled images. We introduce a novel Semi Cross-Entropy loss function to deal with class imbalance. We evaluate PV-S3 on multiple datasets and demonstrate its effectiveness and adaptability. With merely 20% labeled samples, we achieve an absolute improvement of 9.7% in IoU, 13.5% in Precision, 29.15% in Recall, and 20.42% in F1-Score over prior state-of-the-art supervised method (which uses 100% labeled samples) on UCF-EL dataset (largest dataset available for semantic segmentation of EL images) showing improvement in performance while reducing the annotation costs by 80%. For more details, visit our GitHub repository:https://github.com/abj247/PV-S3.
Authors: Jorge Tapias Gomez, Aneesh Rangnekar, Hannah Williams, Hannah Thompson, Julio Garcia-Aguilar, Joshua Jesse Smith, Harini Veeraraghavan
Abstract: Endoscopic images are used at various stages of rectal cancer treatment starting from cancer screening, diagnosis, during treatment to assess response and toxicity from treatments such as colitis, and at follow up to detect new tumor or local regrowth (LR). However, subjective assessment is highly variable and can underestimate the degree of response in some patients, subjecting them to unnecessary surgery, or overestimate response that places patients at risk of disease spread. Advances in deep learning has shown the ability to produce consistent and objective response assessment for endoscopic images. However, methods for detecting cancers, regrowth, and monitoring response during the entire course of patient treatment and follow-up are lacking. This is because, automated diagnosis and rectal cancer response assessment requires methods that are robust to inherent imaging illumination variations and confounding conditions (blood, scope, blurring) present in endoscopy images as well as changes to the normal lumen and tumor during treatment. Hence, a hierarchical shifted window (Swin) transformer was trained to distinguish rectal cancer from normal lumen using endoscopy images. Swin as well as two convolutional (ResNet-50, WideResNet-50), and vision transformer (ViT) models were trained and evaluated on follow-up longitudinal images to detect LR on private dataset as well as on out-of-distribution (OOD) public colonoscopy datasets to detect pre/non-cancerous polyps. Color shifts were applied using optimal transport to simulate distribution shifts. Swin and ResNet models were similarly accurate in the in-distribution dataset. Swin was more accurate than other methods (follow-up: 0.84, OOD: 0.83) even when subject to color shifts (follow-up: 0.83, OOD: 0.87), indicating capability to provide robust performance for longitudinal cancer assessment.
Authors: Xiang Li, Cristina Mata, Jongwoo Park, Kumara Kahatapitiya, Yoo Sung Jang, Jinghuan Shang, Kanchana Ranasinghe, Ryan Burgert, Mu Cai, Yong Jae Lee, Michael S. Ryoo
Abstract: Vision Language Models (VLMs) have recently been leveraged to generate robotic actions, forming Vision-Language-Action (VLA) models. However, directly adapting a pretrained VLM for robotic control remains challenging, particularly when constrained by a limited number of robot demonstrations. In this work, we introduce LLaRA: Large Language and Robotics Assistant, a framework that formulates robot action policy as visuo-textual conversations and enables an efficient transfer of a pretrained VLM into a powerful VLA, motivated by the success of visual instruction tuning in Computer Vision. First, we present an automated pipeline to generate conversation-style instruction tuning data for robots from existing behavior cloning datasets, aligning robotic actions with image pixel coordinates. Further, we enhance this dataset in a self-supervised manner by defining six auxiliary tasks, without requiring any additional action annotations. We show that a VLM finetuned with a limited amount of such datasets can produce meaningful action decisions for robotic control. Through experiments across multiple simulated and real-world tasks, we demonstrate that LLaRA achieves state-of-the-art performance while preserving the generalization capabilities of large language models. The code, datasets, and pretrained models are available at https://github.com/LostXine/LLaRA.
Authors: Qi Huang, Emanuele Mezzi, Osman Mutlu, Miltiadis Kofinas, Vidya Prasad, Shadnan Azwad Khan, Elena Ranguelova, Niki van Stein
Abstract: We introduce a novel metric for measuring semantic continuity in Explainable AI methods and machine learning models. We posit that for models to be truly interpretable and trustworthy, similar inputs should yield similar explanations, reflecting a consistent semantic understanding. By leveraging XAI techniques, we assess semantic continuity in the task of image recognition. We conduct experiments to observe how incremental changes in input affect the explanations provided by different XAI methods. Through this approach, we aim to evaluate the models' capability to generalize and abstract semantic concepts accurately and to evaluate different XAI methods in correctly capturing the model behaviour. This paper contributes to the broader discourse on AI interpretability by proposing a quantitative measure for semantic continuity for XAI methods, offering insights into the models' and explainers' internal reasoning processes, and promoting more reliable and transparent AI systems.
Authors: J Shepard Bryan IV, Pedro Pessoa, Meyam Tavakoli, Steve Presse
Abstract: Deep learning based approaches are now widely used across biophysics to help automate a variety of tasks including image segmentation, feature selection, and deconvolution. However, the presence of multiple competing deep learning architectures, each with its own unique advantages and disadvantages, makes it challenging to select an architecture best suited for a specific application. As such, we present a comprehensive comparison of common models. Here, we focus on the task of segmentation assuming the typically small training dataset sizes available from biophysics experiments and compare the following four commonly used architectures: convolutional neural networks, U-Nets, vision transformers, and vision state space models. In doing so, we establish criteria for determining optimal conditions under which each model excels, thereby offering practical guidelines for researchers and practitioners in the field.
Authors: Chengen Wang, Murat Kantarcioglu
Abstract: Consistency models are a new class of models that generate images by directly mapping noise to data, allowing for one-step generation and significantly accelerating the sampling process. However, their robustness against adversarial attacks has not yet been thoroughly investigated. In this work, we conduct the first study on the vulnerability of consistency models to backdoor attacks. While previous research has explored backdoor attacks on diffusion models, those studies have primarily focused on conventional diffusion models, employing a customized backdoor training process and objective, whereas consistency models have distinct training processes and objectives. Our proposed framework demonstrates the vulnerability of consistency models to backdoor attacks. During image generation, poisoned consistency models produce images with a Fr\'echet Inception Distance (FID) comparable to that of a clean model when sampling from Gaussian noise. However, once the trigger is activated, they generate backdoor target images. We explore various trigger and target configurations to evaluate the vulnerability of consistency models, including the use of random noise as a trigger. This novel trigger is visually inconspicuous, more challenging to detect, and aligns well with the sampling process of consistency models. Across all configurations, our framework successfully compromises the consistency models while maintaining high utility and specificity. We also examine the stealthiness of our proposed attack, which is attributed to the unique properties of consistency models and the elusive nature of the Gaussian noise trigger.
Authors: Patrick Styll, Dowon Kim, Jiook Cha
Abstract: Brain development in the first few months of human life is a critical phase characterized by rapid structural growth and functional organization. Accurately predicting developmental outcomes during this time is crucial for identifying delays and enabling timely interventions. This study introduces the SwiFT (Swin 4D fMRI Transformer) model, designed to predict Bayley-III composite scores using neonatal fMRI from the Developing Human Connectome Project (dHCP). To enhance predictive accuracy, we apply dimensionality reduction via group independent component analysis (ICA) and pretrain SwiFT on large adult fMRI datasets to address the challenges of limited neonatal data. Our analysis shows that SwiFT significantly outperforms baseline models in predicting cognitive, motor, and language outcomes, leveraging both single-label and multi-label prediction strategies. The model's attention-based architecture processes spatiotemporal data end-to-end, delivering superior predictive performance. Additionally, we use Integrated Gradients with Smoothgrad sQuare (IG-SQ) to interpret predictions, identifying neural spatial representations linked to early cognitive and behavioral development. These findings underscore the potential of Transformer models to advance neurodevelopmental research and clinical practice.
Authors: Weijia Shi, Xiaochuang Han, Chunting Zhou, Weixin Liang, Xi Victoria Lin, Luke Zettlemoyer, Lili Yu
Abstract: We present LMFusion, a framework for empowering pretrained text-only large language models (LLMs) with multimodal generative capabilities, enabling them to understand and generate both text and images in arbitrary sequences. LMFusion leverages existing Llama-3's weights for processing texts autoregressively while introducing additional and parallel transformer modules for processing images with diffusion. During training, the data from each modality is routed to its dedicated modules: modality-specific feedforward layers, query-key-value projections, and normalization layers process each modality independently, while the shared self-attention layers allow interactions across text and image features. By freezing the text-specific modules and only training the image-specific modules, LMFusion preserves the language capabilities of text-only LLMs while developing strong visual understanding and generation abilities. Compared to methods that pretrain multimodal generative models from scratch, our experiments demonstrate that, LMFusion improves image understanding by 20% and image generation by 3.6% using only 50% of the FLOPs while maintaining Llama-3's language capabilities. We also demonstrate that this framework can adapt existing vision-language models with multimodal generation ability. Overall, this framework not only leverages existing computational investments in text-only LLMs but also enables the parallel development of language and vision capabilities, presenting a promising direction for efficient multimodal model development.
Authors: Haichao Zhang, Haonan Yu, Le Zhao, Andrew Choi, Qinxun Bai, Break Yang, Wei Xu
Abstract: We present a low-cost legged mobile manipulation system that solves long-horizon real-world tasks, trained by reinforcement learning purely in simulation. This system is made possible by 1) a hierarchical design of a high-level policy for visual-mobile manipulation following task instructions, and a low-level quadruped locomotion policy, 2) a teacher and student training pipeline for the high level, which trains a teacher to tackle long-horizon tasks using privileged task decomposition and target object information, and further trains a student for visual-mobile manipulation via RL guided by the teacher's behavior, and 3) a suite of techniques for minimizing the sim-to-real gap. In contrast to many previous works that use high-end equipments, our system demonstrates effective performance with more accessible hardware -- specifically, a Unitree Go1 quadruped, a WidowX-250S arm, and a single wrist-mounted RGB camera -- despite the increased challenges of sim-to-real transfer. Trained fully in simulation, a single policy autonomously solves long-horizon tasks involving search, move to, grasp, transport, and drop into, achieving nearly 80% real-world success. This performance is comparable to that of expert human teleoperation on the same tasks while the robot is more efficient, operating at about 1.5x the speed of the teleoperation. Finally, we perform extensive ablations on key techniques for efficient RL training and effective sim-to-real transfer, and demonstrate effective deployment across diverse indoor and outdoor scenes under various lighting conditions.
Authors: Mohamed Elfeki, Rui Liu, Chad Voegele
Abstract: The dominance of large decoder-only language models has overshadowed encoder-decoder architectures, despite their fundamental efficiency advantages in sequence processing. For small language models (SLMs) - those with 1 billion parameters or fewer - our systematic analysis across GPU, CPU, and NPU platforms reveals that encoder-decoder architectures achieve 47% lower first-token latency and 4.7x higher throughput compared to decoder-only models on edge devices. These gains may be attributed to encoder-decoder's one-time input processing and efficient separation of understanding and generation phases. We introduce a novel knowledge distillation framework that enables encoder-decoder models to leverage capabilities from large scalable decoder-only teachers while preserving their architectural advantages, achieving up to 6 average performance points improvement across diverse tasks, with significant gains in asymmetric sequence tasks where input and output distributions can benefit from different processing approaches. When combined with modern advances like Rotary Positional Embeddings (RoPE) and Vision encoders, our systematic investigation demonstrates that encoder-decoder architectures provide a more practical path toward deploying capable language models in resource-constrained environments. Our findings challenge the prevailing trend toward decoder-only scaling, showing that architectural choices become increasingly crucial as parameter budgets decrease, particularly for on-device and edge deployments where computational efficiency is paramount.
Authors: Yihua Shao, Minxi Yan, Yang Liu, Siyu Chen, Wenjie Chen, Xinwei Long, Ziyang Yan, Lei Li, Chenyu Zhang, Nicu Sebe, Hao Tang, Yan Wang, Hao Zhao, Mengzhu Wang, Jingcai Guo
Abstract: Low-rank Adaptation (LoRA) has demonstrated remarkable capabilities for task specific fine-tuning. However, in scenarios that involve multiple tasks, training a separate LoRA model for each one results in considerable inefficiency in terms of storage and inference. Moreover, existing parameter generation methods fail to capture the correlations among these tasks, making multi-task LoRA parameter generation challenging. To address these limitations, we propose In-Context Meta LoRA (ICM-LoRA), a novel approach that efficiently achieves task-specific customization of large language models (LLMs). Specifically, we use training data from all tasks to train a tailored generator, Conditional Variational Autoencoder (CVAE). CVAE takes task descriptions as inputs and produces task-aware LoRA weights as outputs. These LoRA weights are then merged with LLMs to create task-specialized models without the need for additional fine-tuning. Furthermore, we utilize in-context meta-learning for knowledge enhancement and task mapping, to capture the relationship between tasks and parameter distributions. As a result, our method achieves more accurate LoRA parameter generation for diverse tasks using CVAE. ICM-LoRA enables more accurate LoRA parameter reconstruction than current parameter reconstruction methods and is useful for implementing task-specific enhancements of LoRA parameters. At the same time, our method occupies 283MB, only 1\% storage compared with the original LoRA.