Authors: Saurav Sagar, Mohammed Javed, David S Doermann
Abstract: The agricultural sector plays an essential role in the economic growth of a country. Specifically, in an Indian context, it is the critical source of livelihood for millions of people living in rural areas. Plant Disease is one of the significant factors affecting the agricultural sector. Plants get infected with diseases for various reasons, including synthetic fertilizers, archaic practices, environmental conditions, etc., which impact the farm yield and subsequently hinder the economy. To address this issue, researchers have explored many applications based on AI and Machine Learning techniques to detect plant diseases. This research survey provides a comprehensive understanding of common plant leaf diseases, evaluates traditional and deep learning techniques for disease detection, and summarizes available datasets. It also explores Explainable AI (XAI) to enhance the interpretability of deep learning models' decisions for end-users. By consolidating this knowledge, the survey offers valuable insights to researchers, practitioners, and stakeholders in the agricultural sector, fostering the development of efficient and transparent solutions for combating plant diseases and promoting sustainable agricultural practices.
Authors: Ethan Kane Waters, Carla Chia-Ming Chen, Mostafa Rahimi Azghadi
Abstract: Research into large-scale crop monitoring has flourished due to increased accessibility to satellite imagery. This review delves into previously unexplored and under-explored areas in sugarcane health monitoring and disease/pest detection using satellite-based spectroscopy and Machine Learning (ML). It discusses key considerations in system development, including relevant satellites, vegetation indices, ML methods, factors influencing sugarcane reflectance, optimal growth conditions, common diseases, and traditional detection methods. Many studies highlight how factors like crop age, soil type, viewing angle, water content, recent weather patterns, and sugarcane variety can impact spectral reflectance, affecting the accuracy of health assessments via spectroscopy. However, these variables have not been fully considered in the literature. In addition, the current literature lacks comprehensive comparisons between ML techniques and vegetation indices. We address these gaps in this review. We discuss that, while current findings suggest the potential for an ML-driven satellite spectroscopy system for monitoring sugarcane health, further research is essential. This paper offers a comprehensive analysis of previous research to aid in unlocking this potential and advancing the development of an effective sugarcane health monitoring system using satellite technology.
Authors: Chen Dudai, Morris Alper, Hana Bezalel, Rana Hanocka, Itai Lang, Hadar Averbuch-Elor
Abstract: Internet image collections containing photos captured by crowds of photographers show promise for enabling digital exploration of large-scale tourist landmarks. However, prior works focus primarily on geometric reconstruction and visualization, neglecting the key role of language in providing a semantic interface for navigation and fine-grained understanding. In constrained 3D domains, recent methods have leveraged vision-and-language models as a strong prior of 2D visual semantics. While these models display an excellent understanding of broad visual semantics, they struggle with unconstrained photo collections depicting such tourist landmarks, as they lack expert knowledge of the architectural domain. In this work, we present a localization system that connects neural representations of scenes depicting large-scale landmarks with text describing a semantic region within the scene, by harnessing the power of SOTA vision-and-language models with adaptations for understanding landmark scene semantics. To bolster such models with fine-grained knowledge, we leverage large-scale Internet data containing images of similar landmarks along with weakly-related textual information. Our approach is built upon the premise that images physically grounded in space can provide a powerful supervision signal for localizing new concepts, whose semantics may be unlocked from Internet textual metadata with large language models. We use correspondences between views of scenes to bootstrap spatial understanding of these semantics, providing guidance for 3D-compatible segmentation that ultimately lifts to a volumetric scene representation. Our results show that HaLo-NeRF can accurately localize a variety of semantic concepts related to architectural landmarks, surpassing the results of other 3D models as well as strong 2D segmentation baselines. Our project page is at https://tau-vailab.github.io/HaLo-NeRF/.
Authors: Peter Myung-Won Pak, Francis Ogoke, Andrew Polonsky, Anthony Garland, Dan S. Bolintineanu, Dan R. Moser, Michael J. Heiden, Amir Barati Farimani
Abstract: We present a deep learning approach for quantifying and localizing ex-situ porosity within Laser Powder Bed Fusion fabricated samples utilizing in-situ thermal image monitoring data. Our goal is to build the real time porosity map of parts based on thermal images acquired during the build. The quantification task builds upon the established Convolutional Neural Network model architecture to predict pore count and the localization task leverages the spatial and temporal attention mechanisms of the novel Video Vision Transformer model to indicate areas of expected porosity. Our model for porosity quantification achieved a $R^2$ score of 0.57 and our model for porosity localization produced an average IoU score of 0.32 and a maximum of 1.0. This work is setting the foundations of part porosity "Digital Twins" based on additive manufacturing monitoring data and can be applied downstream to reduce time-intensive post-inspection and testing activities during part qualification and certification. In addition, we seek to accelerate the acquisition of crucial insights normally only available through ex-situ part evaluation by means of machine learning analysis of in-situ process monitoring data.
Authors: Rayner Kay Jin Tan, Dilruk Perera, Salomi Arasaratnam, Yudara Kularathne
Abstract: Artificial Intelligence applications have shown promise in the management of pandemics and have been widely used to assist the identification, classification, and diagnosis of medical images. In response to the global outbreak of Monkeypox (Mpox), the HeHealth.ai team leveraged an existing tool to screen for sexually transmitted diseases to develop a digital screening test for symptomatic Mpox through AI approaches. Prior to the global outbreak of Mpox, the team developed a smartphone app, where app users can use their own smartphone cameras to take pictures of their own penises to screen for symptomatic STD. The AI model was initially developed using 5000 cases and use a modified convolutional neural network to output prediction scores across visually diagnosable penis pathologies including Syphilis, Herpes Simplex Virus, and Human Papilloma Virus. From June 2022 to October 2022, a total of about 22,000 users downloaded the HeHealth app, and about 21,000 images have been analyzed using HeHealth AI technology. We then engaged in formative research, stakeholder engagement, rapid consolidation images, a validation study, and implementation of the tool from July 2022. From July 2022 to October 2022, a total of 1000 Mpox related images had been used to train the Mpox symptom checker tool. Our digital symptom checker tool showed accuracy of 87% to rule in Mpox and 90% to rule out symptomatic Mpox. Several hurdles identified included issues of data privacy and security for app users, initial lack of data to train the AI tool, and the potential generalizability of input data. We offer several suggestions to help others get started on similar projects in emergency situations, including engaging a wide range of stakeholders, having a multidisciplinary team, prioritizing pragmatism, as well as the concept that big data in fact is made up of small data.
Authors: Mehmet Kerem Turkcan, Sanjeev Narasimhan, Chengbo Zang, Gyung Hyun Je, Bo Yu, Mahshid Ghasemi, Javad Ghaderi, Gil Zussman, Zoran Kostic
Abstract: We introduce Constellation, a dataset of 13K images suitable for research on detection of objects in dense urban streetscapes observed from high-elevation cameras, collected for a variety of temporal conditions. The dataset addresses the need for curated data to explore problems in small object detection exemplified by the limited pixel footprint of pedestrians observed tens of meters from above. It enables the testing of object detection models for variations in lighting, building shadows, weather, and scene dynamics. We evaluate contemporary object detection architectures on the dataset, observing that state-of-the-art methods have lower performance in detecting small pedestrians compared to vehicles, corresponding to a 10% difference in average precision (AP). Using structurally similar datasets for pretraining the models results in an increase of 1.8% mean AP (mAP). We further find that incorporating domain-specific data augmentations helps improve model performance. Using pseudo-labeled data, obtained from inference outcomes of the best-performing models, improves the performance of the models. Finally, comparing the models trained using the data collected in two different time intervals, we find a performance drift in models due to the changes in intersection conditions over time. The best-performing model achieves a pedestrian AP of 92.0% with 11.5 ms inference time on NVIDIA A100 GPUs, and an mAP of 95.4%.
Authors: Samia Shafique, Shu Kong, Charless Fowlkes
Abstract: Shoeprints are a common type of evidence found at crime scenes and are used regularly in forensic investigations. However, existing methods cannot effectively employ deep learning techniques to match noisy and occluded crime-scene shoeprints to a shoe database due to a lack of training data. Moreover, all existing methods match crime-scene shoeprints to clean reference prints, yet our analysis shows matching to more informative tread depth maps yields better retrieval results. The matching task is further complicated by the necessity to identify similarities only in corresponding regions (heels, toes, etc) of prints and shoe treads. To overcome these challenges, we leverage shoe tread images from online retailers and utilize an off-the-shelf predictor to estimate depth maps and clean prints. Our method, named CriSp, matches crime-scene shoeprints to tread depth maps by training on this data. CriSp incorporates data augmentation to simulate crime-scene shoeprints, an encoder to learn spatially-aware features, and a masking module to ensure only visible regions of crime-scene prints affect retrieval results. To validate our approach, we introduce two validation sets by reprocessing existing datasets of crime-scene shoeprints and establish a benchmarking protocol for comparison. On this benchmark, CriSp significantly outperforms state-of-the-art methods in both automated shoeprint matching and image retrieval tailored to this task.
Authors: Lin Xu, Yilin Zhao, Daquan Zhou, Zhijie Lin, See Kiong Ng, Jiashi Feng
Abstract: Vision-language pre-training has significantly elevated performance across a wide range of image-language applications. Yet, the pre-training process for video-related tasks demands exceptionally large computational and data resources, which hinders the progress of video-language models. This paper investigates a straightforward, highly efficient, and resource-light approach to adapting an existing image-language pre-trained model for dense video understanding. Our preliminary experiments reveal that directly fine-tuning pre-trained image-language models with multiple frames as inputs on video datasets leads to performance saturation or even a drop. Our further investigation reveals that it is largely attributed to the bias of learned high-norm visual features. Motivated by this finding, we propose a simple but effective pooling strategy to smooth the feature distribution along the temporal dimension and thus reduce the dominant impacts from the extreme features. The new model is termed Pooling LLaVA, or \nameofmethod{} in short. \nameofmethod{} achieves new state-of-the-art performance on modern benchmark datasets for both video question-answer and captioning tasks. Notably, on the recent popular Video ChatGPT benchmark, PLLaVA achieves a score of 3.48 out of 5 on average of five evaluated dimensions, exceeding the previous SOTA results from GPT4V (IG-VLM) by 9\%. On the latest multi-choice benchmark MVBench, PLLaVA achieves 58.1\% accuracy on average across 20 sub-tasks, 14.5\% higher than GPT4V (IG-VLM). Code is available at \url{https://github.com/magic-research/PLLaVA}.
Authors: Vazgen Zohranyan, Vagner Navasardyan, Hayk Navasardyan, Jan Borggrefe, Shant Navasardyan
Abstract: Recent advancements in AI have significantly transformed medical imaging, particularly in angiography, by enhancing diagnostic precision and patient care. However existing works are limited in analyzing the aorta and iliac arteries, above all for vascular anomaly detection and characterization. To close this gap, we propose Dr-SAM, a comprehensive multi-stage framework for vessel segmentation, diameter estimation, and anomaly analysis aiming to examine the peripheral vessels through angiography images. For segmentation we introduce a customized positive/negative point selection mechanism applied on top of the Segment Anything Model (SAM), specifically for medical (Angiography) images. Then we propose a morphological approach to determine the vessel diameters followed by our histogram-driven anomaly detection approach. Moreover, we introduce a new benchmark dataset for the comprehensive analysis of peripheral vessel angiography images which we hope can boost the upcoming research in this direction leading to enhanced diagnostic precision and ultimately better health outcomes for individuals facing vascular issues.
Authors: Hao Wang, Jiayou Qin, Xiwen Chen, Ashish Bastola, John Suchanek, Zihao Gong, Abolfazl Razi
Abstract: Motion analysis plays a critical role in various applications, from virtual reality and augmented reality to assistive visual navigation. Traditional self-driving technologies, while advanced, typically do not translate directly to pedestrian applications due to their reliance on extensive sensor arrays and non-feasible computational frameworks. This highlights a significant gap in applying these solutions to human users since human navigation introduces unique challenges, including the unpredictable nature of human movement, limited processing capabilities of portable devices, and the need for directional responsiveness due to the limited perception range of humans. In this project, we introduce an image-only method that applies motion analysis using optical flow with ego-motion compensation to predict Motor Focus-where and how humans or machines focus their movement intentions. Meanwhile, this paper addresses the camera shaking issue in handheld and body-mounted devices which can severely degrade performance and accuracy, by applying a Gaussian aggregation to stabilize the predicted motor focus area and enhance the prediction accuracy of movement direction. This also provides a robust, real-time solution that adapts to the user's immediate environment. Furthermore, in the experiments part, we show the qualitative analysis of motor focus estimation between the conventional dense optical flow-based method and the proposed method. In quantitative tests, we show the performance of the proposed method on a collected small dataset that is specialized for motor focus estimation tasks.
Authors: Tanvi Deshpande, Eva Prakash, Elsie Gyang Ross, Curtis Langlotz, Andrew Ng, Jeya Maria Jose Valanarasu
Abstract: The high cost of creating pixel-by-pixel gold-standard labels, limited expert availability, and presence of diverse tasks make it challenging to generate segmentation labels to train deep learning models for medical imaging tasks. In this work, we present a new approach to overcome the hurdle of costly medical image labeling by leveraging foundation models like Segment Anything Model (SAM) and its medical alternate MedSAM. Our pipeline has the ability to generate weak labels for any unlabeled medical image and subsequently use it to augment label-scarce datasets. We perform this by leveraging a model trained on a few gold-standard labels and using it to intelligently prompt MedSAM for weak label generation. This automation eliminates the manual prompting step in MedSAM, creating a streamlined process for generating labels for both real and synthetic images, regardless of quantity. We conduct experiments on label-scarce settings for multiple tasks pertaining to modalities ranging from ultrasound, dermatology, and X-rays to demonstrate the usefulness of our pipeline. The code is available at https://github.com/stanfordmlgroup/Auto-Generate-WLs/.
URLs: https://github.com/stanfordmlgroup/Auto-Generate-WLs/.
Authors: Adith Jeyasangar, Abdullah Alsalemi, Shan E Ahmed Raza
Abstract: Whole Slide Images (WSIs) provide exceptional detail for studying tissue architecture at the cell level. To study tumour microenvironment (TME) with the context of various protein biomarkers and cell sub-types, analysis and registration of features using multi-stained WSIs is often required. Multi-stained WSI pairs normally suffer from rigid and non-rigid deformities in addition to slide artefacts and control tissue which present challenges at precise registration. Traditional registration methods mainly focus on global rigid/non-rigid registration but struggle with aligning slides with complex tissue deformations at the nuclei level. However, nuclei level non-rigid registration is essential for downstream tasks such as cell sub-type analysis in the context of protein biomarker signatures. This paper focuses on local level non-rigid registration using a nuclei-location based point set registration approach for aligning multi-stained WSIs. We exploit the spatial distribution of nuclei that is prominent and consistent (to a large level) across different stains to establish a spatial correspondence. We evaluate our approach using the HYRECO dataset consisting of 54 re-stained images of H\&E and PHH3 image pairs. The approach can be extended to other IHC and IF stained WSIs considering a good nuclei detection algorithm is accessible. The performance of the model is tested against established registration algorithms and is shown to outperform the model for nuclei level registration.
Authors: Weiran Chen, Qi Sun, Qi Xu
Abstract: Spiking Neural Networks (SNNs) aim to bridge the gap between neuroscience and machine learning by emulating the structure of the human nervous system. However, like convolutional neural networks, SNNs are vulnerable to adversarial attacks. To tackle the challenge, we propose a biologically inspired methodology to enhance the robustness of SNNs, drawing insights from the visual masking effect and filtering theory. First, an end-to-end SNN-based image purification model is proposed to defend against adversarial attacks, including a noise extraction network and a non-blind denoising network. The former network extracts noise features from noisy images, while the latter component employs a residual U-Net structure to reconstruct high-quality noisy images and generate clean images. Simultaneously, a multi-level firing SNN based on Squeeze-and-Excitation Network is introduced to improve the robustness of the classifier. Crucially, the proposed image purification network serves as a pre-processing module, avoiding modifications to classifiers. Unlike adversarial training, our method is highly flexible and can be seamlessly integrated with other defense strategies. Experimental results on various datasets demonstrate that the proposed methodology outperforms state-of-the-art baselines in terms of defense effectiveness, training time, and resource consumption.
Authors: Yuanyuan Liu, Yuxuan Huang, Shuyang Liu, Yibing Zhan, Zijing Chen, Zhe Chen
Abstract: In Video-based Facial Expression Recognition (V-FER), models are typically trained on closed-set datasets with a fixed number of known classes. However, these V-FER models cannot deal with unknown classes that are prevalent in real-world scenarios. In this paper, we introduce a challenging Open-set Video-based Facial Expression Recognition (OV-FER) task, aiming at identifying not only known classes but also new, unknown human facial expressions not encountered during training. While existing approaches address open-set recognition by leveraging large-scale vision-language models like CLIP to identify unseen classes, we argue that these methods may not adequately capture the nuanced and subtle human expression patterns required by the OV-FER task. To address this limitation, we propose a novel Human Expression-Sensitive Prompting (HESP) mechanism to significantly enhance CLIP's ability to model video-based facial expression details effectively, thereby presenting a new CLIP-based OV-FER approach. Our proposed HESP comprises three components: 1) a textual prompting module with learnable prompt representations to complement the original CLIP textual prompts and enhance the textual representations of both known and unknown emotions, 2) a visual prompting module that encodes temporal emotional information from video frames using expression-sensitive attention, equipping CLIP with a new visual modeling ability to extract emotion-rich information, 3) a delicately designed open-set multi-task learning scheme that facilitates prompt learning and encourages interactions between the textual and visual prompting modules. Extensive experiments conducted on four OV-FER task settings demonstrate that HESP can significantly boost CLIP's performance (a relative improvement of 17.93% on AUROC and 106.18% on OSCR) and outperform other state-of-the-art open-set video understanding methods by a large margin.
Authors: Shivangi Yadav, Arun Ross
Abstract: Biometric systems based on iris recognition are currently being used in border control applications and mobile devices. However, research in iris recognition is stymied by various factors such as limited datasets of bonafide irides and presentation attack instruments; restricted intra-class variations; and privacy concerns. Some of these issues can be mitigated by the use of synthetic iris data. In this paper, we present a comprehensive review of state-of-the-art GAN-based synthetic iris image generation techniques, evaluating their strengths and limitations in producing realistic and useful iris images that can be used for both training and testing iris recognition systems and presentation attack detectors. In this regard, we first survey the various methods that have been used for synthetic iris generation and specifically consider generators based on StyleGAN, RaSGAN, CIT-GAN, iWarpGAN, StarGAN, etc. We then analyze the images generated by these models for realism, uniqueness, and biometric utility. This comprehensive analysis highlights the pros and cons of various GANs in the context of developing robust iris matchers and presentation attack detectors.
Authors: Yasuyo Kita, Yudai Fujieda, Ichiro Matsuda, Nobuyuki Kita
Abstract: In this paper, we propose a method for calculating the three-dimensional (3D) position and orientation of a pallet placed on a shelf on the side of a forklift truck using a 360-degree camera. By using a 360-degree camera mounted on the forklift truck, it is possible to observe both the pallet at the side of the forklift and one several meters ahead. However, the pallet on the obtained image is observed with different distortion depending on its 3D position, so that it is difficult to extract the pallet from the image. To solve this problem, a method [1] has been proposed for detecting a pallet by projecting a 360-degree image on a vertical plane that coincides with the front of the shelf to calculate an image similar to the image seen from the front of the shelf. At the same time as the detection, the approximate position and orientation of the detected pallet can be obtained, but the accuracy is not sufficient for automatic control of the forklift truck. In this paper, we propose a method for accurately detecting the yaw angle, which is the angle of the front surface of the pallet in the horizontal plane, by projecting the 360-degree image on a horizontal plane including the boundary line of the front surface of the detected pallet. The position of the pallet is also determined by moving the vertical plane having the detected yaw angle back and forth, and finding the position at which the degree of coincidence between the projection image on the vertical plane and the actual size of the front surface of the pallet is maximized. Experiments using real images taken in a laboratory and an actual warehouse have confirmed that the proposed method can calculate the position and orientation of a pallet within a reasonable calculation time and with the accuracy necessary for inserting the fork into the hole in the front of the pallet.
Authors: Zhenrong Zhang, Jianan Liu, Xi Zhou, Tao Huang, Qing-Long Han, Jingxin Liu, Hongbin Liu
Abstract: Cooperative perception is essential to enhance the efficiency and safety of future transportation systems, requiring extensive data sharing among vehicles on the road, which raises significant privacy concerns. Federated learning offers a promising solution by enabling data privacy-preserving collaborative enhancements in perception, decision-making, and planning among connected and autonomous vehicles (CAVs). However, federated learning is impeded by significant challenges arising from data heterogeneity across diverse clients, potentially diminishing model accuracy and prolonging convergence periods. This study introduces a specialized federated learning framework for CP, termed the federated dynamic weighted aggregation (FedDWA) algorithm, facilitated by dynamic adjusting loss (DALoss) function. This framework employs dynamic client weighting to direct model convergence and integrates a novel loss function that utilizes Kullback-Leibler divergence (KLD) to counteract the detrimental effects of non-independently and identically distributed (Non-IID) and unbalanced data. Utilizing the BEV transformer as the primary model, our rigorous testing on the OpenV2V dataset, augmented with FedBEVT data, demonstrates significant improvements in the average intersection over union (IoU). These results highlight the substantial potential of our federated learning framework to address data heterogeneity challenges in CP, thereby enhancing the accuracy of environmental perception models and facilitating more robust and efficient collaborative learning solutions in the transportation sector.
Authors: Xiongjun Guan, Yongjie Duan, Jianjiang Feng, Jie Zhou
Abstract: Skin distortion is a long standing challenge in fingerprint matching, which causes false non-matches. Previous studies have shown that the recognition rate can be improved by estimating the distortion field from a distorted fingerprint and then rectifying it into a normal fingerprint. However, existing rectification methods are based on principal component representation of distortion fields, which is not accurate and are very sensitive to finger pose. In this paper, we propose a rectification method where a self-reference based network is utilized to directly estimate the dense distortion field of distorted fingerprint instead of its low dimensional representation. This method can output accurate distortion fields of distorted fingerprints with various finger poses. Considering the limited number and variety of distorted fingerprints in the existing public dataset, we collected more distorted fingerprints with diverse finger poses and distortion patterns as a new database. Experimental results demonstrate that our proposed method achieves the state-of-the-art rectification performance in terms of distortion field estimation and rectified fingerprint matching.
Authors: Xiongjun Guan, Jianjiang Feng, Jie Zhou
Abstract: In order to make 3D fingerprints compatible with traditional 2D flat fingerprints, a common practice is to unfold the 3D fingerprint into a 2D rolled fingerprint, which is then matched with the flat fingerprints by traditional 2D fingerprint recognition algorithms. The problem with this method is that there may be large elastic deformation between the unfolded rolled fingerprint and flat fingerprint, which affects the recognition rate. In this paper, we propose a pose-specific 3D fingerprint unfolding algorithm to unfold the 3D fingerprint using the same pose as the flat fingerprint. Our experiments show that the proposed unfolding algorithm improves the compatibility between 3D fingerprint and flat fingerprint and thus leads to higher genuine matching scores.
Authors: Tunhou Zhang, Shiyu Li, Hsin-Pai Cheng, Feng Yan, Hai Li, Yiran Chen
Abstract: Exploring dense connectivity of convolutional operators establishes critical "synapses" to communicate feature vectors from different levels and enriches the set of transformations on Computer Vision applications. Yet, even with heavy-machinery approaches such as Neural Architecture Search (NAS), discovering effective connectivity patterns requires tremendous efforts due to either constrained connectivity design space or a sub-optimal exploration process induced by an unconstrained search space. In this paper, we propose CSCO, a novel paradigm that fabricates effective connectivity of convolutional operators with minimal utilization of existing design motifs and further utilizes the discovered wiring to construct high-performing ConvNets. CSCO guides the exploration via a neural predictor as a surrogate of the ground-truth performance. We introduce Graph Isomorphism as data augmentation to improve sample efficiency and propose a Metropolis-Hastings Evolutionary Search (MH-ES) to evade locally optimal architectures and advance search quality. Results on ImageNet show ~0.6% performance improvement over hand-crafted and NAS-crafted dense connectivity. Our code is publicly available.
Authors: Xiongjun Guan, Jianjiang Feng, Jie Zhou
Abstract: Fingerprint dense registration aims to finely align fingerprint pairs at the pixel level, thereby reducing intra-class differences caused by distortion. Unfortunately, traditional methods exhibited subpar performance when dealing with low-quality fingerprints while suffering from slow inference speed. Although deep learning based approaches shows significant improvement in these aspects, their registration accuracy is still unsatisfactory. In this paper, we propose a Phase-aggregated Dual-branch Registration Network (PDRNet) to aggregate the advantages of both types of methods. A dual-branch structure with multi-stage interactions is introduced between correlation information at high resolution and texture feature at low resolution, to perceive local fine differences while ensuring global stability. Extensive experiments are conducted on more comprehensive databases compared to previous works. Experimental results demonstrate that our method reaches the state-of-the-art registration performance in terms of accuracy and robustness, while maintaining considerable competitiveness in efficiency.
Authors: Ronghua Liao, Chen Hui, Lang Yuan, Feng Jiang
Abstract: No-Reference Image Quality Assessment (IQA) aims at estimating image quality in accordance with subjective human perception. However, most existing NR-IQA methods focus on exploring increasingly complex networks or components to improve the final performance. Such practice imposes great limitations and complexity on IQA methods, especially when they are applied to high-resolution (HR) images in the real world. Actually, most images own high spatial redundancy, especially for those HR data. To further exploit the characteristic and alleviate the issue above, we propose a new framework for Image Quality Assessment with compressive Sampling (dubbed S-IQA), which consists of three components: (1) The Flexible Sampling Module (FSM) samples the image to obtain measurements at an arbitrary ratio. (2) Vision Transformer with the Adaptive Embedding Module (AEM) makes measurements of uniform size and extracts deep features (3) Dual Branch (DB) allocates weight for every patch and predicts the final quality score. Experiments show that our proposed S-IQA achieves state-of-the-art result on various datasets with less data usage.
Authors: Yanbiao Ma, Licheng Jiao, Fang Liu, Lingling Li, Shuyuan Yang, Xu Liu
Abstract: In semi-supervised learning, methods that rely on confidence learning to generate pseudo-labels have been widely proposed. However, increasing research finds that when faced with noisy and biased data, the model's representation network is more reliable than the classification network. Additionally, label generation methods based on model predictions often show poor adaptability across different datasets, necessitating customization of the classification network. Therefore, we propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model predictions and utilizes image embeddings to generate sample labels. We also introduce an adaptive method for selecting hyperparameters in HDL, enhancing its versatility. Moreover, HDL can be combined with general image encoders (e.g., CLIP) to serve as a fundamental data processing module. We extract embeddings from datasets with class-balanced and long-tailed distributions using pre-trained semi-supervised models. Subsequently, samples are re-labeled using HDL, and the re-labeled samples are used to further train the semi-supervised models. Experiments demonstrate improved model performance, validating the motivation that representation networks are more reliable than classifiers or predictors. Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.
Authors: Enxin Song, Wenhao Chai, Tian Ye, Jenq-Neng Hwang, Xi Li, Gaoang Wang
Abstract: Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing methods either employ complex spatial-temporal modules or rely heavily on additional perception models to extract temporal features for video understanding, and they only perform well on short videos. For long videos, the computational complexity and memory costs associated with long-term temporal connections are significantly increased, posing additional challenges.Taking advantage of the Atkinson-Shiffrin memory model, with tokens in Transformers being employed as the carriers of memory in combination with our specially designed memory mechanism, we propose MovieChat to overcome these challenges. We lift pre-trained multi-modal large language models for understanding long videos without incorporating additional trainable temporal modules, employing a zero-shot approach. MovieChat achieves state-of-the-art performance in long video understanding, along with the released MovieChat-1K benchmark with 1K long video, 2K temporal grounding labels, and 14K manual annotations for validation of the effectiveness of our method. The code along with the dataset can be accessed via the following https://github.com/rese1f/MovieChat.
Authors: Yuhang Zhou, Haolin Li, Siyuan Du, Jiangchao Yao, Ya Zhang, Yanfeng Wang
Abstract: The popularity of large-scale pre-training has promoted the development of medical foundation models. However, some studies have shown that although foundation models exhibit strong general feature extraction capabilities, their performance on specific tasks is still inferior to task-specific methods. In this paper, we explore a new perspective called ``Knowledge Decomposition'' to improve the performance on specific medical tasks, which deconstruct the foundation model into multiple lightweight expert models, each dedicated to a particular task, with the goal of improving specialization while concurrently mitigating resource expenditure. To accomplish the above objective, we design a novel framework named Low-Rank Knowledge Decomposition (LoRKD), which explicitly separates graidents by incorporating low-rank expert modules and the efficient knowledge separation convolution. Extensive experimental results demonstrate that the decomposed models perform well in terms of performance and transferability, even surpassing the original foundation models.
Authors: Jiajun Liang, Baoquan Zhang, Yunming Ye, Xutao Li, Chuyao Luo, Xukai Fu
Abstract: The accurate detection of Mesoscale Convective Systems (MCS) is crucial for meteorological monitoring due to their potential to cause significant destruction through severe weather phenomena such as hail, thunderstorms, and heavy rainfall. However, the existing methods for MCS detection mostly targets on single-frame detection, which just considers the static characteristics and ignores the temporal evolution in the life cycle of MCS. In this paper, we propose a novel encoder-decoder neural network for MCS detection(MCSDNet). MCSDNet has a simple architecture and is easy to expand. Different from the previous models, MCSDNet targets on multi-frames detection and leverages multi-scale spatiotemporal information for the detection of MCS regions in remote sensing imagery(RSI). As far as we know, it is the first work to utilize multi-scale spatiotemporal information to detect MCS regions. Firstly, we design a multi-scale spatiotemporal information module to extract multi-level semantic from different encoder levels, which makes our models can extract more detail spatiotemporal features. Secondly, a Spatiotemporal Mix Unit(STMU) is introduced to MCSDNet to capture both intra-frame features and inter-frame correlations, which is a scalable module and can be replaced by other spatiotemporal module, e.g., CNN, RNN, Transformer and our proposed Dual Spatiotemporal Attention(DSTA). This means that the future works about spatiotemporal modules can be easily integrated to our model. Finally, we present MCSRSI, the first publicly available dataset for multi-frames MCS detection based on visible channel images from the FY-4A satellite. We also conduct several experiments on MCSRSI and find that our proposed MCSDNet achieve the best performance on MCS detection task when comparing to other baseline methods.
Authors: Fangda Chen, Jiacheng Nie, Lichuan Jiang, Zhuoer Zeng
Abstract: We introduced "Presidifussion," a novel approach to learning and replicating the unique style of calligraphy of President Xu, using a pretrained diffusion model adapted through a two-stage training process. Initially, our model is pretrained on a diverse dataset containing works from various calligraphers. This is followed by fine-tuning on a smaller, specialized dataset of President Xu's calligraphy, comprising just under 200 images. Our method introduces innovative techniques of font image conditioning and stroke information conditioning, enabling the model to capture the intricate structural elements of Chinese characters. The effectiveness of our approach is demonstrated through a comparison with traditional methods like zi2zi and CalliGAN, with our model achieving comparable performance using significantly smaller datasets and reduced computational resources. This work not only presents a breakthrough in the digital preservation of calligraphic art but also sets a new standard for data-efficient generative modeling in the domain of cultural heritage digitization.
Authors: Sotirios Konstantakos, Despina Ioanna Chalkiadaki, Ioannis Mademlis, Yuki M. Asano, Efstratios Gavves, Georgios Th. Papadopoulos
Abstract: Self-Supervised Learning (SSL) is a valuable and robust training methodology for contemporary Deep Neural Networks (DNNs), enabling unsupervised pretraining on a `pretext task' that does not require ground-truth labels/annotation. This allows efficient representation learning from massive amounts of unlabeled training data, which in turn leads to increased accuracy in a `downstream task' by exploiting supervised transfer learning. Despite the relatively straightforward conceptualization and applicability of SSL, it is not always feasible to collect and/or to utilize very large pretraining datasets, especially when it comes to real-world application settings. In particular, in cases of specialized and domain-specific application scenarios, it may not be achievable or practical to assemble a relevant image pretraining dataset in the order of millions of instances or it could be computationally infeasible to pretrain at this scale. This motivates an investigation on the effectiveness of common SSL pretext tasks, when the pretraining dataset is of relatively limited/constrained size. In this context, this work introduces a taxonomy of modern visual SSL methods, accompanied by detailed explanations and insights regarding the main categories of approaches, and, subsequently, conducts a thorough comparative experimental evaluation in the low-data regime, targeting to identify: a) what is learnt via low-data SSL pretraining, and b) how do different SSL categories behave in such training scenarios. Interestingly, for domain-specific downstream tasks, in-domain low-data SSL pretraining outperforms the common approach of large-scale pretraining on general datasets. Grounded on the obtained results, valuable insights are highlighted regarding the performance of each category of SSL methods, which in turn suggest straightforward future research directions in the field.
Authors: Xinpeng Li, Teng Wang, Jian Zhao, Shuyi Mao, Jinbao Wang, Feng Zheng, Xiaojiang Peng, Xuelong Li
Abstract: Emotion recognition aims to discern the emotional state of subjects within an image, relying on subject-centric and contextual visual cues. Current approaches typically follow a two-stage pipeline: first localize subjects by off-the-shelf detectors, then perform emotion classification through the late fusion of subject and context features. However, the complicated paradigm suffers from disjoint training stages and limited interaction between fine-grained subject-context elements. To address the challenge, we present a single-stage emotion recognition approach, employing a Decoupled Subject-Context Transformer (DSCT), for simultaneous subject localization and emotion classification. Rather than compartmentalizing training stages, we jointly leverage box and emotion signals as supervision to enrich subject-centric feature learning. Furthermore, we introduce DSCT to facilitate interactions between fine-grained subject-context cues in a decouple-then-fuse manner. The decoupled query token--subject queries and context queries--gradually intertwine across layers within DSCT, during which spatial and semantic relations are exploited and aggregated. We evaluate our single-stage framework on two widely used context-aware emotion recognition datasets, CAER-S and EMOTIC. Our approach surpasses two-stage alternatives with fewer parameter numbers, achieving a 3.39% accuracy improvement and a 6.46% average precision gain on CAER-S and EMOTIC datasets, respectively.
Authors: Marco Peer, Florian Kleber, Robert Sablatnig
Abstract: This paper introduces SAGHOG, a self-supervised pretraining strategy for writer retrieval using HOG features of the binarized input image. Our preprocessing involves the application of the Segment Anything technique to extract handwriting from various datasets, ending up with about 24k documents, followed by training a vision transformer on reconstructing masked patches of the handwriting. SAGHOG is then finetuned by appending NetRVLAD as an encoding layer to the pretrained encoder. Evaluation of our approach on three historical datasets, Historical-WI, HisFrag20, and GRK-Papyri, demonstrates the effectiveness of SAGHOG for writer retrieval. Additionally, we provide ablation studies on our architecture and evaluate un- and supervised finetuning. Notably, on HisFrag20, SAGHOG outperforms related work with a mAP of 57.2 % - a margin of 11.6 % to the current state of the art, showcasing its robustness on challenging data, and is competitive on even small datasets, e.g. GRK-Papyri, where we achieve a Top-1 accuracy of 58.0%.
Authors: Ziyue Zhang, Mingbao Lin, Rongrong Ji
Abstract: We introduce ObjectAdd, a training-free diffusion modification method to add user-expected objects into user-specified area. The motive of ObjectAdd stems from: first, describing everything in one prompt can be difficult, and second, users often need to add objects into the generated image. To accommodate with real world, our ObjectAdd maintains accurate image consistency after adding objects with technical innovations in: (1) embedding-level concatenation to ensure correct text embedding coalesce; (2) object-driven layout control with latent and attention injection to ensure objects accessing user-specified area; (3) prompted image inpainting in an attention refocusing & object expansion fashion to ensure rest of the image stays the same. With a text-prompted image, our ObjectAdd allows users to specify a box and an object, and achieves: (1) adding object inside the box area; (2) exact content outside the box area; (3) flawless fusion between the two areas
Authors: Fabio Quattrini, Vittorio Pippi, Silvia Cascianelli, Rita Cucchiara
Abstract: Document Image Binarization is a well-known problem in Document Analysis and Computer Vision, although it is far from being solved. One of the main challenges of this task is that documents generally exhibit degradations and acquisition artifacts that can greatly vary throughout the page. Nonetheless, even when dealing with a local patch of the document, taking into account the overall appearance of a wide portion of the page can ease the prediction by enriching it with semantic information on the ink and background conditions. In this respect, approaches able to model both local and global information have been proven suitable for this task. In particular, recent applications of Vision Transformer (ViT)-based models, able to model short and long-range dependencies via the attention mechanism, have demonstrated their superiority over standard Convolution-based models, which instead struggle to model global dependencies. In this work, we propose an alternative solution based on the recently introduced Fast Fourier Convolutions, which overcomes the limitation of standard convolutions in modeling global information while requiring fewer parameters than ViTs. We validate the effectiveness of our approach via extensive experimental analysis considering different types of degradations.
Authors: Reza Akbarian Bafghi, Nidhin Harilal, Claire Monteleoni, Maziar Raissi
Abstract: Artificial neural networks often suffer from catastrophic forgetting, where learning new concepts leads to a complete loss of previously acquired knowledge. We observe that this issue is particularly magnified in vision transformers (ViTs), where post-pre-training and fine-tuning on new tasks can significantly degrade the model's original general abilities. For instance, a DINO ViT-Base/16 pre-trained on ImageNet-1k loses over 70% accuracy on ImageNet-1k after just 10 iterations of fine-tuning on CIFAR-100. Overcoming this stability-plasticity dilemma is crucial for enabling ViTs to continuously learn and adapt to new domains while preserving their initial knowledge. In this work, we study two new parameter-efficient fine-tuning strategies: (1)~Block Expansion, and (2) Low-rank adaptation (LoRA). Our experiments reveal that using either Block Expansion or LoRA on self-supervised pre-trained ViTs surpass fully fine-tuned ViTs in new domains while offering significantly greater parameter efficiency. Notably, we find that Block Expansion experiences only a minimal performance drop in the pre-training domain, thereby effectively mitigating catastrophic forgetting in pre-trained ViTs.
Authors: Samuel Cerezo, Javier Civera
Abstract: In this paper, we introduce a novel formulation for camera motion estimation that integrates RGB-D images and inertial data through scene flow. Our goal is to accurately estimate the camera motion in a rigid 3D environment, along with the state of the inertial measurement unit (IMU). Our proposed method offers the flexibility to operate as a multi-frame optimization or to marginalize older data, thus effectively utilizing past measurements. To assess the performance of our method, we conducted evaluations using both synthetic data from the ICL-NUIM dataset and real data sequences from the OpenLORIS-Scene dataset. Our results show that the fusion of these two sensors enhances the accuracy of camera motion estimation when compared to using only visual data.
Authors: Glen Pouliquen (IDnow AI & ML Center of Excellence, France, EPITA Research Lab), Guillaume Chiron (IDnow AI & ML Center of Excellence, France), Joseph Chazalon (EPITA Research Lab), Thierry G\'eraud (EPITA Research Lab), Ahmad Montaser Awal (IDnow AI & ML Center of Excellence, France)
Abstract: We propose a method to remotely verify the authenticity of Optically Variable Devices (OVDs), often referred to as ``holograms'', in identity documents. Our method processes video clips captured with smartphones under common lighting conditions, and is evaluated on two public datasets: MIDV-HOLO and MIDV-2020. Thanks to a weakly-supervised training, we optimize a feature extraction and decision pipeline which achieves a new leading performance on MIDV-HOLO, while maintaining a high recall on documents from MIDV-2020 used as attack samples. It is also the first method, to date, to effectively address the photo replacement attack task, and can be trained on either genuine samples, attack samples, or both for increased performance. By enabling to verify OVD shapes and dynamics with very little supervision, this work opens the way towards the use of massive amounts of unlabeled data to build robust remote identity document verification systems on commodity smartphones. Code is available at https://github.com/EPITAResearchLab/pouliquen.24.icdar
URLs: https://github.com/EPITAResearchLab/pouliquen.24.icdar
Authors: Jiawei Song, Dengpan Ye, Yunming Zhang
Abstract: Artificial Intelligence Generated Content (AIGC) techniques, represented by text-to-image generation, have led to a malicious use of deep forgeries, raising concerns about the trustworthiness of multimedia content. Adapting traditional forgery detection methods to diffusion models proves challenging. Thus, this paper proposes a forgery detection method explicitly designed for diffusion models called Trinity Detector. Trinity Detector incorporates coarse-grained text features through a CLIP encoder, coherently integrating them with fine-grained artifacts in the pixel domain for comprehensive multimodal detection. To heighten sensitivity to diffusion-generated image features, a Multi-spectral Channel Attention Fusion Unit (MCAF) is designed, extracting spectral inconsistencies through adaptive fusion of diverse frequency bands and further integrating spatial co-occurrence of the two modalities. Extensive experimentation validates that our Trinity Detector method outperforms several state-of-the-art methods, our performance is competitive across all datasets and up to 17.6\% improvement in transferability in the diffusion datasets.
Authors: Georgia Baltsou, Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos
Abstract: AI systems rely on extensive training on large datasets to address various tasks. However, image-based systems, particularly those used for demographic attribute prediction, face significant challenges. Many current face image datasets primarily focus on demographic factors such as age, gender, and skin tone, overlooking other crucial facial attributes like hairstyle and accessories. This narrow focus limits the diversity of the data and consequently the robustness of AI systems trained on them. This work aims to address this limitation by proposing a methodology for generating synthetic face image datasets that capture a broader spectrum of facial diversity. Specifically, our approach integrates a systematic prompt formulation strategy, encompassing not only demographics and biometrics but also non-permanent traits like make-up, hairstyle, and accessories. These prompts guide a state-of-the-art text-to-image model in generating a comprehensive dataset of high-quality realistic images and can be used as an evaluation set in face analysis systems. Compared to existing datasets, our proposed dataset proves equally or more challenging in image classification tasks while being much smaller in size.
Authors: Xuri Ge, Songpei Xu, Fuhai Chen, Jie Wang, Guoxin Wang, Shan An, Joemon M. Jose
Abstract: In this paper, we propose a novel visual Semantic-Spatial Self-Highlighting Network (termed 3SHNet) for high-precision, high-efficiency and high-generalization image-sentence retrieval. 3SHNet highlights the salient identification of prominent objects and their spatial locations within the visual modality, thus allowing the integration of visual semantics-spatial interactions and maintaining independence between two modalities. This integration effectively combines object regions with the corresponding semantic and position layouts derived from segmentation to enhance the visual representation. And the modality-independence guarantees efficiency and generalization. Additionally, 3SHNet utilizes the structured contextual visual scene information from segmentation to conduct the local (region-based) or global (grid-based) guidance and achieve accurate hybrid-level retrieval. Extensive experiments conducted on MS-COCO and Flickr30K benchmarks substantiate the superior performances, inference efficiency and generalization of the proposed 3SHNet when juxtaposed with contemporary state-of-the-art methodologies. Specifically, on the larger MS-COCO 5K test set, we achieve 16.3%, 24.8%, and 18.3% improvements in terms of rSum score, respectively, compared with the state-of-the-art methods using different image representations, while maintaining optimal retrieval efficiency. Moreover, our performance on cross-dataset generalization improves by 18.6%. Data and code are available at https://github.com/XuriGe1995/3SHNet.
Authors: Xiang Gu, Xi Yu, Yan Yang, Jian Sun, Zongben Xu
Abstract: The practical Domain Adaptation (DA) tasks, e.g., Partial DA (PDA), open-set DA, universal DA, and test-time adaptation, have gained increasing attention in the machine learning community. In this paper, we propose a novel approach, dubbed Adversarial Reweighting with $\alpha$-Power Maximization (ARPM), for PDA where the source domain contains private classes absent in target domain. In ARPM, we propose a novel adversarial reweighting model that adversarially learns to reweight source domain data to identify source-private class samples by assigning smaller weights to them, for mitigating potential negative transfer. Based on the adversarial reweighting, we train the transferable recognition model on the reweighted source distribution to be able to classify common class data. To reduce the prediction uncertainty of the recognition model on the target domain for PDA, we present an $\alpha$-power maximization mechanism in ARPM, which enriches the family of losses for reducing the prediction uncertainty for PDA. Extensive experimental results on five PDA benchmarks, i.e., Office-31, Office-Home, VisDA-2017, ImageNet-Caltech, and DomainNet, show that our method is superior to recent PDA methods. Ablation studies also confirm the effectiveness of components in our approach. To theoretically analyze our method, we deduce an upper bound of target domain expected error for PDA, which is approximately minimized in our approach. We further extend ARPM to open-set DA, universal DA, and test time adaptation, and verify the usefulness through experiments.
Authors: Yuanman Li, Yingjie He, Changsheng Chen, Li Dong, Bin Li, Jiantao Zhou, Xia Li
Abstract: Recent advances in deep learning algorithms have shown impressive progress in image copy-move forgery detection (CMFD). However, these algorithms lack generalizability in practical scenarios where the copied regions are not present in the training images, or the cloned regions are part of the background. Additionally, these algorithms utilize convolution operations to distinguish source and target regions, leading to unsatisfactory results when the target regions blend well with the background. To address these limitations, this study proposes a novel end-to-end CMFD framework that integrates the strengths of conventional and deep learning methods. Specifically, the study develops a deep cross-scale PatchMatch (PM) method that is customized for CMFD to locate copy-move regions. Unlike existing deep models, our approach utilizes features extracted from high-resolution scales to seek explicit and reliable point-to-point matching between source and target regions. Furthermore, we propose a novel pairwise rank learning framework to separate source and target regions. By leveraging the strong prior of point-to-point matches, the framework can identify subtle differences and effectively discriminate between source and target regions, even when the target regions blend well with the background. Our framework is fully differentiable and can be trained end-to-end. Comprehensive experimental results highlight the remarkable generalizability of our scheme across various copy-move scenarios, significantly outperforming existing methods.
Authors: Jyri Maanp\"a\"a, Julius Pesonen, Heikki Hyyti, Iaroslav Melekhov, Juho Kannala, Petri Manninen, Antero Kukko, Juha Hyypp\"a
Abstract: Slippery road weather conditions are prevalent in many regions and cause a regular risk for traffic. Still, there has been less research on how autonomous vehicles could detect slippery driving conditions on the road to drive safely. In this work, we propose a method to predict a dense grip map from the area in front of the car, based on postprocessed multimodal sensor data. We trained a convolutional neural network to predict pixelwise grip values from fused RGB camera, thermal camera, and LiDAR reflectance images, based on weakly supervised ground truth from an optical road weather sensor. The experiments show that it is possible to predict dense grip values with good accuracy from the used data modalities as the produced grip map follows both ground truth measurements and local weather conditions, such as snowy areas on the road. The model using only the RGB camera or LiDAR reflectance modality provided good baseline results for grip prediction accuracy while using models fusing the RGB camera, thermal camera, and LiDAR modalities improved the grip predictions significantly.
Authors: Xin Zhang, Liangxiu Han, Tam Sobeih, Lianghao Han, Darren Dancey
Abstract: Depth estimation is crucial for interpreting complex environments, especially in areas such as autonomous vehicle navigation and robotics. Nonetheless, obtaining accurate depth readings from event camera data remains a formidable challenge. Event cameras operate differently from traditional digital cameras, continuously capturing data and generating asynchronous binary spikes that encode time, location, and light intensity. Yet, the unique sampling mechanisms of event cameras render standard image based algorithms inadequate for processing spike data. This necessitates the development of innovative, spike-aware algorithms tailored for event cameras, a task compounded by the irregularity, continuity, noise, and spatial and temporal characteristics inherent in spiking data.Harnessing the strong generalization capabilities of transformer neural networks for spatiotemporal data, we propose a purely spike-driven spike transformer network for depth estimation from spiking camera data. To address performance limitations with Spiking Neural Networks (SNN), we introduce a novel single-stage cross-modality knowledge transfer framework leveraging knowledge from a large vision foundational model of artificial neural networks (ANN) (DINOv2) to enhance the performance of SNNs with limited data. Our experimental results on both synthetic and real datasets show substantial improvements over existing models, with notable gains in Absolute Relative and Square Relative errors (49% and 39.77% improvements over the benchmark model Spike-T, respectively). Besides accuracy, the proposed model also demonstrates reduced power consumptions, a critical factor for practical applications.
Authors: Chengliang Liu, Jie Wen, Yabo Liu, Chao Huang, Zhihao Wu, Xiaoling Luo, Yong Xu
Abstract: Multi-view learning has become a popular research topic in recent years, but research on the cross-application of classic multi-label classification and multi-view learning is still in its early stages. In this paper, we focus on the complex yet highly realistic task of incomplete multi-view weak multi-label learning and propose a masked two-channel decoupling framework based on deep neural networks to solve this problem. The core innovation of our method lies in decoupling the single-channel view-level representation, which is common in deep multi-view learning methods, into a shared representation and a view-proprietary representation. We also design a cross-channel contrastive loss to enhance the semantic property of the two channels. Additionally, we exploit supervised information to design a label-guided graph regularization loss, helping the extracted embedding features preserve the geometric structure among samples. Inspired by the success of masking mechanisms in image and text analysis, we develop a random fragment masking strategy for vector features to improve the learning ability of encoders. Finally, it is important to emphasize that our model is fully adaptable to arbitrary view and label absences while also performing well on the ideal full data. We have conducted sufficient and convincing experiments to confirm the effectiveness and advancement of our model.
Authors: Maoxun Yuan, Bo Cui, Tianyi Zhao, Xingxing Wei
Abstract: Semantic analysis on visible (RGB) and infrared (IR) images has gained attention for its ability to be more accurate and robust under low-illumination and complex weather conditions. Due to the lack of pre-trained foundation models on the large-scale infrared image datasets, existing methods prefer to design task-specific frameworks and directly fine-tune them with pre-trained foundation models on their RGB-IR semantic relevance datasets, which results in poor scalability and limited generalization. In this work, we propose a scalable and efficient framework called UniRGB-IR to unify RGB-IR downstream tasks, in which a novel adapter is developed to efficiently introduce richer RGB-IR features into the pre-trained RGB-based foundation model. Specifically, our framework consists of a vision transformer (ViT) foundation model, a Multi-modal Feature Pool (MFP) module and a Supplementary Feature Injector (SFI) module. The MFP and SFI modules cooperate with each other as an adpater to effectively complement the ViT features with the contextual multi-scale features. During training process, we freeze the entire foundation model to inherit prior knowledge and only optimize the MFP and SFI modules. Furthermore, to verify the effectiveness of our framework, we utilize the ViT-Base as the pre-trained foundation model to perform extensive experiments. Experimental results on various RGB-IR downstream tasks demonstrate that our method can achieve state-of-the-art performance. The source code and results are available at https://github.com/PoTsui99/UniRGB-IR.git.
Authors: Haoyu Wang, Zhilu Zhang, Donglin Di, Shiliang Zhang, Wangmeng Zuo
Abstract: The goal of image-based virtual try-on is to generate an image of the target person naturally wearing the given clothing. However, most existing methods solely focus on the frontal try-on using the frontal clothing. When the views of the clothing and person are significantly inconsistent, particularly when the person's view is non-frontal, the results are unsatisfactory. To address this challenge, we introduce Multi-View Virtual Try-ON (MV-VTON), which aims to reconstruct the dressing results of a person from multiple views using the given clothes. On the one hand, given that single-view clothes provide insufficient information for MV-VTON, we instead employ two images, i.e., the frontal and back views of the clothing, to encompass the complete view as much as possible. On the other hand, the diffusion models that have demonstrated superior abilities are adopted to perform our MV-VTON. In particular, we propose a view-adaptive selection method where hard-selection and soft-selection are applied to the global and local clothing feature extraction, respectively. This ensures that the clothing features are roughly fit to the person's view. Subsequently, we suggest a joint attention block to align and fuse clothing features with person features. Additionally, we collect a MV-VTON dataset, i.e., Multi-View Garment (MVG), in which each person has multiple photos with diverse views and poses. Experiments show that the proposed method not only achieves state-of-the-art results on MV-VTON task using our MVG dataset, but also has superiority on frontal-view virtual try-on task using VITON-HD and DressCode datasets. Codes and datasets will be publicly released at https://github.com/hywang2002/MV-VTON .
Authors: Shun Maeda, Chunzhi Gu, Jun Yu, Shogo Tokai, Shangce Gao, Chao Zhang
Abstract: We introduce the task of human action anomaly detection (HAAD), which aims to identify anomalous motions in an unsupervised manner given only the pre-determined normal category of training action samples. Compared to prior human-related anomaly detection tasks which primarily focus on unusual events from videos, HAAD involves the learning of specific action labels to recognize semantically anomalous human behaviors. To address this task, we propose a normalizing flow (NF)-based detection framework where the sample likelihood is effectively leveraged to indicate anomalies. As action anomalies often occur in some specific body parts, in addition to the full-body action feature learning, we incorporate extra encoding streams into our framework for a finer modeling of body subsets. Our framework is thus multi-level to jointly discover global and local motion anomalies. Furthermore, to show awareness of the potentially jittery data during recording, we resort to discrete cosine transformation by converting the action samples from the temporal to the frequency domain to mitigate the issue of data instability. Extensive experimental results on two human action datasets demonstrate that our method outperforms the baselines formed by adapting state-of-the-art human activity AD approaches to our task of HAAD.
Authors: Zishu Yao, Guodong Fan, Jinfu Fan, Min Gan, C. L. Philip Chen
Abstract: Low-light remote sensing images generally feature high resolution and high spatial complexity, with continuously distributed surface features in space. This continuity in scenes leads to extensive long-range correlations in spatial domains within remote sensing images. Convolutional Neural Networks, which rely on local correlations for long-distance modeling, struggle to establish long-range correlations in such images. On the other hand, transformer-based methods that focus on global information face high computational complexities when processing high-resolution remote sensing images. From another perspective, Fourier transform can compute global information without introducing a large number of parameters, enabling the network to more efficiently capture the overall image structure and establish long-range correlations. Therefore, we propose a Dual-Domain Feature Fusion Network (DFFN) for low-light remote sensing image enhancement. Specifically, this challenging task of low-light enhancement is divided into two more manageable sub-tasks: the first phase learns amplitude information to restore image brightness, and the second phase learns phase information to refine details. To facilitate information exchange between the two phases, we designed an information fusion affine block that combines data from different phases and scales. Additionally, we have constructed two dark light remote sensing datasets to address the current lack of datasets in dark light remote sensing image enhancement. Extensive evaluations show that our method outperforms existing state-of-the-art methods. The code is available at https://github.com/iijjlk/DFFN.
Authors: Seungwook Kim, Yichun Shi, Kejie Li, Minsu Cho, Peng Wang
Abstract: Using image as prompts for 3D generation demonstrate particularly strong performances compared to using text prompts alone, for images provide a more intuitive guidance for the 3D generation process. In this work, we delve into the potential of using multiple image prompts, instead of a single image prompt, for 3D generation. Specifically, we build on ImageDream, a novel image-prompt multi-view diffusion model, to support multi-view images as the input prompt. Our method, dubbed MultiImageDream, reveals that transitioning from a single-image prompt to multiple-image prompts enhances the performance of multi-view and 3D object generation according to various quantitative evaluation metrics and qualitative assessments. This advancement is achieved without the necessity of fine-tuning the pre-trained ImageDream multi-view diffusion model.
Authors: Moussa Kassem Sbeyti, Michelle Karg, Christian Wirth, Nadja Klein, Sahin Albayrak
Abstract: Object detectors in real-world applications often fail to detect objects due to varying factors such as weather conditions and noisy input. Therefore, a process that mitigates false detections is crucial for both safety and accuracy. While uncertainty-based thresholding shows promise, previous works demonstrate an imperfect correlation between uncertainty and detection errors. This hinders ideal thresholding, prompting us to further investigate the correlation and associated cost with different types of uncertainty. We therefore propose a cost-sensitive framework for object detection tailored to user-defined budgets on the two types of errors, missing and false detections. We derive minimum thresholding requirements to prevent performance degradation and define metrics to assess the applicability of uncertainty for failure recognition. Furthermore, we automate and optimize the thresholding process to maximize the failure recognition rate w.r.t. the specified budget. Evaluation on three autonomous driving datasets demonstrates that our approach significantly enhances safety, particularly in challenging scenarios. Leveraging localization aleatoric uncertainty and softmax-based entropy only, our method boosts the failure recognition rate by 36-60\% compared to conventional approaches. Code is available at https://mos-ks.github.io/publications.
Authors: Bingchen Li, Xin Li, Yiting Lu, Ruoyu Feng, Mengxi Guo, Shijie Zhao, Li Zhang, Zhibo Chen
Abstract: Blind Compressed Image Restoration (CIR) has garnered significant attention due to its practical applications. It aims to mitigate compression artifacts caused by unknown quality factors, particularly with JPEG codecs. Existing works on blind CIR often seek assistance from a quality factor prediction network to facilitate their network to restore compressed images. However, the predicted numerical quality factor lacks spatial information, preventing network adaptability toward image contents. Recent studies in prompt-learning-based image restoration have showcased the potential of prompts to generalize across varied degradation types and degrees. This motivated us to design a prompt-learning-based compressed image restoration network, dubbed PromptCIR, which can effectively restore images from various compress levels. Specifically, PromptCIR exploits prompts to encode compression information implicitly, where prompts directly interact with soft weights generated from image features, thus providing dynamic content-aware and distortion-aware guidance for the restoration process. The light-weight prompts enable our method to adapt to different compression levels, while introducing minimal parameter overhead. Overall, PromptCIR leverages the powerful transformer-based backbone with the dynamic prompt module to proficiently handle blind CIR tasks, winning first place in the NTIRE 2024 challenge of blind compressed image enhancement track. Extensive experiments have validated the effectiveness of our proposed PromptCIR. The code is available at https://github.com/lbc12345/PromptCIR-NTIRE24.
Authors: Zhenghong Li, Jiaxiang Ren, Wensheng Cheng, Congwu Du, Yingtian Pan, Haibin Ling
Abstract: Optical Doppler Tomography (ODT) is a blood flow imaging technique popularly used in bioengineering applications. The fundamental unit of ODT is the 1D frequency response along the A-line (depth), named raw A-scan. A 2D ODT image (B-scan) is obtained by first sensing raw A-scans along the B-line (width), and then constructing the B-scan from these raw A-scans via magnitude-phase analysis and post-processing. To obtain a high-resolution B-scan with a precise flow map, densely sampled A-scans are required in current methods, causing both computational and storage burdens. To address this issue, in this paper we propose a novel sparse reconstruction framework with four main sequential steps: 1) early magnitude-phase fusion that encourages rich interaction of the complementary information in magnitude and phase, 2) State Space Model (SSM)-based representation learning, inspired by recent successes in Mamba and VMamba, to naturally capture both the intra-A-scan sequential information and between-A-scan interactions, 3) an Inception-based Feedforward Network module (IncFFN) to further boost the SSM-module, and 4) a B-line Pixel Shuffle (BPS) layer to effectively reconstruct the final results. In the experiments on real-world animal data, our method shows clear effectiveness in reconstruction accuracy. As the first application of SSM for image reconstruction tasks, we expect our work to inspire related explorations in not only efficient ODT imaging techniques but also generic image enhancement.
Authors: Hengfei Wang, Zhongqun Zhang, Yihua Cheng, Hyung Jin Chang
Abstract: Generating face image with specific gaze information has attracted considerable attention. Existing approaches typically input gaze values directly for face generation, which is unnatural and requires annotated gaze datasets for training, thereby limiting its application. In this paper, we present a novel gaze-controllable face generation task. Our approach inputs textual descriptions that describe human gaze and head behavior and generates corresponding face images. Our work first introduces a text-of-gaze dataset containing over 90k text descriptions spanning a dense distribution of gaze and head poses. We further propose a gaze-controllable text-to-face method. Our method contains a sketch-conditioned face diffusion module and a model-based sketch diffusion module. We define a face sketch based on facial landmarks and eye segmentation map. The face diffusion module generates face images from the face sketch, and the sketch diffusion module employs a 3D face model to generate face sketch from text description. Experiments on the FFHQ dataset show the effectiveness of our method. We will release our dataset and code for future research.
Authors: Danja Brandt, Martin Tschaikner, Teodor Chiaburu, Henning Schmidt, Ilona Schrimpf, Alexandra Stadel, Ingeborg E. Beckers, Frank Hau{\ss}er
Abstract: Preserving the number and diversity of insects is one of our society's most important goals in the area of environmental sustainability. A prerequisite for this is a systematic and up-scaled monitoring in order to detect correlations and identify countermeasures. Therefore, automatized monitoring using live traps is important, but so far there is no system that provides image data of sufficient detailed information for entomological classification. In this work, we present an imaging method as part of a multisensor system developed as a low-cost, scalable, open-source system that is adaptable to classical trap types. The image quality meets the requirements needed for classification in the taxonomic tree. Therefore, illumination and resolution have been optimized and motion artefacts have been suppressed. The system is evaluated exemplarily on a dataset consisting of 16 insect species of the same as well as different genus, family and order. We demonstrate that standard CNN-architectures like ResNet50 (pretrained on iNaturalist data) or MobileNet perform very well for the prediction task after re-training. Smaller custom made CNNs also lead to promising results. Classification accuracy of $>96\%$ has been achieved. Moreover, it was proved that image cropping of insects is necessary for classification of species with high inter-class similarity.
Authors: Lucas Ventura, Cordelia Schmid, G\"ul Varol
Abstract: We describe a protocol to study text-to-video retrieval training with unlabeled videos, where we assume (i) no access to labels for any videos, i.e., no access to the set of ground-truth captions, but (ii) access to labeled images in the form of text. Using image expert models is a realistic scenario given that annotating images is cheaper therefore scalable, in contrast to expensive video labeling schemes. Recently, zero-shot image experts such as CLIP have established a new strong baseline for video understanding tasks. In this paper, we make use of this progress and instantiate the image experts from two types of models: a text-to-image retrieval model to provide an initial backbone, and image captioning models to provide supervision signal into unlabeled videos. We show that automatically labeling video frames with image captioning allows text-to-video retrieval training. This process adapts the features to the target domain at no manual annotation cost, consequently outperforming the strong zero-shot CLIP baseline. During training, we sample captions from multiple video frames that best match the visual content, and perform a temporal pooling over frame representations by scoring frames according to their relevance to each caption. We conduct extensive ablations to provide insights and demonstrate the effectiveness of this simple framework by outperforming the CLIP zero-shot baselines on text-to-video retrieval on three standard datasets, namely ActivityNet, MSR-VTT, and MSVD.
Authors: Libang Chen, Yikun Liu, Jianying Zhou
Abstract: Imaging through fog significantly impacts fields such as object detection and recognition. In conditions of extremely low visibility, essential image information can be obscured, rendering standard extraction methods ineffective. Traditional digital processing techniques, such as histogram stretching, aim to mitigate fog effects by enhancing object light contrast diminished by atmospheric scattering. However, these methods often experience reduce effectiveness under inhomogeneous illumination. This paper introduces a novel approach that adaptively filters background illumination under extremely low visibility and preserve only the essential signal information. Additionally, we employ a visual optimization strategy based on image gradients to eliminate grayscale banding. Finally, the image is transformed to achieve high contrast and maintain fidelity to the original information through maximum histogram equalization. Our proposed method significantly enhances signal clarity in conditions of extremely low visibility and outperforms existing algorithms.
Authors: Wonjae Kim, Sanghyuk Chun, Taekyung Kim, Dongyoon Han, Sangdoo Yun
Abstract: In an era where the volume of data drives the effectiveness of self-supervised learning, the specificity and clarity of data semantics play a crucial role in model training. Addressing this, we introduce HYPerbolic Entailment filtering (HYPE), a novel methodology designed to meticulously extract modality-wise meaningful and well-aligned data from extensive, noisy image-text pair datasets. Our approach leverages hyperbolic embeddings and the concept of entailment cones to evaluate and filter out samples with meaningless or underspecified semantics, focusing on enhancing the specificity of each data sample. HYPE not only demonstrates a significant improvement in filtering efficiency but also sets a new state-of-the-art in the DataComp benchmark when combined with existing filtering techniques. This breakthrough showcases the potential of HYPE to refine the data selection process, thereby contributing to the development of more accurate and efficient self-supervised learning models. Additionally, the image specificity $\epsilon_{i}$ can be independently applied to induce an image-only dataset from an image-text or image-only data pool for training image-only self-supervised models and showed superior performance when compared to the dataset induced by CLIP score.
Authors: Tianqi Liu, Xinyi Ye, Min Shi, Zihao Huang, Zhiyu Pan, Zhan Peng, Zhiguo Cao
Abstract: Generalizable NeRF aims to synthesize novel views for unseen scenes. Common practices involve constructing variance-based cost volumes for geometry reconstruction and encoding 3D descriptors for decoding novel views. However, existing methods show limited generalization ability in challenging conditions due to inaccurate geometry, sub-optimal descriptors, and decoding strategies. We address these issues point by point. First, we find the variance-based cost volume exhibits failure patterns as the features of pixels corresponding to the same point can be inconsistent across different views due to occlusions or reflections. We introduce an Adaptive Cost Aggregation (ACA) approach to amplify the contribution of consistent pixel pairs and suppress inconsistent ones. Unlike previous methods that solely fuse 2D features into descriptors, our approach introduces a Spatial-View Aggregator (SVA) to incorporate 3D context into descriptors through spatial and inter-view interaction. When decoding the descriptors, we observe the two existing decoding strategies excel in different areas, which are complementary. A Consistency-Aware Fusion (CAF) strategy is proposed to leverage the advantages of both. We incorporate the above ACA, SVA, and CAF into a coarse-to-fine framework, termed Geometry-aware Reconstruction and Fusion-refined Rendering (GeFu). GeFu attains state-of-the-art performance across multiple datasets. Code is available at https://github.com/TQTQliu/GeFu .
Authors: Yuhang Huang, Zihan Wu, Chongyang Gao, Jiawei Peng, Xu Yang
Abstract: Large Vision-Language Models (LVLMs) are gaining traction for their remarkable ability to process and integrate visual and textual data. Despite their popularity, the capacity of LVLMs to generate precise, fine-grained textual descriptions has not been fully explored. This study addresses this gap by focusing on \textit{distinctiveness} and \textit{fidelity}, assessing how models like Open-Flamingo, IDEFICS, and MiniGPT-4 can distinguish between similar objects and accurately describe visual features. We proposed the Textual Retrieval-Augmented Classification (TRAC) framework, which, by leveraging its generative capabilities, allows us to delve deeper into analyzing fine-grained visual description generation. This research provides valuable insights into the generation quality of LVLMs, enhancing the understanding of multimodal language models. Notably, MiniGPT-4 stands out for its better ability to generate fine-grained descriptions, outperforming the other two models in this aspect. The code is provided at \url{https://anonymous.4open.science/r/Explore_FGVDs-E277}.
Authors: Mubashir Noman, Mustansar Fiaz, Hisham Cholakkal
Abstract: Change detection (CD) is a fundamental task in remote sensing (RS) which aims to detect the semantic changes between the same geographical regions at different time stamps. Existing convolutional neural networks (CNNs) based approaches often struggle to capture long-range dependencies. Whereas recent transformer-based methods are prone to the dominant global representation and may limit their capabilities to capture the subtle change regions due to the complexity of the objects in the scene. To address these limitations, we propose an effective Siamese-based framework to encode the semantic changes occurring in the bi-temporal RS images. The main focus of our design is to introduce a change encoder that leverages local and global feature representations to capture both subtle and large change feature information from multi-scale features to precisely estimate the change regions. Our experimental study on two challenging CD datasets reveals the merits of our approach and obtains state-of-the-art performance.
Authors: Shangzhan Zhang, Sida Peng, Tao Xu, Yuanbo Yang, Tianrun Chen, Nan Xue, Yujun Shen, Hujun Bao, Ruizhen Hu, Xiaowei Zhou
Abstract: This paper aims to generate materials for 3D meshes from text descriptions. Unlike existing methods that synthesize texture maps, we propose to generate segment-wise procedural material graphs as the appearance representation, which supports high-quality rendering and provides substantial flexibility in editing. Instead of relying on extensive paired data, i.e., 3D meshes with material graphs and corresponding text descriptions, to train a material graph generative model, we propose to leverage the pre-trained 2D diffusion model as a bridge to connect the text and material graphs. Specifically, our approach decomposes a shape into a set of segments and designs a segment-controlled diffusion model to synthesize 2D images that are aligned with mesh parts. Based on generated images, we initialize parameters of material graphs and fine-tune them through the differentiable rendering module to produce materials in accordance with the textual description. Extensive experiments demonstrate the superior performance of our framework in photorealism, resolution, and editability over existing methods. Project page: https://zhanghe3z.github.io/MaPa/
Authors: Zhengze Xu, Mengting Chen, Zhao Wang, Linyu Xing, Zhonghua Zhai, Nong Sang, Jinsong Lan, Shuai Xiao, Changxin Gao
Abstract: Video try-on is a challenging task and has not been well tackled in previous works. The main obstacle lies in preserving the details of the clothing and modeling the coherent motions simultaneously. Faced with those difficulties, we address video try-on by proposing a diffusion-based framework named "Tunnel Try-on." The core idea is excavating a "focus tunnel" in the input video that gives close-up shots around the clothing regions. We zoom in on the region in the tunnel to better preserve the fine details of the clothing. To generate coherent motions, we first leverage the Kalman filter to construct smooth crops in the focus tunnel and inject the position embedding of the tunnel into attention layers to improve the continuity of the generated videos. In addition, we develop an environment encoder to extract the context information outside the tunnels as supplementary cues. Equipped with these techniques, Tunnel Try-on keeps the fine details of the clothing and synthesizes stable and smooth videos. Demonstrating significant advancements, Tunnel Try-on could be regarded as the first attempt toward the commercial-level application of virtual try-on in videos.
Authors: Shi-Yu Xia, Wenxuan Zhu, Xu Yang, Xin Geng
Abstract: In practice, we usually need to build variable-sized models adapting for diverse resource constraints in different application scenarios, where weight initialization is an important step prior to training. The Learngene framework, introduced recently, firstly learns one compact part termed as learngene from a large well-trained model, after which learngene is expanded to initialize variable-sized models. In this paper, we start from analysing the importance of guidance for the expansion of well-trained learngene layers, inspiring the design of a simple but highly effective Learngene approach termed SWS (Stage-wise Weight Sharing), where both learngene layers and their learning process critically contribute to providing knowledge and guidance for initializing models at varying scales. Specifically, to learn learngene layers, we build an auxiliary model comprising multiple stages where the layer weights in each stage are shared, after which we train it through distillation. Subsequently, we expand these learngene layers containing stage information at their corresponding stage to initialize models of variable depths. Extensive experiments on ImageNet-1K demonstrate that SWS achieves consistent better performance compared to many models trained from scratch, while reducing around 6.6x total training costs. In some cases, SWS performs better only after 1 epoch tuning. When initializing variable-sized models adapting for different resource constraints, SWS achieves better results while reducing around 20x parameters stored to initialize these models and around 10x pre-training costs, in contrast to the pre-training and fine-tuning approach.
Authors: Irfan Mohammad Al Hasib
Abstract: Informative gradients are often lost in large batch updates. We propose a robust mechanism to reinforce the sparse components within a random batch of data points. A finite queue of online gradients is used to determine their expected instantaneous statistics. We propose a function to measure the scarcity of incoming gradients using these statistics and establish the theoretical ground of this mechanism. To minimize conflicting components within large mini-batches, samples are grouped with aligned objectives by clustering based on inherent feature space. Sparsity is measured for each centroid and weighted accordingly. A strong intuitive criterion to squeeze out redundant information from each cluster is the backbone of the system. It makes rare information indifferent to aggressive momentum also exhibits superior performance with larger mini-batch horizon. The effective length of the queue kept variable to follow the local loss pattern. The contribution of our method is to restore intra-mini-batch diversity at the same time widening the optimal batch boundary. Both of these collectively drive it deeper towards the minima. Our method has shown superior performance for CIFAR10, MNIST, and Reuters News category dataset compared to mini-batch gradient descent.
Authors: William Huang, Sam Ghahremani, Siyou Pei, Yang Zhang
Abstract: Existing pose estimation models perform poorly on wheelchair users due to a lack of representation in training data. We present a data synthesis pipeline to address this disparity in data collection and subsequently improve pose estimation performance for wheelchair users. Our configurable pipeline generates synthetic data of wheelchair users using motion capture data and motion generation outputs simulated in the Unity game engine. We validated our pipeline by conducting a human evaluation, investigating perceived realism, diversity, and an AI performance evaluation on a set of synthetic datasets from our pipeline that synthesized different backgrounds, models, and postures. We found our generated datasets were perceived as realistic by human evaluators, had more diversity than existing image datasets, and had improved person detection and pose estimation performance when fine-tuned on existing pose estimation models. Through this work, we hope to create a foothold for future efforts in tackling the inclusiveness of AI in a data-centric and human-centric manner with the data synthesis techniques demonstrated in this work. Finally, for future works to extend upon, we open source all code in this research and provide a fully configurable Unity Environment used to generate our datasets. In the case of any models we are unable to share due to redistribution and licensing policies, we provide detailed instructions on how to source and replace said models.
Authors: Ziliang Hong, Debesh Jha, Koushik Biswas, Zheyuan Zhang, Yury Velichko, Cemal Yazici, Temel Tirkes, Amir Borhani, Baris Turkbey, Alpay Medetalibeyoglu, Gorkem Durak, Ulas Bagci
Abstract: Identifying peri-pancreatic edema is a pivotal indicator for identifying disease progression and prognosis, emphasizing the critical need for accurate detection and assessment in pancreatitis diagnosis and management. This study \textit{introduces a novel CT dataset sourced from 255 patients with pancreatic diseases, featuring annotated pancreas segmentation masks and corresponding diagnostic labels for peri-pancreatic edema condition}. With the novel dataset, we first evaluate the efficacy of the \textit{LinTransUNet} model, a linear Transformer based segmentation algorithm, to segment the pancreas accurately from CT imaging data. Then, we use segmented pancreas regions with two distinctive machine learning classifiers to identify existence of peri-pancreatic edema: deep learning-based models and a radiomics-based eXtreme Gradient Boosting (XGBoost). The LinTransUNet achieved promising results, with a dice coefficient of 80.85\%, and mIoU of 68.73\%. Among the nine benchmarked classification models for peri-pancreatic edema detection, \textit{Swin-Tiny} transformer model demonstrated the highest recall of $98.85 \pm 0.42$ and precision of $98.38\pm 0.17$. Comparatively, the radiomics-based XGBoost model achieved an accuracy of $79.61\pm4.04$ and recall of $91.05\pm3.28$, showcasing its potential as a supplementary diagnostic tool given its rapid processing speed and reduced training time. Our code is available \url{https://github.com/NUBagciLab/Peri-Pancreatic-Edema-Detection}.
URLs: https://github.com/NUBagciLab/Peri-Pancreatic-Edema-Detection
Authors: Deepak Bhatia, Muhammad Abdullah, Anne Querfurth, Mahdi Mantash
Abstract: This paper investigates the use of deep learning approaches to estimate the femur caput-collum-diaphyseal (CCD) angle from X-ray images. The CCD angle is an important measurement in the diagnosis of hip problems, and correct prediction can help in the planning of surgical procedures. Manual measurement of this angle, on the other hand, can be time-intensive and vulnerable to inter-observer variability. In this paper, we present a deep-learning algorithm that can reliably estimate the femur CCD angle from X-ray images. To train and test the performance of our model, we employed an X-ray image dataset with associated femur CCD angle measurements. Furthermore, we built a prototype to display the resulting predictions and to allow the user to interact with the predictions. As this is happening in a sterile setting during surgery, we expanded our interface to the possibility of being used only by voice commands. Our results show that our deep learning model predicts the femur CCD angle on X-ray images with great accuracy, with a mean absolute error of 4.3 degrees on the left femur and 4.9 degrees on the right femur on the test dataset. Our results suggest that deep learning has the potential to give a more efficient and accurate technique for predicting the femur CCD angle, which might have substantial therapeutic implications for the diagnosis and management of hip problems.
Authors: Alice Gao, Samyukta Jayakumar, Marcello Maniglia, Brian Curless, Ira Kemelmacher-Shlizerman, Aaron R. Seitz, Steven M. Seitz
Abstract: We consider the question of how to best achieve the perception of eye contact when a person is captured by camera and then rendered on a 2D display. For single subjects photographed by a camera, conventional wisdom tells us that looking directly into the camera achieves eye contact. Through empirical user studies, we show that it is instead preferable to {\em look just below the camera lens}. We quantitatively assess where subjects should direct their gaze relative to a camera lens to optimize the perception that they are making eye contact.
Authors: Chengpei Xu, Wenjing Jia, Ruomei Wang, Xiaonan Luo, Xiangjian He
Abstract: Bottom-up text detection methods play an important role in arbitrary-shape scene text detection but there are two restrictions preventing them from achieving their great potential, i.e., 1) the accumulation of false text segment detections, which affects subsequent processing, and 2) the difficulty of building reliable connections between text segments. Targeting these two problems, we propose a novel approach, named ``MorphText", to capture the regularity of texts by embedding deep morphology for arbitrary-shape text detection. Towards this end, two deep morphological modules are designed to regularize text segments and determine the linkage between them. First, a Deep Morphological Opening (DMOP) module is constructed to remove false text segment detections generated in the feature extraction process. Then, a Deep Morphological Closing (DMCL) module is proposed to allow text instances of various shapes to stretch their morphology along their most significant orientation while deriving their connections. Extensive experiments conducted on four challenging benchmark datasets (CTW1500, Total-Text, MSRA-TD500 and ICDAR2017) demonstrate that our proposed MorphText outperforms both top-down and bottom-up state-of-the-art arbitrary-shape scene text detection approaches.
Authors: Yawar Ali (Indian Institute of Technology Delhi, New Delhi, India), Krishnan K N (Indian Institute of Technology Delhi, New Delhi, India), Debashis Ray Sarkar (Indian Institute of Technology Delhi, New Delhi, India), K. Ramachandra Rao (Indian Institute of Technology Delhi, New Delhi, India), Niladri Chatterjee (Indian Institute of Technology Delhi, New Delhi, India), Ashish Bhaskar (Queensland University of Technology, Brisbane, Australia)
Abstract: Traffic data collection has been an overwhelming task for researchers as well as authorities over the years. With the advancement in technology and introduction of various tools for processing and extracting traffic data the task has been made significantly convenient. Data from Sky (DFS) is one such tool, based on image processing and artificial intelligence (AI), that provides output for macroscopic as well as microscopic variables of the traffic streams. The company claims to provide 98 to 100 percent accuracy on the data exported using DFS tool. The tool is widely used in developed countries where the traffic is homogenous and has lane-based movements. In this study, authors have checked the veracity of DFS tool in heterogenous and area-based traffic movement that is prevailing in most developing countries. The validation is done using various methods using Classified Volume Count (CVC), Space Mean Speeds (SMS) of individual vehicle classes and microscopic trajectory of probe vehicle to verify DFS claim. The error for CVCs for each vehicle class present in the traffic stream is estimated. Mean Absolute Percentage Error (MAPE) values are calculated for average speeds of each vehicle class between manually and DFS extracted space mean speeds (SMSs), and the microscopic trajectories are validated using a GPS based tracker put on probe vehicles. The results are fairly accurate in the case of data taken from a bird eye view with least errors. The other configurations of data collection have some significant errors, that are majorly caused by the varied traffic composition, the view of camera angle, and the direction of traffic.
Authors: Vincent Ress, Wei Zhang, David Skuddis, Norbert Haala, Uwe Soergel
Abstract: Simultaneous localization and mapping (SLAM), i.e., the reconstruction of the environment represented by a (3D) map and the concurrent pose estimation, has made astonishing progress. Meanwhile, large scale applications aiming at the data collection in complex environments like factory halls or construction sites are becoming feasible. However, in contrast to small scale scenarios with building interiors separated to single rooms, shop floors or construction areas require measures at larger distances in potentially texture less areas under difficult illumination. Pose estimation is further aggravated since no GNSS measures are available as it is usual for such indoor applications. In our work, we realize data collection in a large factory hall by a robot system equipped with four stereo cameras as well as a 3D laser scanner. We apply our state-of-the-art LiDAR and visual SLAM approaches and discuss the respective pros and cons of the different sensor types for trajectory estimation and dense map generation in such an environment. Additionally, dense and accurate depth maps are generated by 3D Gaussian splatting, which we plan to use in the context of our project aiming on the automatic construction and site monitoring.
Authors: Kazi Shahriar Sanjid, Md. Tanzim Hossain, Md. Shakib Shahariar Junayed, M. Monir Uddin
Abstract: Deep learning has revolutionized medical imaging by providing innovative solutions to complex healthcare challenges. Traditional models often struggle to dynamically adjust feature importance, resulting in suboptimal representation, particularly in tasks like semantic segmentation crucial for accurate structure delineation. Moreover, their static nature incurs high computational costs. To tackle these issues, we introduce Mamba-Ahnet, a novel integration of State Space Model (SSM) and Advanced Hierarchical Network (AHNet) within the MAMBA framework, specifically tailored for semantic segmentation in medical imaging.Mamba-Ahnet combines SSM's feature extraction and comprehension with AHNet's attention mechanisms and image reconstruction, aiming to enhance segmentation accuracy and robustness. By dissecting images into patches and refining feature comprehension through self-attention mechanisms, the approach significantly improves feature resolution. Integration of AHNet into the MAMBA framework further enhances segmentation performance by selectively amplifying informative regions and facilitating the learning of rich hierarchical representations. Evaluation on the Universal Lesion Segmentation dataset demonstrates superior performance compared to state-of-the-art techniques, with notable metrics such as a Dice similarity coefficient of approximately 98% and an Intersection over Union of about 83%. These results underscore the potential of our methodology to enhance diagnostic accuracy, treatment planning, and ultimately, patient outcomes in clinical practice. By addressing the limitations of traditional models and leveraging the power of deep learning, our approach represents a significant step forward in advancing medical imaging technology.
Authors: Houtan Ghaffari, Paul Devos
Abstract: Transferring the weights of a pre-trained model to assist another task has become a crucial part of modern deep learning, particularly in data-scarce scenarios. Pre-training refers to the initial step of training models outside the current task of interest, typically on another dataset. It can be done via supervised models using human-annotated datasets or self-supervised models trained on unlabeled datasets. In both cases, many pre-trained models are available to fine-tune for the task of interest. Interestingly, research has shown that pre-trained models from ImageNet can be helpful for audio tasks despite being trained on image datasets. Hence, it's unclear whether in-domain models would be advantageous compared to competent out-domain models, such as convolutional neural networks from ImageNet. Our experiments will demonstrate the usefulness of in-domain models and datasets for bird species recognition by leveraging VICReg, a recent and powerful self-supervised method.
Authors: Pengwei Xie, Rui Chen, Siang Chen, Yuzhe Qin, Fanbo Xiang, Tianyu Sun, Jing Xu, Guijin Wang, Hao Su
Abstract: Manipulating unseen articulated objects through visual feedback is a critical but challenging task for real robots. Existing learning-based solutions mainly focus on visual affordance learning or other pre-trained visual models to guide manipulation policies, which face challenges for novel instances in real-world scenarios. In this paper, we propose a novel part-guided 3D RL framework, which can learn to manipulate articulated objects without demonstrations. We combine the strengths of 2D segmentation and 3D RL to improve the efficiency of RL policy training. To improve the stability of the policy on real robots, we design a Frame-consistent Uncertainty-aware Sampling (FUS) strategy to get a condensed and hierarchical 3D representation. In addition, a single versatile RL policy can be trained on multiple articulated object manipulation tasks simultaneously in simulation and shows great generalizability to novel categories and instances. Experimental results demonstrate the effectiveness of our framework in both simulation and real-world settings. Our code is available at https://github.com/THU-VCLab/Part-Guided-3D-RL-for-Sim2Real-Articulated-Object-Manipulation.
URLs: https://github.com/THU-VCLab/Part-Guided-3D-RL-for-Sim2Real-Articulated-Object-Manipulation.
Authors: Mohamed Roshdi, Julian Petzold, Mostafa Wahby, Hussein Ebrahim, Mladen Berekovic, Heiko Hamann
Abstract: In Autonomous Driving (AD) transparency and safety are paramount, as mistakes are costly. However, neural networks used in AD systems are generally considered black boxes. As a countermeasure, we have methods of explainable AI (XAI), such as feature relevance estimation and dimensionality reduction. Coarse graining techniques can also help reduce dimensionality and find interpretable global patterns. A specific coarse graining method is Renormalization Groups from statistical physics. It has previously been applied to Restricted Boltzmann Machines (RBMs) to interpret unsupervised learning. We refine this technique by building a transparent backbone model for convolutional variational autoencoders (VAE) that allows mapping latent values to input features and has performance comparable to trained black box VAEs. Moreover, we propose a custom feature map visualization technique to analyze the internal convolutional layers in the VAE to explain internal causes of poor reconstruction that may lead to dangerous traffic scenarios in AD applications. In a second key contribution, we propose explanation and evaluation techniques for the internal dynamics and feature relevance of prediction networks. We test a long short-term memory (LSTM) network in the computer vision domain to evaluate the predictability and in future applications potentially safety of prediction models. We showcase our methods by analyzing a VAE-LSTM world model that predicts pedestrian perception in an urban traffic situation.
Authors: Yushen Xu, Xiaosong Li, Yuchan Jie, Haishu Tan
Abstract: In clinical practice, tri-modal medical image fusion, compared to the existing dual-modal technique, can provide a more comprehensive view of the lesions, aiding physicians in evaluating the disease's shape, location, and biological activity. However, due to the limitations of imaging equipment and considerations for patient safety, the quality of medical images is usually limited, leading to sub-optimal fusion performance, and affecting the depth of image analysis by the physician. Thus, there is an urgent need for a technology that can both enhance image resolution and integrate multi-modal information. Although current image processing methods can effectively address image fusion and super-resolution individually, solving both problems synchronously remains extremely challenging. In this paper, we propose TFS-Diff, a simultaneously realize tri-modal medical image fusion and super-resolution model. Specially, TFS-Diff is based on the diffusion model generation of a random iterative denoising process. We also develop a simple objective function and the proposed fusion super-resolution loss, effectively evaluates the uncertainty in the fusion and ensures the stability of the optimization process. And the channel attention module is proposed to effectively integrate key information from different modalities for clinical diagnosis, avoiding information loss caused by multiple image processing. Extensive experiments on public Harvard datasets show that TFS-Diff significantly surpass the existing state-of-the-art methods in both quantitative and visual evaluations. The source code will be available at GitHub.
Authors: Emmanouil Seferis, Stefanos Kollias, Chih-Hong Cheng
Abstract: Randomized smoothing (RS) has successfully been used to improve the robustness of predictions for deep neural networks (DNNs) by adding random noise to create multiple variations of an input, followed by deciding the consensus. To understand if an RS-enabled DNN is effective in the sampled input domains, it is mandatory to sample data points within the operational design domain, acquire the point-wise certificate regarding robustness radius, and compare it with pre-defined acceptance criteria. Consequently, ensuring that a point-wise robustness certificate for any given data point is obtained relatively cost-effectively is crucial. This work demonstrates that reducing the number of samples by one or two orders of magnitude can still enable the computation of a slightly smaller robustness radius (commonly ~20% radius reduction) with the same confidence. We provide the mathematical foundation for explaining the phenomenon while experimentally showing promising results on the standard CIFAR-10 and ImageNet datasets.
Authors: Deborah Pereg
Abstract: Image restoration, or inverse problems in image processing, has long been an extensively studied topic. In recent years supervised learning approaches have become a popular strategy attempting to tackle this task. Unfortunately, most supervised learning-based methods are highly demanding in terms of computational resources and training data (sample complexity). In addition, trained models are sensitive to domain changes, such as varying acquisition systems, signal sampling rates, resolution and contrast. In this work, we try to answer a fundamental question: Can supervised learning models generalize well solely by learning from one image or even part of an image? If so, then what is the minimal amount of patches required to achieve acceptable generalization? To this end, we focus on an efficient patch-based learning framework that requires a single image input-output pair for training. Experimental results demonstrate the applicability, robustness and computational efficiency of the proposed approach for supervised image deblurring and super-resolution. Our results showcase significant improvement of learning models' sample efficiency, generalization and time complexity, that can hopefully be leveraged for future real-time applications, and applied to other signals and modalities.
Authors: Puhao Li, Tengyu Liu, Yuyang Li, Muzhi Han, Haoran Geng, Shu Wang, Yixin Zhu, Song-Chun Zhu, Siyuan Huang
Abstract: Autonomous robotic systems capable of learning novel manipulation tasks are poised to transform industries from manufacturing to service automation. However, modern methods (e.g., VIP and R3M) still face significant hurdles, notably the domain gap among robotic embodiments and the sparsity of successful task executions within specific action spaces, resulting in misaligned and ambiguous task representations. We introduce Ag2Manip (Agent-Agnostic representations for Manipulation), a framework aimed at surmounting these challenges through two key innovations: a novel agent-agnostic visual representation derived from human manipulation videos, with the specifics of embodiments obscured to enhance generalizability; and an agent-agnostic action representation abstracting a robot's kinematics to a universal agent proxy, emphasizing crucial interactions between end-effector and object. Ag2Manip's empirical validation across simulated benchmarks like FrankaKitchen, ManiSkill, and PartManip shows a 325% increase in performance, achieved without domain-specific demonstrations. Ablation studies underline the essential contributions of the visual and action representations to this success. Extending our evaluations to the real world, Ag2Manip significantly improves imitation learning success rates from 50% to 77.5%, demonstrating its effectiveness and generalizability across both simulated and physical environments.
Authors: Xiao Han, Yiming Ren, Peishan Cong, Yujing Sun, Jingya Wang, Lan Xu, Yuexin Ma
Abstract: Human gait recognition is crucial in multimedia, enabling identification through walking patterns without direct interaction, enhancing the integration across various media forms in real-world applications like smart homes, healthcare and non-intrusive security. LiDAR's ability to capture depth makes it pivotal for robotic perception and holds promise for real-world gait recognition. In this paper, based on a single LiDAR, we present the Hierarchical Multi-representation Feature Interaction Network (HMRNet) for robust gait recognition. Prevailing LiDAR-based gait datasets primarily derive from controlled settings with predefined trajectory, remaining a gap with real-world scenarios. To facilitate LiDAR-based gait recognition research, we introduce FreeGait, a comprehensive gait dataset from large-scale, unconstrained settings, enriched with multi-modal and varied 2D/3D data. Notably, our approach achieves state-of-the-art performance on prior dataset (SUSTech1K) and on FreeGait. Code and dataset will be released upon publication of this paper.
Authors: Ling Xiao, Toshihiko Yamasaki
Abstract: Fine-grained fashion retrieval searches for items that share a similar attribute with the query image. Most existing methods use a pre-trained feature extractor (e.g., ResNet 50) to capture image representations. However, a pre-trained feature backbone is typically trained for image classification and object detection, which are fundamentally different tasks from fine-grained fashion retrieval. Therefore, existing methods suffer from a feature gap problem when directly using the pre-trained backbone for fine-tuning. To solve this problem, we introduce an attribute-guided multi-level attention network (AG-MAN). Specifically, we first enhance the pre-trained feature extractor to capture multi-level image embedding, thereby enriching the low-level features within these representations. Then, we propose a classification scheme where images with the same attribute, albeit with different values, are categorized into the same class. This can further alleviate the feature gap problem by perturbing object-centric feature learning. Moreover, we propose an improved attribute-guided attention module for extracting more accurate attribute-specific representations. Our model consistently outperforms existing attention based methods when assessed on the FashionAI (62.8788% in MAP), DeepFashion (8.9804% in MAP), and Zappos50k datasets (93.32% in Prediction accuracy). Especially, ours improves the most typical ASENet_V2 model by 2.12%, 0.31%, and 0.78% points in FashionAI, DeepFashion, and Zappos50k datasets, respectively. The source code is available in https://github.com/Dr-LingXiao/AG-MAN.
Authors: Milad Moradi, Ke Yan, David Colwell, Matthias Samwald, Rhona Asgari
Abstract: In recent years, deep neural networks have been widely used for building high-performance Artificial Intelligence (AI) systems for computer vision applications. Object detection is a fundamental task in computer vision, which has been greatly progressed through developing large and intricate deep learning models. However, the lack of transparency is a big challenge that may not allow the widespread adoption of these models. Explainable artificial intelligence is a field of research where methods are developed to help users understand the behavior, decision logics, and vulnerabilities of AI systems. Previously, few explanation methods were developed for object detection, based on the idea of random masks. However, random masks may raise some issues regarding the actual importance of pixels within an image. In this paper, we design and implement a black-box explanation method named Black-box Object Detection Explanation by Masking (BODEM) through adopting a hierarchical random masking approach for AI-based object detection systems. We propose a hierarchical random masking framework in which coarse-grained masks are used in lower levels to find salient regions within an image, and fine-grained mask are used to refine the salient regions in higher levels. Experimentations on various object detection datasets and models showed that BODEM can be effectively used to explain the behavior of object detectors. Moreover, our method outperformed Detector Randomized Input Sampling for Explanation (D-RISE) with respect to different quantitative measures of explanation effectiveness. The experimental results demonstrate that BODEM can be an effective method for explaining and validating object detection systems in black-box testing scenarios.
Authors: Madeline Schiappa, Raiyaan Abdullah, Shehreen Azad, Jared Claypoole, Michael Cogswell, Ajay Divakaran, Yogesh Rawat
Abstract: In recent years large visual-language (V+L) models have achieved great success in various downstream tasks. However, it is not well studied whether these models have a conceptual grasp of the visual content. In this work we focus on conceptual understanding of these large V+L models. To facilitate this study, we propose novel benchmarking datasets for probing three different aspects of content understanding, 1) \textit{relations}, 2) \textit{composition}, and 3) \textit{context}. Our probes are grounded in cognitive science and help determine if a V+L model can, for example, determine if snow garnished with a man is implausible, or if it can identify beach furniture by knowing it is located on a beach. We experimented with many recent state-of-the-art V+L models and observe that these models mostly \textit{fail to demonstrate} a conceptual understanding. This study reveals several interesting insights such as that \textit{cross-attention} helps learning conceptual understanding, and that CNNs are better with \textit{texture and patterns}, while Transformers are better at \textit{color and shape}. We further utilize some of these insights and investigate a \textit{simple finetuning technique} that rewards the three conceptual understanding measures with promising initial results. The proposed benchmarks will drive the community to delve deeper into conceptual understanding and foster advancements in the capabilities of large V+L models. The code and dataset is available at: \url{https://tinyurl.com/vlm-robustness}
Authors: Erh-Chung Chen, Pin-Yu Chen, I-Hsin Chung, Che-rung Lee
Abstract: Nowadays, the deployment of deep learning-based applications is an essential task owing to the increasing demands on intelligent services. In this paper, we investigate latency attacks on deep learning applications. Unlike common adversarial attacks for misclassification, the goal of latency attacks is to increase the inference time, which may stop applications from responding to the requests within a reasonable time. This kind of attack is ubiquitous for various applications, and we use object detection to demonstrate how such kind of attacks work. We also design a framework named Overload to generate latency attacks at scale. Our method is based on a newly formulated optimization problem and a novel technique, called spatial attention. This attack serves to escalate the required computing costs during the inference time, consequently leading to an extended inference time for object detection. It presents a significant threat, especially to systems with limited computing resources. We conducted experiments using YOLOv5 models on Nvidia NX. Compared to existing methods, our method is simpler and more effective. The experimental results show that with latency attacks, the inference time of a single image can be increased ten times longer in reference to the normal setting. Moreover, our findings pose a potential new threat to all object detection tasks requiring non-maximum suppression (NMS), as our attack is NMS-agnostic.
Authors: Le Xue, Ning Yu, Shu Zhang, Artemis Panagopoulou, Junnan Li, Roberto Mart\'in-Mart\'in, Jiajun Wu, Caiming Xiong, Ran Xu, Juan Carlos Niebles, Silvio Savarese
Abstract: Recent advancements in multimodal pre-training have shown promising efficacy in 3D representation learning by aligning multimodal features across 3D shapes, their 2D counterparts, and language descriptions. However, the methods used by existing frameworks to curate such multimodal data, in particular language descriptions for 3D shapes, are not scalable, and the collected language descriptions are not diverse. To address this, we introduce ULIP-2, a simple yet effective tri-modal pre-training framework that leverages large multimodal models to automatically generate holistic language descriptions for 3D shapes. It only needs 3D data as input, eliminating the need for any manual 3D annotations, and is therefore scalable to large datasets. ULIP-2 is also equipped with scaled-up backbones for better multimodal representation learning. We conduct experiments on two large-scale 3D datasets, Objaverse and ShapeNet, and augment them with tri-modal datasets of 3D point clouds, images, and language for training ULIP-2. Experiments show that ULIP-2 demonstrates substantial benefits in three downstream tasks: zero-shot 3D classification, standard 3D classification with fine-tuning, and 3D captioning (3D-to-language generation). It achieves a new SOTA of 50.6% (top-1) on Objaverse-LVIS and 84.7% (top-1) on ModelNet40 in zero-shot classification. In the ScanObjectNN benchmark for standard fine-tuning, ULIP-2 reaches an overall accuracy of 91.5% with a compact model of only 1.4 million parameters. ULIP-2 sheds light on a new paradigm for scalable multimodal 3D representation learning without human annotations and shows significant improvements over existing baselines. The code and datasets are released at https://github.com/salesforce/ULIP.
Authors: Xiaofeng Liu, Jiaxin Gao, Xin Fan, Risheng Liu
Abstract: Contemporary Low-Light Image Enhancement (LLIE) techniques have made notable advancements in preserving image details and enhancing contrast, achieving commendable results on specific datasets. Nevertheless, these approaches encounter persistent challenges in efficiently mitigating dynamic noise and accommodating diverse low-light scenarios. Insufficient constraints on complex pixel-wise mapping learning lead to overfitting to specific types of noise and artifacts associated with low-light conditions, reducing effectiveness in variable lighting scenarios. To this end, we first propose a method for estimating the noise level in low light images in a quick and accurate way. This facilitates precise denoising, prevents over-smoothing, and adapts to dynamic noise patterns. Subsequently, we devise a Learnable Illumination Interpolator (LII), which employs learnlable interpolation operations between the input and unit vector to satisfy general constraints between illumination and input. Finally, we introduce a self-regularization loss that incorporates intrinsic image properties and essential visual attributes to guide the output towards meeting human visual expectations. Comprehensive experiments validate the competitiveness of our proposed algorithm in both qualitative and quantitative assessments. Notably, our noise estimation method, with linear time complexity and suitable for various denoisers, significantly improves both denoising and enhancement performance. Benefiting from this, our approach achieves a 0.675dB PSNR improvement on the LOL dataset and 0.818dB on the MIT dataset on LLIE task, even compared to supervised methods.
Authors: Tianzhe Chu, Shengbang Tong, Tianjiao Ding, Xili Dai, Benjamin David Haeffele, Ren\'e Vidal, Yi Ma
Abstract: The advent of large pre-trained models has brought about a paradigm shift in both visual representation learning and natural language processing. However, clustering unlabeled images, as a fundamental and classic machine learning problem, still lacks an effective solution, particularly for large-scale datasets. In this paper, we propose a novel image clustering pipeline that leverages the powerful feature representation of large pre-trained models such as CLIP and cluster images effectively and efficiently at scale. We first developed a novel algorithm to estimate the number of clusters in a given dataset. We then show that the pre-trained features are significantly more structured by further optimizing the rate reduction objective. The resulting features may significantly improve the clustering accuracy, e.g., from 57\% to 66\% on ImageNet-1k. Furthermore, by leveraging CLIP's multimodality bridge between image and text, we develop a simple yet effective self-labeling algorithm that produces meaningful captions for the clusters. Through extensive experiments, we show that our pipeline works well on standard datasets such as CIFAR-10, CIFAR-100, and ImageNet-1k. It also extends to datasets that are not curated for clustering, such as LAION-Aesthetics and WikiArts. We released the code in https://github.com/LeslieTrue/CPP.
Authors: Fuxiao Liu, Hao Tan, Chris Tensmeyer
Abstract: Vision-language pretraining models have achieved great success in supporting multimedia applications by understanding the alignments between images and text. While existing vision-language pretraining models primarily focus on understanding single image associated with a single piece of text, they often ignore the alignment at the intra-document level, consisting of multiple sentences with multiple images. In this work, we propose DocumentCLIP, a salience-aware contrastive learning framework to enforce vision-language pretraining models to comprehend the interaction between images and longer text within documents. Our model is beneficial for the real-world multimodal document understanding like news article, magazines, product descriptions, which contain linguistically and visually richer content. To the best of our knowledge, we are the first to explore multimodal intra-document links by contrastive learning. In addition, we collect a large Wikipedia dataset for pretraining, which provides various topics and structures. Experiments show DocumentCLIP not only outperforms the state-of-the-art baselines in the supervised setting, but also achieves the best zero-shot performance in the wild after human evaluation. Our code is available at https://github.com/FuxiaoLiu/DocumentCLIP.
Authors: Syed Waleed Hyder, Muhammad Usama, Anas Zafar, Muhammad Naufil, Fawad Javed Fateh, Andrey Konin, M. Zeeshan Zia, Quoc-Huy Tran
Abstract: This paper presents a 2D skeleton-based action segmentation method with applications in fine-grained human activity recognition. In contrast with state-of-the-art methods which directly take sequences of 3D skeleton coordinates as inputs and apply Graph Convolutional Networks (GCNs) for spatiotemporal feature learning, our main idea is to use sequences of 2D skeleton heatmaps as inputs and employ Temporal Convolutional Networks (TCNs) to extract spatiotemporal features. Despite lacking 3D information, our approach yields comparable/superior performances and better robustness against missing keypoints than previous methods on action segmentation datasets. Moreover, we improve the performances further by using both 2D skeleton heatmaps and RGB videos as inputs. To our best knowledge, this is the first work to utilize 2D skeleton heatmap inputs and the first work to explore 2D skeleton+RGB fusion for action segmentation.
Authors: Roberto Daza, Aythami Morales, Julian Fierrez, Ruben Tolosana, Ruben Vera-Rodriguez
Abstract: This work introduces a new multispectral database and novel approaches for eyeblink detection in RGB and Near-Infrared (NIR) individual images. Our contributed dataset (mEBAL2, multimodal Eye Blink and Attention Level estimation, Version 2) is the largest existing eyeblink database, representing a great opportunity to improve data-driven multispectral approaches for blink detection and related applications (e.g., attention level estimation and presentation attack detection in face biometrics). mEBAL2 includes 21,100 image sequences from 180 different students (more than 2 million labeled images in total) while conducting a number of e-learning tasks of varying difficulty or taking a real course on HTML initiation through the edX MOOC platform. mEBAL2 uses multiple sensors, including two Near-Infrared (NIR) and one RGB camera to capture facial gestures during the execution of the tasks, as well as an Electroencephalogram (EEG) band to get the cognitive activity of the user and blinking events. Furthermore, this work proposes a Convolutional Neural Network architecture as benchmark for blink detection on mEBAL2 with performances up to 97%. Different training methodologies are implemented using the RGB spectrum, NIR spectrum, and the combination of both to enhance the performance on existing eyeblink detectors. We demonstrate that combining NIR and RGB images during training improves the performance of RGB eyeblink detectors (i.e., detection based only on a RGB image). Finally, the generalization capacity of the proposed eyeblink detectors is validated in wilder and more challenging environments like the HUST-LEBW dataset to show the usefulness of mEBAL2 to train a new generation of data-driven approaches for eyeblink detection.
Authors: Risto Ojala, Alvari Sepp\"anen
Abstract: Winter conditions pose several challenges for automated driving applications. A key challenge during winter is accurate assessment of road surface condition, as its impact on friction is a critical parameter for safely and reliably controlling a vehicle. This paper proposes a deep learning regression model, SIWNet, capable of estimating road surface friction properties from camera images. SIWNet extends state of the art by including an uncertainty estimation mechanism in the architecture. This is achieved by including an additional head in the network, which estimates a prediction interval. The prediction interval head is trained with a maximum likelihood loss function. The model was trained and tested with the SeeingThroughFog dataset, which features corresponding road friction sensor readings and images from an instrumented vehicle. Acquired results highlight the functionality of the prediction interval estimation of SIWNet, while the network also achieved similar point estimate accuracy as the previous state of the art. Furthermore, the SIWNet architecture is several times more lightweight than the previously applied state-of-the-art model, resulting in more practical and efficient deployment.
Authors: Xichen Pan, Li Dong, Shaohan Huang, Zhiliang Peng, Wenhu Chen, Furu Wei
Abstract: Recent advancements in subject-driven image generation have made significant strides. However, current methods still fall short in diverse application scenarios, as they require test-time tuning and cannot accept interleaved multi-image and text input. These limitations keep them far from the ultimate goal of "image as a foreign language in image generation." This paper presents Kosmos-G, a model that leverages the advanced multimodal perception capabilities of Multimodal Large Language Models (MLLMs) to tackle the aforementioned challenge. Our approach aligns the output space of MLLM with CLIP using the textual modality as an anchor and performs compositional instruction tuning on curated data. Kosmos-G demonstrates an impressive capability of zero-shot subject-driven generation with interleaved multi-image and text input. Notably, the score distillation instruction tuning requires no modifications to the image decoder. This allows for a seamless substitution of CLIP and effortless integration with a myriad of U-Net techniques ranging from fine-grained controls to personalized image decoder variants. We posit Kosmos-G as an initial attempt towards the goal of "image as a foreign language in image generation." The code can be found at https://aka.ms/Kosmos-G
URLs: https://aka.ms/Kosmos-G
Authors: Nataliia Molchanova, Vatsal Raina, Andrey Malinin, Francesco La Rosa, Adrien Depeursinge, Mark Gales, Cristina Granziera, Henning Muller, Mara Graziani, Meritxell Bach Cuadra
Abstract: This paper explores uncertainty quantification (UQ) as an indicator of the trustworthiness of automated deep-learning (DL) tools in the context of white matter lesion (WML) segmentation from magnetic resonance imaging (MRI) scans of multiple sclerosis (MS) patients. Our study focuses on two principal aspects of uncertainty in structured output segmentation tasks. Firstly, we postulate that a good uncertainty measure should indicate predictions likely to be incorrect with high uncertainty values. Second, we investigate the merit of quantifying uncertainty at different anatomical scales (voxel, lesion, or patient). We hypothesize that uncertainty at each scale is related to specific types of errors. Our study aims to confirm this relationship by conducting separate analyses for in-domain and out-of-domain settings. Our primary methodological contributions are (i) the development of novel measures for quantifying uncertainty at lesion and patient scales, derived from structural prediction discrepancies, and (ii) the extension of an error retention curve analysis framework to facilitate the evaluation of UQ performance at both lesion and patient scales. The results from a multi-centric MRI dataset of 334 patients demonstrate that our proposed measures more effectively capture model errors at the lesion and patient scales compared to measures that average voxel-scale uncertainty values. We provide the UQ protocols code at https://github.com/Medical-Image-Analysis-Laboratory/MS_WML_uncs.
URLs: https://github.com/Medical-Image-Analysis-Laboratory/MS_WML_uncs.
Authors: Tony Lindeberg
Abstract: The influence of natural image transformations on receptive field responses is crucial for modelling visual operations in computer vision and biological vision. In this regard, covariance properties with respect to geometric image transformations in the earliest layers of the visual hierarchy are essential for expressing robust image operations, and for formulating invariant visual operations at higher levels. This paper defines and proves a set of joint covariance properties under compositions of spatial scaling transformations, spatial affine transformations, Galilean transformations and temporal scaling transformations, which make it possible to characterize how different types of image transformations interact with each other and the associated spatio-temporal receptive field responses. In this regard, we also extend the notion of scale-normalized derivatives to affine-normalized derivatives, to be able to obtain true affine-covariant properties of spatial derivatives, that are computed based on spatial smoothing with affine Gaussian kernels. The derived relations show how the parameters of the receptive fields need to be transformed, in order to match the output from spatio-temporal receptive fields under composed spatio-temporal image transformations. As a side effect, the presented proof for the joint covariance property over the integrated combination of the different geometric image transformations also provides specific proofs for the individual transformation properties, which have not previously been fully reported in the literature. The paper also presents an in-depth theoretical analysis of geometric interpretations of the derived covariance properties, as well as outlines a number of biological interpretations of these results.
Authors: Ayush Kumar Shah, Bryan Manrique Amador, Abhisek Dey, Ming Creekmore, Blake Ocampo, Scott Denmark, Richard Zanibbi
Abstract: Most molecular diagram parsers recover chemical structure from raster images (e.g., PNGs). However, many PDFs include commands giving explicit locations and shapes for characters, lines, and polygons. We present a new parser that uses these born-digital PDF primitives as input. The parsing model is fast and accurate, and does not require GPUs, Optical Character Recognition (OCR), or vectorization. We use the parser to annotate raster images and then train a new multi-task neural network for recognizing molecules in raster images. We evaluate our parsers using SMILES and standard benchmarks, along with a novel evaluation protocol comparing molecular graphs directly that supports automatic error compilation and reveals errors missed by SMILES-based evaluation.
Authors: Xiaoyu Yang, Lijian Xu, Hao Sun, Hongsheng Li, Shaoting Zhang
Abstract: Visual grounding (VG) occupies a pivotal position in multi-modality vision-language models. In this study, we propose ViLaM, a large multi-modality model, that supports multi-tasks of VG using the cycle training strategy, with abundant interaction instructions. The cycle training between referring expression generation (REG) and referring expression comprehension (REC) is introduced. It enhances the consistency between visual location and referring expressions, and addresses the need for high-quality, multi-tasks VG datasets. Moreover, multi-tasks of VG are promoted in our model, contributed by the cycle training strategy. The multi-tasks in REC encompass a range of granularities, from region-level to pixel-level, which include referring bbox detection, referring keypoints detection, and referring image segmentation. In REG, referring region classification determines the fine-grained category of the target, while referring region captioning generates a comprehensive description. Meanwhile, all tasks participate in the joint training, synergistically enhancing one another and collectively improving the overall performance of the model. Furthermore, leveraging the capabilities of large language models, ViLaM extends a wide range of instructions, thereby significantly enhancing its generalization and interaction potentials. Extensive public datasets corroborate the superior capabilities of our model in VG with muti-tasks. Additionally, validating its robust generalization, ViLaM is validated under open-set and few-shot scenarios. Especially in the medical field, our model demonstrates cross-domain robust generalization capabilities. Furthermore, we contribute a VG dataset, especially with multi-tasks. To support and encourage the community focused on VG, we have made both the dataset and our code public: https://github.com/AnonymGiant/ViLaM.
Authors: Zhiqin Chen, Qimin Chen, Hang Zhou, Hao Zhang
Abstract: We present an unsupervised 3D shape co-segmentation method which learns a set of deformable part templates from a shape collection. To accommodate structural variations in the collection, our network composes each shape by a selected subset of template parts which are affine-transformed. To maximize the expressive power of the part templates, we introduce a per-part deformation network to enable the modeling of diverse parts with substantial geometry variations, while imposing constraints on the deformation capacity to ensure fidelity to the originally represented parts. We also propose a training scheme to effectively overcome local minima. Architecturally, our network is a branched autoencoder, with a CNN encoder taking a voxel shape as input and producing per-part transformation matrices, latent codes, and part existence scores, and the decoder outputting point occupancies to define the reconstruction loss. Our network, coined DAE-Net for Deforming Auto-Encoder, can achieve unsupervised 3D shape co-segmentation that yields fine-grained, compact, and meaningful parts that are consistent across diverse shapes. We conduct extensive experiments on the ShapeNet Part dataset, DFAUST, and an animal subset of Objaverse to show superior performance over prior methods. Code and data are available at https://github.com/czq142857/DAE-Net.
Authors: Jianhao Zeng, Dan Song, Weizhi Nie, Hongshuo Tian, Tongtong Wang, Anan Liu
Abstract: Generative Adversarial Networks (GANs) dominate the research field in image-based virtual try-on, but have not resolved problems such as unnatural deformation of garments and the blurry generation quality. While the generative quality of diffusion models is impressive, achieving controllability poses a significant challenge when applying it to virtual try-on and multiple denoising iterations limit its potential for real-time applications. In this paper, we propose Controllable Accelerated virtual Try-on with Diffusion Model (CAT-DM). To enhance the controllability, a basic diffusion-based virtual try-on network is designed, which utilizes ControlNet to introduce additional control conditions and improves the feature extraction of garment images. In terms of acceleration, CAT-DM initiates a reverse denoising process with an implicit distribution generated by a pre-trained GAN-based model. Compared with previous try-on methods based on diffusion models, CAT-DM not only retains the pattern and texture details of the inshop garment but also reduces the sampling steps without compromising generation quality. Extensive experiments demonstrate the superiority of CAT-DM against both GANbased and diffusion-based methods in producing more realistic images and accurately reproducing garment patterns.
Authors: Gabriel della Maggiora, Luis Alberto Croquevielle, Nikita Deshpande, Harry Horsley, Thomas Heinis, Artur Yakimovich
Abstract: Inverse problems aim to determine parameters from observations, a crucial task in engineering and science. Lately, generative models, especially diffusion models, have gained popularity in this area for their ability to produce realistic solutions and their good mathematical properties. Despite their success, an important drawback of diffusion models is their sensitivity to the choice of variance schedule, which controls the dynamics of the diffusion process. Fine-tuning this schedule for specific applications is crucial but time-costly and does not guarantee an optimal result. We propose a novel approach for learning the schedule as part of the training process. Our method supports probabilistic conditioning on data, provides high-quality solutions, and is flexible, proving able to adapt to different applications with minimum overhead. This approach is tested in two unrelated inverse problems: super-resolution microscopy and quantitative phase imaging, yielding comparable or superior results to previous methods and fine-tuned diffusion models. We conclude that fine-tuning the schedule by experimentation should be avoided because it can be learned during training in a stable way that yields better results.
Authors: Shufan Li, Harkanwar Singh, Aditya Grover
Abstract: The ability to provide fine-grained control for generating and editing visual imagery has profound implications for computer vision and its applications. Previous works have explored extending controllability in two directions: instruction tuning with text-based prompts and multi-modal conditioning. However, these works make one or more unnatural assumptions on the number and/or type of modality inputs used to express controllability. We propose InstructAny2Pix, a flexible multi-modal instruction-following system that enables users to edit an input image using instructions involving audio, images, and text. InstructAny2Pix consists of three building blocks that facilitate this capability: a multi-modal encoder that encodes different modalities such as images and audio into a unified latent space, a diffusion model that learns to decode representations in this latent space into images, and a multi-modal LLM that can understand instructions involving multiple images and audio pieces and generate a conditional embedding of the desired output, which can be used by the diffusion decoder. Additionally, to facilitate training efficiency and improve generation quality, we include an additional refinement prior module that enhances the visual quality of LLM outputs. These designs are critical to the performance of our system. We demonstrate that our system can perform a series of novel instruction-guided editing tasks. The code is available at https://github.com/jacklishufan/InstructAny2Pix.git
Authors: Mosam Dabhi, Laszlo A. Jeni, Simon Lucey
Abstract: The lifting of 3D structure and camera from 2D landmarks is at the cornerstone of the entire discipline of computer vision. Traditional methods have been confined to specific rigid objects, such as those in Perspective-n-Point (PnP) problems, but deep learning has expanded our capability to reconstruct a wide range of object classes (e.g. C3DPO and PAUL) with resilience to noise, occlusions, and perspective distortions. All these techniques, however, have been limited by the fundamental need to establish correspondences across the 3D training data -- significantly limiting their utility to applications where one has an abundance of "in-correspondence" 3D data. Our approach harnesses the inherent permutation equivariance of transformers to manage varying number of points per 3D data instance, withstands occlusions, and generalizes to unseen categories. We demonstrate state of the art performance across 2D-3D lifting task benchmarks. Since our approach can be trained across such a broad class of structures we refer to it simply as a 3D Lifting Foundation Model (3D-LFM) -- the first of its kind.
Authors: Liman Wang, Hanyang Zhong
Abstract: Inspired by human driving focus, this research pioneers networks augmented with Focusing Sampling, Partial Field of View Evaluation, Enhanced FPN architecture and Directional IoU Loss - targeted innovations addressing obstacles to precise lane detection for autonomous driving. Experiments demonstrate our Focusing Sampling strategy, emphasizing vital distant details unlike uniform approaches, significantly boosts both benchmark and practical curved/distant lane recognition accuracy essential for safety. While FENetV1 achieves state-of-the-art conventional metric performance via enhancements isolating perspective-aware contexts mimicking driver vision, FENetV2 proves most reliable on the proposed Partial Field analysis. Hence we specifically recommend V2 for practical lane navigation despite fractional degradation on standard entire-image measures. Future directions include collecting on-road data and integrating complementary dual frameworks to further breakthroughs guided by human perception principles. The Code is available at https://github.com/HanyangZhong/FENet.
Authors: Jun Wang, Hao Ruan, Mingjie Wang, Chuanghui Zhang, Huachun Li, Jun Zhou
Abstract: Over the past decade, visual gaze estimation has garnered increasing attention within the research community, owing to its wide-ranging application scenarios. While existing estimation approaches have achieved remarkable success in enhancing prediction accuracy, they primarily infer gaze from single-image signals, neglecting the potential benefits of the currently dominant text guidance. Notably, visual-language collaboration has been extensively explored across various visual tasks, such as image synthesis and manipulation, leveraging the remarkable transferability of large-scale Contrastive Language-Image Pre-training (CLIP) model. Nevertheless, existing gaze estimation approaches overlook the rich semantic cues conveyed by linguistic signals and the priors embedded in CLIP feature space, thereby yielding performance setbacks. To address this gap, we delve deeply into the text-eye collaboration protocol and introduce a novel gaze estimation framework, named GazeCLIP. Specifically, we intricately design a linguistic description generator to produce text signals with coarse directional cues. Additionally, a CLIP-based backbone that excels in characterizing text-eye pairs for gaze estimation is presented. This is followed by the implementation of a fine-grained multi-modal fusion module aimed at modeling the interrelationships between heterogeneous inputs. Extensive experiments on three challenging datasets demonstrate the superiority of the proposed GazeCLIP which achieves the state-of-the-art accuracy.
Authors: Pablo Martin-Ramiro, Unai Sainz de la Maza, Sukhbinder Singh, Roman Orus, Samuel Mugel
Abstract: Defect detection is one of the most important yet challenging tasks in the quality control stage in the manufacturing sector. In this work, we introduce a Tensor Convolutional Neural Network (T-CNN) and examine its performance on a real defect detection application in one of the components of the ultrasonic sensors produced at Robert Bosch's manufacturing plants. Our quantum-inspired T-CNN operates on a reduced model parameter space to substantially improve the training speed and performance of an equivalent CNN model without sacrificing accuracy. More specifically, we demonstrate how T-CNNs are able to reach the same performance as classical CNNs as measured by quality metrics, with up to fifteen times fewer parameters and 4% to 19% faster training times. Our results demonstrate that the T-CNN greatly outperforms the results of traditional human visual inspection, providing value in a current real application in manufacturing.
Authors: Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley, Gabriel Sarch, Kriti Aggarwal, Vishrav Chaudhary, Katerina Fragkiadaki
Abstract: State-of-the-art models on contemporary 3D segmentation benchmarks like ScanNet consume and label dataset-provided 3D point clouds, obtained through post processing of sensed multiview RGB-D images. They are typically trained in-domain, forego large-scale 2D pre-training and outperform alternatives that featurize the posed RGB-D multiview images instead. The gap in performance between methods that consume posed images versus post-processed 3D point clouds has fueled the belief that 2D and 3D perception require distinct model architectures. In this paper, we challenge this view and propose ODIN (Omni-Dimensional INstance segmentation), a model that can segment and label both 2D RGB images and 3D point clouds, using a transformer architecture that alternates between 2D within-view and 3D cross-view information fusion. Our model differentiates 2D and 3D feature operations through the positional encodings of the tokens involved, which capture pixel coordinates for 2D patch tokens and 3D coordinates for 3D feature tokens. ODIN achieves state-of-the-art performance on ScanNet200, Matterport3D and AI2THOR 3D instance segmentation benchmarks, and competitive performance on ScanNet, S3DIS and COCO. It outperforms all previous works by a wide margin when the sensed 3D point cloud is used in place of the point cloud sampled from 3D mesh. When used as the 3D perception engine in an instructable embodied agent architecture, it sets a new state-of-the-art on the TEACh action-from-dialogue benchmark. Our code and checkpoints can be found at the project website (https://odin-seg.github.io).
Authors: Chenxi Yang, Yujia Liu, Dingquan Li, Tingting Jiang
Abstract: No-Reference Image Quality Assessment (NR-IQA) aims to predict image quality scores consistent with human perception without relying on pristine reference images, serving as a crucial component in various visual tasks. Ensuring the robustness of NR-IQA methods is vital for reliable comparisons of different image processing techniques and consistent user experiences in recommendations. The attack methods for NR-IQA provide a powerful instrument to test the robustness of NR-IQA. However, current attack methods of NR-IQA heavily rely on the gradient of the NR-IQA model, leading to limitations when the gradient information is unavailable. In this paper, we present a pioneering query-based black box attack against NR-IQA methods. We propose the concept of score boundary and leverage an adaptive iterative approach with multiple score boundaries. Meanwhile, the initial attack directions are also designed to leverage the characteristics of the Human Visual System (HVS). Experiments show our method outperforms all compared state-of-the-art attack methods and is far ahead of previous black-box methods. The effective NR-IQA model DBCNN suffers a Spearman's rank-order correlation coefficient (SROCC) decline of 0.6381 attacked by our method, revealing the vulnerability of NR-IQA models to black-box attacks. The proposed attack method also provides a potent tool for further exploration into NR-IQA robustness.
Authors: Haibo Wang, Chenghang Lai, Yixuan Sun, Weifeng Ge
Abstract: Video Question Answering (VideoQA) aims to answer natural language questions based on the information observed in videos. Despite the recent success of Large Multimodal Models (LMMs) in image-language understanding and reasoning, they deal with VideoQA insufficiently, by simply taking uniformly sampled frames as visual inputs, which ignores question-relevant visual clues. Moreover, there are no human annotations for question-critical timestamps in existing VideoQA datasets. In light of this, we propose a novel weakly supervised framework to enforce the LMMs to reason out the answers with question-critical moments as visual inputs. Specifically, we first fuse the question and answer pairs as event descriptions to find multiple keyframes as target moments and pseudo-labels, with the visual-language alignment capability of the CLIP models. With these pseudo-labeled keyframes as additionally weak supervision, we devise a lightweight Gaussian-based Contrastive Grounding (GCG) module. GCG learns multiple Gaussian functions to characterize the temporal structure of the video, and sample question-critical frames as positive moments to be the visual inputs of LMMs. Extensive experiments on several benchmarks verify the effectiveness of our framework, and we achieve substantial improvements compared to previous state-of-the-art methods.
Authors: Eric Peh, Paritosh Parmar, Basura Fernando
Abstract: In this work, we introduce the novel concept of visually Connecting Actions and Their Effects (CATE) in video understanding. CATE can have applications in areas like task planning and learning from demonstration. We identify and explore two different aspects of the concept of CATE: Action Selection and Effect-Affinity Assessment, where video understanding models connect actions and effects at semantic and fine-grained levels, respectively. We observe that different formulations produce representations capturing intuitive action properties. We also design various baseline models for Action Selection and Effect-Affinity Assessment. Despite the intuitive nature of the task, we observe that models struggle, and humans outperform them by a large margin. The study aims to establish a foundation for future efforts, showcasing the flexibility and versatility of connecting actions and effects in video understanding, with the hope of inspiring advanced formulations and models.
Authors: Mike Laszkiewicz, Imant Daunhawer, Julia E. Vogt, Asja Fischer, Johannes Lederer
Abstract: Recent years have witnessed a rapid development of deep generative models for creating synthetic media, such as images and videos. While the practical applications of these models in everyday tasks are enticing, it is crucial to assess the inherent risks regarding their fairness. In this work, we introduce a comprehensive framework for benchmarking the performance and fairness of conditional generative models. We develop a set of metrics$\unicode{x2013}$inspired by their supervised fairness counterparts$\unicode{x2013}$to evaluate the models on their fairness and diversity. Focusing on the specific application of image upsampling, we create a benchmark covering a wide variety of modern upsampling methods. As part of the benchmark, we introduce UnfairFace, a subset of FairFace that replicates the racial distribution of common large-scale face datasets. Our empirical study highlights the importance of using an unbiased training set and reveals variations in how the algorithms respond to dataset imbalances. Alarmingly, we find that none of the considered methods produces statistically fair and diverse results. All experiments can be reproduced using our provided repository.
Authors: Diandian Guo, Deng-Ping Fan, Tongyu Lu, Christos Sakaridis, Luc Van Gool
Abstract: The estimation of implicit cross-frame correspondences and the high computational cost have long been major challenges in video semantic segmentation (VSS) for driving scenes. Prior works utilize keyframes, feature propagation, or cross-frame attention to address these issues. By contrast, we are the first to harness vanishing point (VP) priors for more effective segmentation. Intuitively, objects near VPs (i.e., away from the vehicle) are less discernible. Moreover, they tend to move radially away from the VP over time in the usual case of a forward-facing camera, a straight road, and linear forward motion of the vehicle. Our novel, efficient network for VSS, named VPSeg, incorporates two modules that utilize exactly this pair of static and dynamic VP priors: sparse-to-dense feature mining (DenseVP) and VP-guided motion fusion (MotionVP). MotionVP employs VP-guided motion estimation to establish explicit correspondences across frames and help attend to the most relevant features from neighboring frames, while DenseVP enhances weak dynamic features in distant regions around VPs. These modules operate within a context-detail framework, which separates contextual features from high-resolution local features at different input resolutions to reduce computational costs. Contextual and local features are integrated through contextualized motion attention (CMA) for the final prediction. Extensive experiments on two popular driving segmentation benchmarks, Cityscapes and ACDC, demonstrate that VPSeg outperforms previous SOTA methods, with only modest computational overhead.
Authors: Muhammad Haseeb Aslam, Muhammad Osama Zeeshan, Soufiane Belharbi, Marco Pedersoli, Alessandro Koerich, Simon Bacon, Eric Granger
Abstract: Deep learning models for multimodal expression recognition have reached remarkable performance in controlled laboratory environments because of their ability to learn complementary and redundant semantic information. However, these models struggle in the wild, mainly because of the unavailability and quality of modalities used for training. In practice, only a subset of the training-time modalities may be available at test time. Learning with privileged information enables models to exploit data from additional modalities that are only available during training. State-of-the-art knowledge distillation (KD) methods have been proposed to distill information from multiple teacher models (each trained on a modality) to a common student model. These privileged KD methods typically utilize point-to-point matching, yet have no explicit mechanism to capture the structural information in the teacher representation space formed by introducing the privileged modality. Experiments were performed on two challenging problems - pain estimation on the Biovid dataset (ordinal classification) and arousal-valance prediction on the Affwild2 dataset (regression). Results show that our proposed method can outperform state-of-the-art privileged KD methods on these problems. The diversity among modalities and fusion architectures indicates that PKDOT is modality- and model-agnostic.
Authors: Yang Liu, Xinshuai Song, Kaixuan Jiang, Weixing Chen, Jingzhou Luo, Guanbin Li, Liang Lin
Abstract: With the surge in the development of large language models, embodied intelligence has attracted increasing attention. Nevertheless, prior works on embodied intelligence typically encode scene or historical memory in an unimodal manner, either visual or linguistic, which complicates the alignment of the model's action planning with embodied control. To overcome this limitation, we introduce the Multimodal Embodied Interactive Agent (MEIA), capable of translating high-level tasks expressed in natural language into a sequence of executable actions. Specifically, we propose a novel Multimodal Environment Memory (MEM) module, facilitating the integration of embodied control with large models through the visual-language memory of scenes. This capability enables MEIA to generate executable action plans based on diverse requirements and the robot's capabilities. Furthermore, we construct an embodied question answering dataset based on a dynamic virtual cafe environment with the help of the large language model. In this virtual environment, we conduct several experiments, utilizing multiple large models through zero-shot learning, and carefully design scenarios for various situations. The experimental results showcase the promising performance of our MEIA in various embodied interactive tasks.
Authors: Parisa Farmanifard, Arun Ross
Abstract: Iris segmentation is a critical component of an iris biometric system and it involves extracting the annular iris region from an ocular image. In this work, we develop a pixel-level iris segmentation model from a foundational model, viz., Segment Anything Model (SAM), that has been successfully used for segmenting arbitrary objects. The primary contribution of this work lies in the integration of different loss functions during the fine-tuning of SAM on ocular images. In particular, the importance of Focal Loss is borne out in the fine-tuning process since it strategically addresses the class imbalance problem (i.e., iris versus non-iris pixels). Experiments on ND-IRIS-0405, CASIA-Iris-Interval-v3, and IIT-Delhi-Iris datasets convey the efficacy of the trained model for the task of iris segmentation. For instance, on the ND-IRIS-0405 dataset, an average segmentation accuracy of 99.58% was achieved, compared to the best baseline performance of 89.75%.
Authors: Zhuoling Li, Xiaogang Xu, SerNam Lim, Hengshuang Zhao
Abstract: Realizing unified monocular 3D object detection, including both indoor and outdoor scenes, holds great importance in applications like robot navigation. However, involving various scenarios of data to train models poses challenges due to their significantly different characteristics, e.g., diverse geometry properties and heterogeneous domain distributions. To address these challenges, we build a detector based on the bird's-eye-view (BEV) detection paradigm, where the explicit feature projection is beneficial to addressing the geometry learning ambiguity when employing multiple scenarios of data to train detectors. Then, we split the classical BEV detection architecture into two stages and propose an uneven BEV grid design to handle the convergence instability caused by the aforementioned challenges. Moreover, we develop a sparse BEV feature projection strategy to reduce computational cost and a unified domain alignment method to handle heterogeneous domains. Combining these techniques, a unified detector UniMODE is derived, which surpasses the previous state-of-the-art on the challenging Omni3D dataset (a large-scale dataset including both indoor and outdoor scenes) by 4.9% AP_3D, revealing the first successful generalization of a BEV detector to unified 3D object detection.
Authors: Nuo Xu, Wen Wang, Rong Yang, Mengjie Qin, Zheyuan Lin, Wei Song, Chunlong Zhang, Jason Gu, Chao Li
Abstract: Object-goal navigation is a challenging task that requires guiding an agent to specific objects based on first-person visual observations. The ability of agent to comprehend its surroundings plays a crucial role in achieving successful object finding. However, existing knowledge-graph-based navigators often rely on discrete categorical one-hot vectors and vote counting strategy to construct graph representation of the scenes, which results in misalignment with visual images. To provide more accurate and coherent scene descriptions and address this misalignment issue, we propose the Aligning Knowledge Graph with Visual Perception (AKGVP) method for object-goal navigation. Technically, our approach introduces continuous modeling of the hierarchical scene architecture and leverages visual-language pre-training to align natural language description with visual perception. The integration of a continuous knowledge graph architecture and multimodal feature alignment empowers the navigator with a remarkable zero-shot navigation capability. We extensively evaluate our method using the AI2-THOR simulator and conduct a series of experiments to demonstrate the effectiveness and efficiency of our navigator. Code available: https://github.com/nuoxu/AKGVP.
Authors: R. Gnana Praveen, Jahangir Alam
Abstract: Person or identity verification has been recently gaining a lot of attention using audio-visual fusion as faces and voices share close associations with each other. Conventional approaches based on audio-visual fusion rely on score-level or early feature-level fusion techniques. Though existing approaches showed improvement over unimodal systems, the potential of audio-visual fusion for person verification is not fully exploited. In this paper, we have investigated the prospect of effectively capturing both the intra- and inter-modal relationships across audio and visual modalities, which can play a crucial role in significantly improving the fusion performance over unimodal systems. In particular, we introduce a recursive fusion of a joint cross-attentional model, where a joint audio-visual feature representation is employed in the cross-attention framework in a recursive fashion to progressively refine the feature representations that can efficiently capture the intra-and inter-modal relationships. To further enhance the audio-visual feature representations, we have also explored BLSTMs to improve the temporal modeling of audio-visual feature representations. Extensive experiments are conducted on the Voxceleb1 dataset to evaluate the proposed model. Results indicate that the proposed model shows promising improvement in fusion performance by adeptly capturing the intra-and inter-modal relationships across audio and visual modalities.
Authors: Baiyuan Chen
Abstract: This paper presents an innovative enhancement to the Sphere as Prior Generative Adversarial Network (SP-GAN) model, a state-of-the-art GAN designed for point cloud generation. A novel method is introduced for point cloud generation that elevates the structural integrity and overall quality of the generated point clouds by incorporating topological priors into the training process of the generator. Specifically, this work utilizes the K-means algorithm to segment a point cloud from the repository into clusters and extract centroids, which are then used as priors in the generation process of the SP-GAN. Furthermore, the discriminator component of the SP-GAN utilizes the identical point cloud that contributed the centroids, ensuring a coherent and consistent learning environment. This strategic use of centroids as intuitive guides not only boosts the efficiency of global feature learning but also substantially improves the structural coherence and fidelity of the generated point clouds. By applying the K-means algorithm to generate centroids as the prior, the work intuitively and experimentally demonstrates that such a prior enhances the quality of generated point clouds.
Authors: Ba Hung Ngo, Nhat-Tuong Do-Tran, Tuan-Ngoc Nguyen, Hae-Gon Jeon, Tae Jong Choi
Abstract: Most domain adaptation (DA) methods are based on either a convolutional neural networks (CNNs) or a vision transformers (ViTs). They align the distribution differences between domains as encoders without considering their unique characteristics. For instance, ViT excels in accuracy due to its superior ability to capture global representations, while CNN has an advantage in capturing local representations. This fact has led us to design a hybrid method to fully take advantage of both ViT and CNN, called Explicitly Class-specific Boundaries (ECB). ECB learns CNN on ViT to combine their distinct strengths. In particular, we leverage ViT's properties to explicitly find class-specific decision boundaries by maximizing the discrepancy between the outputs of the two classifiers to detect target samples far from the source support. In contrast, the CNN encoder clusters target features based on the previously defined class-specific boundaries by minimizing the discrepancy between the probabilities of the two classifiers. Finally, ViT and CNN mutually exchange knowledge to improve the quality of pseudo labels and reduce the knowledge discrepancies of these models. Compared to conventional DA methods, our ECB achieves superior performance, which verifies its effectiveness in this hybrid model. The project website can be found https://dotrannhattuong.github.io/ECB/website.
Authors: Eren Tahir, Mert Bal
Abstract: Image forgery is a topic that has been studied for many years. Before the breakthrough of deep learning, forged images were detected using handcrafted features that did not require training. These traditional methods failed to perform satisfactorily even on datasets much worse in quality than real-life image manipulations. Advances in deep learning have impacted image forgery detection as much as they have impacted other areas of computer vision and have improved the state of the art. Deep learning models require large amounts of labeled data for training. In the case of image forgery, labeled data at the pixel level is a very important factor for the models to learn. None of the existing datasets have sufficient size, realism and pixel-level labeling at the same time. This is due to the high cost of producing and labeling quality images. It can take hours for an image editing expert to manipulate just one image. To bridge this gap, we automate data generation using image composition techniques that are very related to image forgery. Unlike other automated data generation frameworks, we use state of the art image composition deep learning models to generate spliced images close to the quality of real-life manipulations. Finally, we test the generated dataset on the SOTA image manipulation detection model and show that its prediction performance is lower compared to existing datasets, i.e. we produce realistic images that are more difficult to detect. Dataset will be available at https://github.com/99eren99/DIS25k .
Authors: Andrea Atzori, Fadi Boutros, Naser Damer, Gianni Fenu, Mirko Marras
Abstract: Recent advances in deep face recognition have spurred a growing demand for large, diverse, and manually annotated face datasets. Acquiring authentic, high-quality data for face recognition has proven to be a challenge, primarily due to privacy concerns. Large face datasets are primarily sourced from web-based images, lacking explicit user consent. In this paper, we examine whether and how synthetic face data can be used to train effective face recognition models with reduced reliance on authentic images, thereby mitigating data collection concerns. First, we explored the performance gap among recent state-of-the-art face recognition models, trained with synthetic data only and authentic (scarce) data only. Then, we deepened our analysis by training a state-of-the-art backbone with various combinations of synthetic and authentic data, gaining insights into optimizing the limited use of the latter for verification accuracy. Finally, we assessed the effectiveness of data augmentation approaches on synthetic and authentic data, with the same goal in mind. Our results highlighted the effectiveness of FR trained on combined datasets, particularly when combined with appropriate augmentation techniques.
Authors: Danpei Zhao, Bo Yuan, Ziqiang Chen, Tian Li, Zhuoran Liu, Wentao Li, Yue Gao
Abstract: Current remote-sensing interpretation models often focus on a single task such as detection, segmentation, or caption. However, the task-specific designed models are unattainable to achieve the comprehensive multi-level interpretation of images. The field also lacks support for multi-task joint interpretation datasets. In this paper, we propose Panoptic Perception, a novel task and a new fine-grained dataset (FineGrip) to achieve a more thorough and universal interpretation for RSIs. The new task, 1) integrates pixel-level, instance-level, and image-level information for universal image perception, 2) captures image information from coarse to fine granularity, achieving deeper scene understanding and description, and 3) enables various independent tasks to complement and enhance each other through multi-task learning. By emphasizing multi-task interactions and the consistency of perception results, this task enables the simultaneous processing of fine-grained foreground instance segmentation, background semantic segmentation, and global fine-grained image captioning. Concretely, the FineGrip dataset includes 2,649 remote sensing images, 12,054 fine-grained instance segmentation masks belonging to 20 foreground things categories, 7,599 background semantic masks for 5 stuff classes and 13,245 captioning sentences. Furthermore, we propose a joint optimization-based panoptic perception model. Experimental results on FineGrip demonstrate the feasibility of the panoptic perception task and the beneficial effect of multi-task joint optimization on individual tasks. The dataset will be publicly available.
Authors: Rijun Wang, Guanghao Zhang, Fulong Liang, Bo Wang, Xiangwei Mou, Yesheng Chen, Peng Sun, Canjin Wang
Abstract: Using deep learning methods is a promising approach to improving bark removal efficiency and enhancing the quality of wood products. However, the lack of publicly available datasets for wood plate segmentation in bark removal processing poses challenges for researchers in this field. To address this issue, a benchmark for wood plate segmentation in bark removal processing named WPS-dataset is proposed in this study, which consists of 4863 images. We designed an image acquisition device and assembled it on a bark removal equipment to capture images in real industrial settings. We evaluated the WPS-dataset using six typical segmentation models. The models effectively learn and understand the WPS-dataset characteristics during training, resulting in high performance and accuracy in wood plate segmentation tasks. We believe that our dataset can lay a solid foundation for future research in bark removal processing and contribute to advancements in this field.
Authors: Zichen Tang, Hongyu Yang
Abstract: Recent advances in generative visual models and neural radiance fields have greatly boosted 3D-aware image synthesis and stylization tasks. However, previous NeRF-based work is limited to single scene stylization, training a model to generate 3D-aware cartoon faces with arbitrary styles remains unsolved. We propose ArtNeRF, a novel face stylization framework derived from 3D-aware GAN to tackle this problem. In this framework, we utilize an expressive generator to synthesize stylized faces and a triple-branch discriminator module to improve the visual quality and style consistency of the generated faces. Specifically, a style encoder based on contrastive learning is leveraged to extract robust low-dimensional embeddings of style images, empowering the generator with the knowledge of various styles. To smooth the training process of cross-domain transfer learning, we propose an adaptive style blending module which helps inject style information and allows users to freely tune the level of stylization. We further introduce a neural rendering module to achieve efficient real-time rendering of images with higher resolutions. Extensive experiments demonstrate that ArtNeRF is versatile in generating high-quality 3D-aware cartoon faces with arbitrary styles.
Authors: Lei He, Leheng Li, Wenchao Sun, Zeyu Han, Yichen Liu, Sifa Zheng, Jianqiang Wang, Keqiang Li
Abstract: Neural Radiance Field (NeRF) has garnered significant attention from both academia and industry due to its intrinsic advantages, particularly its implicit representation and novel view synthesis capabilities. With the rapid advancements in deep learning, a multitude of methods have emerged to explore the potential applications of NeRF in the domain of Autonomous Driving (AD). However, a conspicuous void is apparent within the current literature. To bridge this gap, this paper conducts a comprehensive survey of NeRF's applications in the context of AD. Our survey is structured to categorize NeRF's applications in Autonomous Driving (AD), specifically encompassing perception, 3D reconstruction, simultaneous localization and mapping (SLAM), and simulation. We delve into in-depth analysis and summarize the findings for each application category, and conclude by providing insights and discussions on future directions in this field. We hope this paper serves as a comprehensive reference for researchers in this domain. To the best of our knowledge, this is the first survey specifically focused on the applications of NeRF in the Autonomous Driving domain.
Authors: Shiyi Zhang, Sule Bai, Guangyi Chen, Lei Chen, Jiwen Lu, Junle Wang, Yansong Tang
Abstract: In this paper, we investigate a new problem called narrative action evaluation (NAE). NAE aims to generate professional commentary that evaluates the execution of an action. Unlike traditional tasks such as score-based action quality assessment and video captioning involving superficial sentences, NAE focuses on creating detailed narratives in natural language. These narratives provide intricate descriptions of actions along with objective evaluations. NAE is a more challenging task because it requires both narrative flexibility and evaluation rigor. One existing possible solution is to use multi-task learning, where narrative language and evaluative information are predicted separately. However, this approach results in reduced performance for individual tasks because of variations between tasks and differences in modality between language information and evaluation information. To address this, we propose a prompt-guided multimodal interaction framework. This framework utilizes a pair of transformers to facilitate the interaction between different modalities of information. It also uses prompts to transform the score regression task into a video-text matching task, thus enabling task interactivity. To support further research in this field, we re-annotate the MTL-AQA and FineGym datasets with high-quality and comprehensive action narration. Additionally, we establish benchmarks for NAE. Extensive experiment results prove that our method outperforms separate learning methods and naive multi-task learning methods. Data and code are released at https://github.com/shiyi-zh0408/NAE_CVPR2024.
Authors: Fan Zhang, Zhi-Qi Cheng, Jian Zhao, Xiaojiang Peng, Xuelong Li
Abstract: Semi-supervised learning has emerged as a promising approach to tackle the challenge of label scarcity in facial expression recognition (FER) task. However, current state-of-the-art methods primarily focus on one side of the coin, i.e., generating high-quality pseudo-labels, while overlooking the other side: enhancing expression-relevant representations. In this paper, we unveil both sides of the coin by proposing a unified framework termed hierarchicaL dEcoupling And Fusing (LEAF) to coordinate expression-relevant representations and pseudo-labels for semi-supervised FER. LEAF introduces a hierarchical expression-aware aggregation strategy that operates at three levels: semantic, instance, and category. (1) At the semantic and instance levels, LEAF decouples representations into expression-agnostic and expression-relevant components, and adaptively fuses them using learnable gating weights. (2) At the category level, LEAF assigns ambiguous pseudo-labels by decoupling predictions into positive and negative parts, and employs a consistency loss to ensure agreement between two augmented views of the same image. Extensive experiments on benchmark datasets demonstrate that by unveiling and harmonizing both sides of the coin, LEAF outperforms state-of-the-art semi-supervised FER methods, effectively leveraging both labeled and unlabeled data. Moreover, the proposed expression-aware aggregation strategy can be seamlessly integrated into existing semi-supervised frameworks, leading to significant performance gains. Our code is available at https://anonymous.4open.science/r/LEAF-BC57/.
Authors: Jingyang Lin, Yingda Xia, Jianpeng Zhang, Ke Yan, Le Lu, Jiebo Luo, Ling Zhang
Abstract: Medical Vision-Language Pretraining (Med-VLP) establishes a connection between visual content from medical images and the relevant textual descriptions. Existing Med-VLP methods primarily focus on 2D images depicting a single body part, notably chest X-rays. In this paper, we extend the scope of Med-VLP to encompass 3D images, specifically targeting full-body scenarios, by using a multimodal dataset of CT images and reports. Compared with the 2D counterpart, 3D VLP is required to effectively capture essential semantics from significantly sparser representation in 3D imaging. In this paper, we introduce CT-GLIP (Grounded Language-Image Pretraining with CT scans), a novel method that constructs organ-level image-text pairs to enhance multimodal contrastive learning, aligning grounded visual features with precise diagnostic text. Additionally, we developed an abnormality dictionary to augment contrastive learning with diverse contrastive pairs. Our method, trained on a multimodal CT dataset comprising 44,011 organ-level vision-text pairs from 17,702 patients across 104 organs, demonstrates it can identify organs and abnormalities in a zero-shot manner using natural languages. The performance of CT-GLIP is validated on a separate test set of 1,130 patients, focusing on the 16 most frequent abnormalities across 7 organs. The experimental results show our model's superior performance over the standard CLIP framework across zero-shot and fine-tuning scenarios, using both CNN and ViT architectures.
Authors: Hanwei Zhang, Ying Zhu, Dan Wang, Lijun Zhang, Tianxiang Chen, Zi Ye
Abstract: State space models (SSMs) with selection mechanisms and hardware-aware architectures, namely Mamba, have recently demonstrated significant promise in long-sequence modeling. Since the self-attention mechanism in transformers has quadratic complexity with image size and increasing computational demands, the researchers are now exploring how to adapt Mamba for computer vision tasks. This paper is the first comprehensive survey aiming to provide an in-depth analysis of Mamba models in the field of computer vision. It begins by exploring the foundational concepts contributing to Mamba's success, including the state space model framework, selection mechanisms, and hardware-aware design. Next, we review these vision mamba models by categorizing them into foundational ones and enhancing them with techniques such as convolution, recurrence, and attention to improve their sophistication. We further delve into the widespread applications of Mamba in vision tasks, which include their use as a backbone in various levels of vision processing. This encompasses general visual tasks, Medical visual tasks (e.g., 2D / 3D segmentation, classification, and image registration, etc.), and Remote Sensing visual tasks. We specially introduce general visual tasks from two levels: High/Mid-level vision (e.g., Object detection, Segmentation, Video classification, etc.) and Low-level vision (e.g., Image super-resolution, Image restoration, Visual generation, etc.). We hope this endeavor will spark additional interest within the community to address current challenges and further apply Mamba models in computer vision.
Authors: Ao Xiang, Jingyu Zhang, Qin Yang, Liyang Wang, Yu Cheng
Abstract: With the development and widespread application of digital image processing technology, image splicing has become a common method of image manipulation, raising numerous security and legal issues. This paper introduces a new splicing image detection algorithm based on the statistical characteristics of natural images, aimed at improving the accuracy and efficiency of splicing image detection. By analyzing the limitations of traditional methods, we have developed a detection framework that integrates advanced statistical analysis techniques and machine learning methods. The algorithm has been validated using multiple public datasets, showing high accuracy in detecting spliced edges and locating tampered areas, as well as good robustness. Additionally, we explore the potential applications and challenges faced by the algorithm in real-world scenarios. This research not only provides an effective technological means for the field of image tampering detection but also offers new ideas and methods for future related research.
Authors: Haotian Yan, Ming Wu, Chuang Zhang
Abstract: Multi-scale learning is central to semantic segmentation. We visualize the effective receptive field (ERF) of canonical multi-scale representations and point out two risks in learning them: scale inadequacy and field inactivation. A novel multi-scale learner, varying window attention (VWA), is presented to address these issues. VWA leverages the local window attention (LWA) and disentangles LWA into the query window and context window, allowing the context's scale to vary for the query to learn representations at multiple scales. However, varying the context to large-scale windows (enlarging ratio R) can significantly increase the memory footprint and computation cost (R^2 times larger than LWA). We propose a simple but professional re-scaling strategy to zero the extra induced cost without compromising performance. Consequently, VWA uses the same cost as LWA to overcome the receptive limitation of the local window. Furthermore, depending on VWA and employing various MLPs, we introduce a multi-scale decoder (MSD), VWFormer, to improve multi-scale representations for semantic segmentation. VWFormer achieves efficiency competitive with the most compute-friendly MSDs, like FPN and MLP decoder, but performs much better than any MSDs. For instance, using nearly half of UPerNet's computation, VWFormer outperforms it by 1.0%-2.5% mIoU on ADE20K. With little extra overhead, ~10G FLOPs, Mask2Former armed with VWFormer improves by 1.0%-1.3%. The code and models are available at https://github.com/yan-hao-tian/vw
Authors: Ilayda Yaman, Guoda Tian, Martin Larsson, Patrik Persson, Michiel Sandra, Alexander D\"urr, Erik Tegler, Nikhil Challa, Henrik Garde, Fredrik Tufvesson, Kalle \r{A}str\"om, Ove Edfors, Steffen Malkowsky, Liang Liu
Abstract: We present a synchronized multisensory dataset for accurate and robust indoor localization: the Lund University Vision, Radio, and Audio (LuViRA) Dataset. The dataset includes color images, corresponding depth maps, inertial measurement unit (IMU) readings, channel response between a 5G massive multiple-input and multiple-output (MIMO) testbed and user equipment, audio recorded by 12 microphones, and accurate six degrees of freedom (6DOF) pose ground truth of 0.5 mm. We synchronize these sensors to ensure that all data is recorded simultaneously. A camera, speaker, and transmit antenna are placed on top of a slowly moving service robot, and 89 trajectories are recorded. Each trajectory includes 20 to 50 seconds of recorded sensor data and ground truth labels. Data from different sensors can be used separately or jointly to perform localization tasks, and data from the motion capture (mocap) system is used to verify the results obtained by the localization algorithms. The main aim of this dataset is to enable research on sensor fusion with the most commonly used sensors for localization tasks. Moreover, the full dataset or some parts of it can also be used for other research areas such as channel estimation, image classification, etc. Our dataset is available at: https://github.com/ilaydayaman/LuViRA_Dataset
Authors: Ziqiang Li, Hong Sun, Pengfei Xia, Beihao Xia, Xue Rui, Wei Zhang, Qinglang Guo, Bin Li
Abstract: Poisoning efficiency plays a critical role in poisoning-based backdoor attacks. To evade detection, attackers aim to use the fewest poisoning samples while achieving the desired attack strength. Although efficient triggers have significantly improved poisoning efficiency, there is still room for further enhancement. Recently, selecting efficient samples has shown promise, but it often requires a proxy backdoor injection task to identify an efficient poisoning sample set. However, the proxy attack-based approach can lead to performance degradation if the proxy attack settings differ from those used by the actual victims due to the shortcut of backdoor learning. This paper presents a Proxy attack-Free Strategy (PFS) designed to identify efficient poisoning samples based on individual similarity and ensemble diversity, effectively addressing the mentioned concern. The proposed PFS is motivated by the observation that selecting the to-be-poisoned samples with high similarity between clean samples and their corresponding poisoning samples results in significantly higher attack success rates compared to using samples with low similarity. Furthermore, theoretical analyses for this phenomenon are provided based on the theory of active learning and neural tangent kernel. We comprehensively evaluate the proposed strategy across various datasets, triggers, poisoning rates, architectures, and training hyperparameters. Our experimental results demonstrate that PFS enhances backdoor attack efficiency, while also exhibiting a remarkable speed advantage over prior proxy-dependent selection methodologies.
Authors: Tong Wu
Abstract: Recently, tensor low-rank representation (TLRR) has become a popular tool for tensor data recovery and clustering, due to its empirical success and theoretical guarantees. However, existing TLRR methods consider Gaussian or gross sparse noise, inevitably leading to performance degradation when the tensor data are contaminated by outliers or sample-specific corruptions. This paper develops an outlier-robust tensor low-rank representation (OR-TLRR) method that provides outlier detection and tensor data clustering simultaneously based on the t-SVD framework. For tensor observations with arbitrary outlier corruptions, OR-TLRR has provable performance guarantee for exactly recovering the row space of clean data and detecting outliers under mild conditions. Moreover, an extension of OR-TLRR is proposed to handle the case when parts of the data are missing. Finally, extensive experimental results on synthetic and real data demonstrate the effectiveness of the proposed algorithms. We release our code at https://github.com/twugithub/2024-AISTATS-ORTLRR.
Authors: Behnood Rasti (HZDR), Alexandre Zouaoui (Thoth), Julien Mairal (Thoth), Jocelyn Chanussot (Thoth)
Abstract: Spectral pixels are often a mixture of the pure spectra of the materials, called endmembers, due to the low spatial resolution of hyperspectral sensors, double scattering, and intimate mixtures of materials in the scenes. Unmixing estimates the fractional abundances of the endmembers within the pixel. Depending on the prior knowledge of endmembers, linear unmixing can be divided into three main groups: supervised, semi-supervised, and unsupervised (blind) linear unmixing. Advances in Image processing and machine learning substantially affected unmixing. This paper provides an overview of advanced and conventional unmixing approaches. Additionally, we draw a critical comparison between advanced and conventional techniques from the three categories. We compare the performance of the unmixing techniques on three simulated and two real datasets. The experimental results reveal the advantages of different unmixing categories for different unmixing scenarios. Moreover, we provide an open-source Python-based package available at https://github.com/BehnoodRasti/HySUPP to reproduce the results.
Authors: Jiaeli Shi, Najah Ghalyan, Kostis Gourgoulias, John Buford, Sean Moran
Abstract: Machine learning models trained on sensitive or private data can inadvertently memorize and leak that information. Machine unlearning seeks to retroactively remove such details from model weights to protect privacy. We contribute a lightweight unlearning algorithm that leverages the Fisher Information Matrix (FIM) for selective forgetting. Prior work in this area requires full retraining or large matrix inversions, which are computationally expensive. Our key insight is that the diagonal elements of the FIM, which measure the sensitivity of log-likelihood to changes in weights, contain sufficient information for effective forgetting. Specifically, we compute the FIM diagonal over two subsets -- the data to retain and forget -- for all trainable weights. This diagonal representation approximates the complete FIM while dramatically reducing computation. We then use it to selectively update weights to maximize forgetting of the sensitive subset while minimizing impact on the retained subset. Experiments show that our algorithm can successfully forget any randomly selected subsets of training data across neural network architectures. By leveraging the FIM diagonal, our approach provides an interpretable, lightweight, and efficient solution for machine unlearning with practical privacy benefits.
Authors: Stephanie L. Hyland, Shruthi Bannur, Kenza Bouzid, Daniel C. Castro, Mercy Ranjit, Anton Schwaighofer, Fernando P\'erez-Garc\'ia, Valentina Salvatelli, Shaury Srivastav, Anja Thieme, Noel Codella, Matthew P. Lungren, Maria Teodora Wetscherek, Ozan Oktay, Javier Alvarez-Valle
Abstract: We present a radiology-specific multimodal model for the task for generating radiological reports from chest X-rays (CXRs). Our work builds on the idea that large language model(s) can be equipped with multimodal capabilities through alignment with pre-trained vision encoders. On natural images, this has been shown to allow multimodal models to gain image understanding and description capabilities. Our proposed model (MAIRA-1) leverages a CXR-specific image encoder in conjunction with a fine-tuned large language model based on Vicuna-7B, and text-based data augmentation, to produce reports with state-of-the-art quality. In particular, MAIRA-1 significantly improves on the radiologist-aligned RadCliQ metric and across all lexical metrics considered. Manual review of model outputs demonstrates promising fluency and accuracy of generated reports while uncovering failure modes not captured by existing evaluation practices. More information and resources can be found on the project website: https://aka.ms/maira.
URLs: https://aka.ms/maira.
Authors: Botos Csaba, Wenxuan Zhang, Matthias M\"uller, Ser-Nam Lim, Mohamed Elhoseiny, Philip Torr, Adel Bibi
Abstract: Online continual learning, the process of training models on streaming data, has gained increasing attention in recent years. However, a critical aspect often overlooked is the label delay, where new data may not be labeled due to slow and costly annotation processes. We introduce a new continual learning framework with explicit modeling of the label delay between data and label streams over time steps. In each step, the framework reveals both unlabeled data from the current time step $t$ and labels delayed with $d$ steps, from the time step $t-d$. In our extensive experiments amounting to 1060 GPU days, we show that merely augmenting the computational resources is insufficient to tackle this challenge. Our findings underline a notable performance decline when solely relying on labeled data when the label delay becomes significant. More surprisingly, when using state-of-the-art SSL and TTA techniques to utilize the newer, unlabeled data, they fail to surpass the performance of a na\"ive method that simply trains on the delayed supervised stream. To this end, we introduce a simple, efficient baseline that rehearses from the labeled memory samples that are most similar to the new unlabeled samples. This method bridges the accuracy gap caused by label delay without significantly increasing computational complexity. We show experimentally that our method is the least affected by the label delay factor and in some cases successfully recovers the accuracy of the non-delayed counterpart. We conduct various ablations and sensitivity experiments, demonstrating the effectiveness of our approach.
Authors: Xianghong Fang, Jian Li, Qiang Sun, Benyou Wang
Abstract: Uniformity plays an important role in evaluating learned representations, providing insights into self-supervised learning. In our quest for effective uniformity metrics, we pinpoint four principled properties that such metrics should possess. Namely, an effective uniformity metric should remain invariant to instance permutations and sample replications while accurately capturing feature redundancy and dimensional collapse. Surprisingly, we find that the uniformity metric proposed by \citet{Wang2020UnderstandingCR} fails to satisfy the majority of these properties. Specifically, their metric is sensitive to sample replications, and can not account for feature redundancy and dimensional collapse correctly. To overcome these limitations, we introduce a new uniformity metric based on the Wasserstein distance, which satisfies all the aforementioned properties. Integrating this new metric in existing self-supervised learning methods effectively mitigates dimensional collapse and consistently improves their performance on downstream tasks involving CIFAR-10 and CIFAR-100 datasets. Code is available at \url{https://github.com/statsle/WassersteinSSL}.
Authors: Marek Wodzinski, Niccol\`o Marini, Manfredo Atzori, Henning M\"uller
Abstract: The automatic registration of differently stained whole slide images (WSIs) is crucial for improving diagnosis and prognosis by fusing complementary information emerging from different visible structures. It is also useful to quickly transfer annotations between consecutive or restained slides, thus significantly reducing the annotation time and associated costs. Nevertheless, the slide preparation is different for each stain and the tissue undergoes complex and large deformations. Therefore, a robust, efficient, and accurate registration method is highly desired by the scientific community and hospitals specializing in digital pathology. We propose a two-step hybrid method consisting of (i) deep learning- and feature-based initial alignment algorithm, and (ii) intensity-based nonrigid registration using the instance optimization. The proposed method does not require any fine-tuning to a particular dataset and can be used directly for any desired tissue type and stain. The method scored 1st place in the ACROBAT 2023 challenge. We evaluated using three open datasets: (i) ANHIR, (ii) ACROBAT, and (iii) HyReCo, and performed several ablation studies concerning the resolution used for registration and the initial alignment robustness and stability. The method achieves the most accurate results for the ACROBAT dataset, the cell-level registration accuracy for the restained slides from the HyReCo dataset, and is among the best methods evaluated on the ANHIR dataset. The method does not require any fine-tuning to a new datasets and can be used out-of-the-box for other types of microscopic images. The method is incorporated into the DeeperHistReg framework, allowing others to directly use it to register, transform, and save the WSIs at any desired pyramid level. The proposed method is a significant contribution to the WSI registration, thus advancing the field of digital pathology.
Authors: Mansoor Hayat, Supavadee Aramvith, Titipat Achakulvisut
Abstract: SEGSRNet addresses the challenge of precisely identifying surgical instruments in low-resolution stereo endoscopic images, a common issue in medical imaging and robotic surgery. Our innovative framework enhances image clarity and segmentation accuracy by applying state-of-the-art super-resolution techniques before segmentation. This ensures higher-quality inputs for more precise segmentation. SEGSRNet combines advanced feature extraction and attention mechanisms with spatial processing to sharpen image details, which is significant for accurate tool identification in medical images. Our proposed model outperforms current models including Dice, IoU, PSNR, and SSIM, SEGSRNet where it produces clearer and more accurate images for stereo endoscopic surgical imaging. SEGSRNet can provide image resolution and precise segmentation which can significantly enhance surgical accuracy and patient care outcomes.