Authors: Jo\~ao Luzio, Alexandre Bernardino, Plinio Moreno
Abstract: The aim of this work is to establish how accurately a recent semantic-based foveal active perception model is able to complete visual tasks that are regularly performed by humans, namely, scene exploration and visual search. This model exploits the ability of current object detectors to localize and classify a large number of object classes and to update a semantic description of a scene across multiple fixations. It has been used previously in scene exploration tasks. In this paper, we revisit the model and extend its application to visual search tasks. To illustrate the benefits of using semantic information in scene exploration and visual search tasks, we compare its performance against traditional saliency-based models. In the task of scene exploration, the semantic-based method demonstrates superior performance compared to the traditional saliency-based model in accurately representing the semantic information present in the visual scene. In visual search experiments, searching for instances of a target class in a visual field containing multiple distractors shows superior performance compared to the saliency-driven model and a random gaze selection algorithm. Our results demonstrate that semantic information, from the top-down, influences visual exploration and search tasks significantly, suggesting a potential area of research for integrating it with traditional bottom-up cues.
Authors: Zhengyang Liang, Meiyu Liang, Wei Huang, Yawen Li, Zhe Xue
Abstract: In recent years, pre-trained multimodal large models have attracted widespread attention due to their outstanding performance in various multimodal applications. Nonetheless, the extensive computational resources and vast datasets required for their training present significant hurdles for deployment in environments with limited computational resources. To address this challenge, we propose a novel dynamic self-adaptive multiscale distillation from pre-trained multimodal large model for efficient cross-modal representation learning for the first time. Unlike existing distillation methods, our strategy employs a multiscale perspective, enabling the extraction structural knowledge across from the pre-trained multimodal large model. Ensuring that the student model inherits a comprehensive and nuanced understanding of the teacher knowledge. To optimize each distillation loss in a balanced and efficient manner, we propose a dynamic self-adaptive distillation loss balancer, a novel component eliminating the need for manual loss weight adjustments and dynamically balances each loss item during the distillation process. Our methodology streamlines pre-trained multimodal large models using only their output features and original image-level information, requiring minimal computational resources. This efficient approach is suited for various applications and allows the deployment of advanced multimodal technologies even in resource-limited settings. Extensive experiments has demonstrated that our method maintains high performance while significantly reducing model complexity and training costs. Moreover, our distilled student model utilizes only image-level information to achieve state-of-the-art performance on cross-modal retrieval tasks, surpassing previous methods that relied on region-level information.
Authors: Toqi Tahamid Sarker, Mohamed G Embaby, Khaled R Ahmed, Amer AbuGhazaleh
Abstract: Methane emissions from livestock, particularly cattle, significantly contribute to climate change. Effective methane emission mitigation strategies are crucial as the global population and demand for livestock products increase. We introduce Gasformer, a novel semantic segmentation architecture for detecting low-flow rate methane emissions from livestock, and controlled release experiments using optical gas imaging. We present two unique datasets captured with a FLIR GF77 OGI camera. Gasformer leverages a Mix Vision Transformer encoder and a Light-Ham decoder to generate multi-scale features and refine segmentation maps. Gasformer outperforms other state-of-the-art models on both datasets, demonstrating its effectiveness in detecting and segmenting methane plumes in controlled and real-world scenarios. On the livestock dataset, Gasformer achieves mIoU of 88.56%, surpassing other state-of-the-art models. Materials are available at: github.com/toqitahamid/Gasformer.
Authors: Henry Marichal, Diego Passarella, Christine Lucas, Ludmila Profumo, Ver\'onica Casaravilla, Mar\'ia Noel Rocha Galli, Serrana Ambite, Gregory Randall
Abstract: The automatic detection of tree-ring boundaries and other anatomical features using image analysis has progressed substantially over the past decade with advances in machine learning and imagery technology, as well as increasing demands from the dendrochronology community. This paper presents a publicly available database of 64 scanned images of transverse sections of commercially grown Pinus taeda trees from northern Uruguay, ranging from 17 to 24 years old. The collection contains several challenging features for automatic ring detection, including illumination and surface preparation variation, fungal infection (blue stains), knot formation, missing cortex or interruptions in outer rings, and radial cracking. This dataset can be used to develop and test automatic tree ring detection algorithms. This paper presents to the dendrochronology community one such method, Cross-Section Tree-Ring Detection (CS-TRD), which identifies and marks complete annual rings in cross-sections for tree species presenting a clear definition between early and latewood. We compare the CS-TRD performance against the ground truth manual delineation of all rings over the UruDendro dataset. The CS-TRD software identified rings with an average F-score of 89% and RMSE error of 5.27px for the entire database in less than 20 seconds per image. Finally, we propose a robust measure of the ring growth using the \emph{equivalent radius} of a circle having the same area enclosed by the detected tree ring. Overall, this study contributes to the dendrochronologist's toolbox of fast and low-cost methods to automatically detect rings in conifer species, particularly for measuring diameter growth rates and stem transverse area using entire cross-sections.
Authors: Alessandro Conti, Enrico Fini, Massimiliano Mancini, Paolo Rota, Yiming Wang, Elisa Ricci
Abstract: Large vision-language models revolutionized image classification and semantic segmentation paradigms. However, they typically assume a pre-defined set of categories, or vocabulary, at test time for composing textual prompts. This assumption is impractical in scenarios with unknown or evolving semantic context. Here, we address this issue and introduce the Vocabulary-free Image Classification (VIC) task, which aims to assign a class from an unconstrained language-induced semantic space to an input image without needing a known vocabulary. VIC is challenging due to the vastness of the semantic space, which contains millions of concepts, including fine-grained categories. To address VIC, we propose Category Search from External Databases (CaSED), a training-free method that leverages a pre-trained vision-language model and an external database. CaSED first extracts the set of candidate categories from the most semantically similar captions in the database and then assigns the image to the best-matching candidate category according to the same vision-language model. Furthermore, we demonstrate that CaSED can be applied locally to generate a coarse segmentation mask that classifies image regions, introducing the task of Vocabulary-free Semantic Segmentation. CaSED and its variants outperform other more complex vision-language models, on classification and semantic segmentation benchmarks, while using much fewer parameters.
Authors: Matthew Inkawhich, Nathan Inkawhich, Hao Yang, Jingyang Zhang, Randolph Linderman, Yiran Chen
Abstract: An object detector's ability to detect and flag \textit{novel} objects during open-world deployments is critical for many real-world applications. Unfortunately, much of the work in open object detection today is disjointed and fails to adequately address applications that prioritize unknown object recall \textit{in addition to} known-class accuracy. To close this gap, we present a new task called Open-Set Object Detection and Discovery (OSODD) and as a solution propose the Open-Set Regions with ViT features (OSR-ViT) detection framework. OSR-ViT combines a class-agnostic proposal network with a powerful ViT-based classifier. Its modular design simplifies optimization and allows users to easily swap proposal solutions and feature extractors to best suit their application. Using our multifaceted evaluation protocol, we show that OSR-ViT obtains performance levels that far exceed state-of-the-art supervised methods. Our method also excels in low-data settings, outperforming supervised baselines using a fraction of the training data.
Authors: Arnab Kumar Mondal, Stefano Alletto, Denis Tome
Abstract: Understanding human motion from video is essential for a range of applications, including pose estimation, mesh recovery and action recognition. While state-of-the-art methods predominantly rely on transformer-based architectures, these approaches have limitations in practical scenarios. Transformers are slower when sequentially predicting on a continuous stream of frames in real-time, and do not generalize to new frame rates. In light of these constraints, we propose a novel attention-free spatiotemporal model for human motion understanding building upon recent advancements in state space models. Our model not only matches the performance of transformer-based models in various motion understanding tasks but also brings added benefits like adaptability to different video frame rates and enhanced training speed when working with longer sequence of keypoints. Moreover, the proposed model supports both offline and real-time applications. For real-time sequential prediction, our model is both memory efficient and several times faster than transformer-based approaches while maintaining their high accuracy.
Authors: Kechun Liu, Wenjun Wu, Joann G. Elmore, Linda G. Shapiro
Abstract: Accurate cancer diagnosis remains a critical challenge in digital pathology, largely due to the gigapixel size and complex spatial relationships present in whole slide images. Traditional multiple instance learning (MIL) methods often struggle with these intricacies, especially in preserving the necessary context for accurate diagnosis. In response, we introduce a novel framework named Semantics-Aware Attention Guidance (SAG), which includes 1) a technique for converting diagnostically relevant entities into attention signals, and 2) a flexible attention loss that efficiently integrates various semantically significant information, such as tissue anatomy and cancerous regions. Our experiments on two distinct cancer datasets demonstrate consistent improvements in accuracy, precision, and recall with two state-of-the-art baseline models. Qualitative analysis further reveals that the incorporation of heuristic guidance enables the model to focus on regions critical for diagnosis. SAG is not only effective for the models discussed here, but its adaptability extends to any attention-based diagnostic model. This opens up exciting possibilities for further improving the accuracy and efficiency of cancer diagnostics.
Authors: Vincenzo Liguori
Abstract: This paper starts with a simple lossless ~1.5:1 compression algorithm for the weights of the Large Language Model (LLM) Llama2 7B [1] that can be implemented in ~200 LUTs in AMD FPGAs, processing over 800 million bfloat16 numbers per second. This framework is then extended to variable precision, variable range, compressed numerical data types that are a user defined super set of both floats and posits [2]. The paper then discusses a simple hardware implementation of such format based on ANS (Asymmetrical Numeral Systems) [3] that acts as a bridge between this flexible data format and a computational engine while, at the same time, achieving bandwidth reduction. An example of a token factory using weight compression and sharing is also given.
Authors: Marah Halawa, Florian Blume, Pia Bideau, Martin Maier, Rasha Abdel Rahman, Olaf Hellwich
Abstract: Human communication is multi-modal; e.g., face-to-face interaction involves auditory signals (speech) and visual signals (face movements and hand gestures). Hence, it is essential to exploit multiple modalities when designing machine learning-based facial expression recognition systems. In addition, given the ever-growing quantities of video data that capture human facial expressions, such systems should utilize raw unlabeled videos without requiring expensive annotations. Therefore, in this work, we employ a multitask multi-modal self-supervised learning method for facial expression recognition from in-the-wild video data. Our model combines three self-supervised objective functions: First, a multi-modal contrastive loss, that pulls diverse data modalities of the same video together in the representation space. Second, a multi-modal clustering loss that preserves the semantic structure of input data in the representation space. Finally, a multi-modal data reconstruction loss. We conduct a comprehensive study on this multimodal multi-task self-supervised learning method on three facial expression recognition benchmarks. To that end, we examine the performance of learning through different combinations of self-supervised tasks on the facial expression recognition downstream task. Our model ConCluGen outperforms several multi-modal self-supervised and fully supervised baselines on the CMU-MOSEI dataset. Our results generally show that multi-modal self-supervision tasks offer large performance gains for challenging tasks such as facial expression recognition, while also reducing the amount of manual annotations required. We release our pre-trained models as well as source code publicly
Authors: Ellianna Abrahams, Tasha Snow, Matthew R. Siegfried, Fernando P\'erez
Abstract: We propose a new tiling strategy, Flip-n-Slide, which has been developed for specific use with large Earth observation satellite images when the location of objects-of-interest (OoI) is unknown and spatial context can be necessary for class disambiguation. Flip-n-Slide is a concise and minimalistic approach that allows OoI to be represented at multiple tile positions and orientations. This strategy introduces multiple views of spatio-contextual information, without introducing redundancies into the training set. By maintaining distinct transformation permutations for each tile overlap, we enhance the generalizability of the training set without misrepresenting the true data distribution. Our experiments validate the effectiveness of Flip-n-Slide in the task of semantic segmentation, a necessary data product in geophysical studies. We find that Flip-n-Slide outperforms the previous state-of-the-art augmentation routines for tiled data in all evaluation metrics. For underrepresented classes, Flip-n-Slide increases precision by as much as 15.8%.
Authors: Yusra Alkendi, Rana Azzam, Sajid Javed, Lakmal Seneviratne, Yahya Zweiri
Abstract: Moving object segmentation is critical to interpret scene dynamics for robotic navigation systems in challenging environments. Neuromorphic vision sensors are tailored for motion perception due to their asynchronous nature, high temporal resolution, and reduced power consumption. However, their unconventional output requires novel perception paradigms to leverage their spatially sparse and temporally dense nature. In this work, we propose a novel event-based motion segmentation algorithm using a Graph Transformer Neural Network, dubbed GTNN. Our proposed algorithm processes event streams as 3D graphs by a series of nonlinear transformations to unveil local and global spatiotemporal correlations between events. Based on these correlations, events belonging to moving objects are segmented from the background without prior knowledge of the dynamic scene geometry. The algorithm is trained on publicly available datasets including MOD, EV-IMO, and \textcolor{black}{EV-IMO2} using the proposed training scheme to facilitate efficient training on extensive datasets. Moreover, we introduce the Dynamic Object Mask-aware Event Labeling (DOMEL) approach for generating approximate ground-truth labels for event-based motion segmentation datasets. We use DOMEL to label our own recorded Event dataset for Motion Segmentation (EMS-DOMEL), which we release to the public for further research and benchmarking. Rigorous experiments are conducted on several unseen publicly-available datasets where the results revealed that GTNN outperforms state-of-the-art methods in the presence of dynamic background variations, motion patterns, and multiple dynamic objects with varying sizes and velocities. GTNN achieves significant performance gains with an average increase of 9.4% and 4.5% in terms of motion segmentation accuracy (IoU%) and detection rate (DR%), respectively.
Authors: Xiao Zhang, Ruoxi Jiang, William Gao, Rebecca Willett, Michael Maire
Abstract: We demonstrate that adding a weighting factor to decay the strength of identity shortcuts within residual networks substantially improves semantic feature learning in the state-of-the-art self-supervised masked autoencoding (MAE) paradigm. Our modification to the identity shortcuts within a VIT-B/16 backbone of an MAE boosts linear probing accuracy on ImageNet from 67.3% to 72.3%. This significant gap suggests that, while residual connection structure serves an essential role in facilitating gradient propagation, it may have a harmful side effect of reducing capacity for abstract learning by virtue of injecting an echo of shallower representations into deeper layers. We ameliorate this downside via a fixed formula for monotonically decreasing the contribution of identity connections as layer depth increases. Our design promotes the gradual development of feature abstractions, without impacting network trainability. Analyzing the representations learned by our modified residual networks, we find correlation between low effective feature rank and downstream task performance.
Authors: Yeonguk Yu, Sungho Shin, Seunghyeok Back, Minhwan Ko, Sangjun Noh, Kyoobin Lee
Abstract: Test-time adaptation (TTA) aims to adapt a pre-trained model to a new test domain without access to source data after deployment. Existing approaches typically rely on self-training with pseudo-labels since ground-truth cannot be obtained from test data. Although the quality of pseudo labels is important for stable and accurate long-term adaptation, it has not been previously addressed. In this work, we propose DPLOT, a simple yet effective TTA framework that consists of two components: (1) domain-specific block selection and (2) pseudo-label generation using paired-view images. Specifically, we select blocks that involve domain-specific feature extraction and train these blocks by entropy minimization. After blocks are adjusted for current test domain, we generate pseudo-labels by averaging given test images and corresponding flipped counterparts. By simply using flip augmentation, we prevent a decrease in the quality of the pseudo-labels, which can be caused by the domain gap resulting from strong augmentation. Our experimental results demonstrate that DPLOT outperforms previous TTA methods in CIFAR10-C, CIFAR100-C, and ImageNet-C benchmarks, reducing error by up to 5.4%, 9.1%, and 2.9%, respectively. Also, we provide an extensive analysis to demonstrate effectiveness of our framework. Code is available at https://github.com/gist-ailab/domain-specific-block-selection-and-paired-view-pseudo-labeling-for-online-TTA.
Authors: Nawfal Guefrachi, Jian Shi, Hakim Ghazzai, Ahmad Alsharoa
Abstract: The integration of Light Detection and Ranging (LiDAR) and Internet of Things (IoT) technologies offers transformative opportunities for public health informatics in urban safety and pedestrian well-being. This paper proposes a novel framework utilizing these technologies for enhanced 3D object detection and activity classification in urban traffic scenarios. By employing elevated LiDAR, we obtain detailed 3D point cloud data, enabling precise pedestrian activity monitoring. To overcome urban data scarcity, we create a specialized dataset through simulated traffic environments in Blender, facilitating targeted model training. Our approach employs a modified Point Voxel-Region-based Convolutional Neural Network (PV-RCNN) for robust 3D detection and PointNet for classifying pedestrian activities, significantly benefiting urban traffic management and public health by offering insights into pedestrian behavior and promoting safer urban environments. Our dual-model approach not only enhances urban traffic management but also contributes significantly to public health by providing insights into pedestrian behavior and promoting safer urban environment.
Authors: Changbin Li, Kangshuo Li, Yuzhe Ou, Lance M. Kaplan, Audun J{\o}sang, Jin-Hee Cho, Dong Hyun Jeong, Feng Chen
Abstract: Deep neural networks (DNNs) have been shown to perform well on exclusive, multi-class classification tasks. However, when different classes have similar visual features, it becomes challenging for human annotators to differentiate them. This scenario necessitates the use of composite class labels. In this paper, we propose a novel framework called Hyper-Evidential Neural Network (HENN) that explicitly models predictive uncertainty due to composite class labels in training data in the context of the belief theory called Subjective Logic (SL). By placing a grouped Dirichlet distribution on the class probabilities, we treat predictions of a neural network as parameters of hyper-subjective opinions and learn the network that collects both single and composite evidence leading to these hyper-opinions by a deterministic DNN from data. We introduce a new uncertainty type called vagueness originally designed for hyper-opinions in SL to quantify composite classification uncertainty for DNNs. Our results demonstrate that HENN outperforms its state-of-the-art counterparts based on four image datasets. The code and datasets are available at: https://github.com/Hugo101/HyperEvidentialNN.
Authors: Junbiao Pang, Zailin Dong, Jiaxin Deng, Mengyuan Zhu, Yunwei Zhang
Abstract: Parsing Computer-Aided Design (CAD) drawings is a fundamental step for CAD revision, semantic-based management, and the generation of 3D prototypes in both the architecture and engineering industries. Labeling symbols from a CAD drawing is a challenging yet notorious task from a practical point of view. In this work, we propose to label and spot symbols from CAD images that are converted from CAD drawings. The advantage of spotting symbols from CAD images lies in the low requirement of labelers and the low-cost annotation. However, pixel-wise spotting symbols from CAD images is challenging work. We propose a pixel-wise point location via Progressive Gaussian Kernels (PGK) to balance between training efficiency and location accuracy. Besides, we introduce a local offset to the heatmap-based point location method. Based on the keypoints detection, we propose a symbol grouping method to redraw the rectangle symbols in CAD images. We have released a dataset containing CAD images of equipment rooms from telecommunication industrial CAD drawings. Extensive experiments on this real-world dataset show that the proposed method has good generalization ability.
Authors: Amit Kumar Singh Yadav, Kratika Bhagtani, Davide Salvi, Paolo Bestagini, Edward J. Delp
Abstract: Methods that can generate synthetic speech which is perceptually indistinguishable from speech recorded by a human speaker, are easily available. Several incidents report misuse of synthetic speech generated from these methods to commit fraud. To counter such misuse, many methods have been proposed to detect synthetic speech. Some of these detectors are more interpretable, can generalize to detect synthetic speech in the wild and are robust to noise. However, limited work has been done on understanding bias in these detectors. In this work, we examine bias in existing synthetic speech detectors to determine if they will unfairly target a particular gender, age and accent group. We also inspect whether these detectors will have a higher misclassification rate for bona fide speech from speech-impaired speakers w.r.t fluent speakers. Extensive experiments on 6 existing synthetic speech detectors using more than 0.9 million speech signals demonstrate that most detectors are gender, age and accent biased, and future work is needed to ensure fairness. To support future research, we release our evaluation dataset, models used in our study and source code at https://gitlab.com/viper-purdue/fairssd.
Authors: Muhammad Z. Alam, Zeeshan Kaleem, Sousso Kelouwani
Abstract: Vision sensors are versatile and can capture a wide range of visual cues, such as color, texture, shape, and depth. This versatility, along with the relatively inexpensive availability of machine vision cameras, played an important role in adopting vision-based environment perception systems in autonomous vehicles (AVs). However, vision-based perception systems can be easily affected by glare in the presence of a bright source of light, such as the sun or the headlights of the oncoming vehicle at night or simply by light reflecting off snow or ice-covered surfaces; scenarios encountered frequently during driving. In this paper, we investigate various glare reduction techniques, including the proposed saturated pixel-aware glare reduction technique for improved performance of the computer vision (CV) tasks employed by the perception layer of AVs. We evaluate these glare reduction methods based on various performance metrics of the CV algorithms used by the perception layer. Specifically, we considered object detection, object recognition, object tracking, depth estimation, and lane detection which are crucial for autonomous driving. The experimental findings validate the efficacy of the proposed glare reduction approach, showcasing enhanced performance across diverse perception tasks and remarkable resilience against varying levels of glare.
Authors: Qi Han, Zhibo Tian, Chengwei Xia, Kun Zhan
Abstract: Semi-supervised image classification, leveraging pseudo supervision and consistency regularization, has demonstrated remarkable success. However, the ongoing challenge lies in fully exploiting the potential of unlabeled data. To address this, we employ information entropy neural estimation to harness the potential of unlabeled samples. Inspired by contrastive learning, the entropy is estimated by maximizing a lower bound on mutual information across different augmented views. Moreover, we theoretically analyze that the information entropy of the posterior of an image classifier is approximated by maximizing the likelihood function of the softmax predictions. Guided by these insights, we optimize our model from both perspectives to ensure that the predicted probability distribution closely aligns with the ground-truth distribution. Given the theoretical connection to information entropy, we name our method \textit{InfoMatch}. Through extensive experiments, we show its superior performance.
Authors: Qing En, Yuhong Guo
Abstract: Lung-infected area segmentation is crucial for assessing the severity of lung diseases. However, existing image-text multi-modal methods typically rely on labour-intensive annotations for model training, posing challenges regarding time and expertise. To address this issue, we propose a novel attribute knowledge-guided framework for unsupervised lung-infected area segmentation (AKGNet), which achieves segmentation solely based on image-text data without any mask annotation. AKGNet facilitates text attribute knowledge learning, attribute-image cross-attention fusion, and high-confidence-based pseudo-label exploration simultaneously. It can learn statistical information and capture spatial correlations between image and text attributes in the embedding space, iteratively refining the mask to enhance segmentation. Specifically, we introduce a text attribute knowledge learning module by extracting attribute knowledge and incorporating it into feature representations, enabling the model to learn statistical information and adapt to different attributes. Moreover, we devise an attribute-image cross-attention module by calculating the correlation between attributes and images in the embedding space to capture spatial dependency information, thus selectively focusing on relevant regions while filtering irrelevant areas. Finally, a self-training mask improvement process is employed by generating pseudo-labels using high-confidence predictions to iteratively enhance the mask and segmentation. Experimental results on a benchmark medical image dataset demonstrate the superior performance of our method compared to state-of-the-art segmentation techniques in unsupervised scenarios.
Authors: Jiayang Li, Junjun Jiang, Pengwei Liang, Jiayi Ma
Abstract: In this research, we introduce MaeFuse, a novel autoencoder model designed for infrared and visible image fusion (IVIF). The existing approaches for image fusion often rely on training combined with downstream tasks to obtain high-level visual information, which is effective in emphasizing target objects and delivering impressive results in visual quality and task-specific applications. MaeFuse, however, deviates from the norm. Instead of being driven by downstream tasks, our model utilizes a pretrained encoder from Masked Autoencoders (MAE), which facilities the omni features extraction for low-level reconstruction and high-level vision tasks, to obtain perception friendly features with a low cost. In order to eliminate the domain gap of different modal features and the block effect caused by the MAE encoder, we further develop a guided training strategy. This strategy is meticulously crafted to ensure that the fusion layer seamlessly adjusts to the feature space of the encoder, gradually enhancing the fusion effect. It facilitates the comprehensive integration of feature vectors from both infrared and visible modalities, preserving the rich details inherent in each. MaeFuse not only introduces a novel perspective in the realm of fusion techniques but also stands out with impressive performance across various public datasets.
Authors: Sanggeon Yun, Ryozo Masukawa, SungHeon Jeong, Mohsen Imani
Abstract: In the face of burgeoning image data, efficiently retrieving similar images poses a formidable challenge. Past research has focused on refining hash functions to distill images into compact indicators of resemblance. Initial attempts used shallow models, evolving to attention mechanism-based architectures from Convolutional Neural Networks (CNNs) to advanced models. Recognizing limitations in gradient-based models for spatial information embedding, we propose an innovative image hashing method, NeuroHash leveraging Hyperdimensional Computing (HDC). HDC symbolically encodes spatial information into high-dimensional vectors, reshaping image representation. Our approach combines pre-trained large vision models with HDC operations, enabling spatially encoded feature representations. Hashing with locality-sensitive hashing (LSH) ensures swift and efficient image retrieval. Notably, our framework allows dynamic hash manipulation for conditional image retrieval. Our work introduces a transformative image hashing framework enabling spatial-aware conditional retrieval. By seamlessly combining DNN-based neural and HDC-based symbolic models, our methodology breaks from traditional training, offering flexible and conditional image retrieval. Performance evaluations signify a paradigm shift in image-hashing methodologies, demonstrating enhanced retrieval accuracy.
Authors: Chengyang Yan, Donald Dansereau
Abstract: The performance of robots in their applications heavily depends on the quality of sensory input. However, designing sensor payloads and their parameters for specific robotic tasks is an expensive process that requires well-established sensor knowledge and extensive experiments with physical hardware. With cameras playing a pivotal role in robotic perception, we introduce a novel end-to-end optimization approach for co-designing a camera with specific robotic tasks by combining derivative-free and gradient-based optimizers. The proposed method leverages recent computer graphics techniques and physical camera characteristics to prototype the camera in software, simulate operational environments and tasks for robots, and optimize the camera design based on the desired tasks in a cost-effective way. We validate the accuracy of our camera simulation by comparing it with physical cameras, and demonstrate the design of cameras with stronger performance than common off-the-shelf alternatives. Our approach supports the optimization of both continuous and discrete camera parameters, manufacturing constraints, and can be generalized to a broad range of camera design scenarios including multiple cameras and unconventional cameras. This work advances the fully automated design of cameras for specific robotics tasks.
Authors: Rijun Wang, Guanghao Zhang, Fulong Liang, Bo Wang, Xiangwei Mou, Yesheng Chen
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: Mohammad Shiri, Jiangwen Sun
Abstract: Invasive ductal carcinoma (IDC) is the most prevalent form of breast cancer. Breast tissue histopathological examination is critical in diagnosing and classifying breast cancer. Although existing methods have shown promising results, there is still room for improvement in the classification accuracy and generalization of IDC using histopathology images. We present a novel approach, Supervised Contrastive Vision Transformer (SupCon-ViT), for improving the classification of invasive ductal carcinoma in terms of accuracy and generalization by leveraging the inherent strengths and advantages of both transfer learning, i.e., pre-trained vision transformer, and supervised contrastive learning. Our results on a benchmark breast cancer dataset demonstrate that SupCon-Vit achieves state-of-the-art performance in IDC classification, with an F1-score of 0.8188, precision of 0.7692, and specificity of 0.8971, outperforming existing methods. In addition, the proposed model demonstrates resilience in scenarios with minimal labeled data, making it highly efficient in real-world clinical settings where labelled data is limited. Our findings suggest that supervised contrastive learning in conjunction with pre-trained vision transformers appears to be a viable strategy for an accurate classification of IDC, thus paving the way for a more efficient and reliable diagnosis of breast cancer through histopathological image analysis.
Authors: Ying Zhang, Bo Peng, Jiaran Zhou, Huiyu Zhou, Junyu Dong, Yuezun Li
Abstract: The task of video inpainting detection is to expose the pixel-level inpainted regions within a video sequence. Existing methods usually focus on leveraging spatial and temporal inconsistencies. However, these methods typically employ fixed operations to combine spatial and temporal clues, limiting their applicability in different scenarios. In this paper, we introduce a novel Multilateral Temporal-view Pyramid Transformer ({\em MumPy}) that collaborates spatial-temporal clues flexibly. Our method utilizes a newly designed multilateral temporal-view encoder to extract various collaborations of spatial-temporal clues and introduces a deformable window-based temporal-view interaction module to enhance the diversity of these collaborations. Subsequently, we develop a multi-pyramid decoder to aggregate the various types of features and generate detection maps. By adjusting the contribution strength of spatial and temporal clues, our method can effectively identify inpainted regions. We validate our method on existing datasets and also introduce a new challenging and large-scale Video Inpainting dataset based on the YouTube-VOS dataset, which employs several more recent inpainting methods. The results demonstrate the superiority of our method in both in-domain and cross-domain evaluation scenarios.
Authors: Yongdong Luo, Haojia Lin, Xiawu Zheng, Yigeng Jiang, Fei Chao, Jie Hu, Guannan Jiang, Songan Zhang, Rongrong Ji
Abstract: 3D Visual Grounding (3DVG) and 3D Dense Captioning (3DDC) are two crucial tasks in various 3D applications, which require both shared and complementary information in localization and visual-language relationships. Therefore, existing approaches adopt the two-stage "detect-then-describe/discriminate" pipeline, which relies heavily on the performance of the detector, resulting in suboptimal performance. Inspired by DETR, we propose a unified framework, 3DGCTR, to jointly solve these two distinct but closely related tasks in an end-to-end fashion. The key idea is to reconsider the prompt-based localization ability of the 3DVG model. In this way, the 3DVG model with a well-designed prompt as input can assist the 3DDC task by extracting localization information from the prompt. In terms of implementation, we integrate a Lightweight Caption Head into the existing 3DVG network with a Caption Text Prompt as a connection, effectively harnessing the existing 3DVG model's inherent localization capacity, thereby boosting 3DDC capability. This integration facilitates simultaneous multi-task training on both tasks, mutually enhancing their performance. Extensive experimental results demonstrate the effectiveness of this approach. Specifically, on the ScanRefer dataset, 3DGCTR surpasses the state-of-the-art 3DDC method by 4.3% in CIDEr@0.5IoU in MLE training and improves upon the SOTA 3DVG method by 3.16% in Acc@0.25IoU.
Authors: Jingrong Wang, Bo Xu, Ronghe Jin, Shoujian Zhang, Kefu Gao, Jingnan Liu
Abstract: Accurate, continuous, and reliable positioning is a critical component of achieving autonomous driving. However, in complex urban canyon environments, the vulnerability of a stand-alone sensor and non-line-of-sight (NLOS) caused by high buildings, trees, and elevated structures seriously affect positioning results. To address these challenges, a sky-view images segmentation algorithm based on Fully Convolutional Network (FCN) is proposed for GNSS NLOS detection. Building upon this, a novel NLOS detection and mitigation algorithm (named S-NDM) is extended to the tightly coupled Global Navigation Satellite Systems (GNSS), Inertial Measurement Units (IMU), and visual feature system which is called Sky-GVIO, with the aim of achieving continuous and accurate positioning in urban canyon environments. Furthermore, the system harmonizes Single Point Positioning (SPP) with Real-Time Kinematic (RTK) methodologies to bolster its operational versatility and resilience. In urban canyon environments, the positioning performance of S-NDM algorithm proposed in this paper is evaluated under different tightly coupled SPP-related and RTK-related models. The results exhibit that Sky-GVIO system achieves meter-level accuracy under SPP mode and sub-decimeter precision with RTK, surpassing the performance of GNSS/INS/Vision frameworks devoid of S-NDM. Additionally, the sky-view image dataset, inclusive of training and evaluation subsets, has been made publicly accessible for scholarly exploration at https://github.com/whuwangjr/sky-view-images .
Authors: Dingkun Zhang, Sijia Li, Chen Chen, Qingsong Xie, Haonan Lu
Abstract: In the era of AIGC, the demand for low-budget or even on-device applications of diffusion models emerged. In terms of compressing the Stable Diffusion models (SDMs), several approaches have been proposed, and most of them leveraged the handcrafted layer removal methods to obtain smaller U-Nets, along with knowledge distillation to recover the network performance. However, such a handcrafting manner of layer removal is inefficient and lacks scalability and generalization, and the feature distillation employed in the retraining phase faces an imbalance issue that a few numerically significant feature loss terms dominate over others throughout the retraining process. To this end, we proposed the layer pruning and normalized distillation for compressing diffusion models (LAPTOP-Diff). We, 1) introduced the layer pruning method to compress SDM's U-Net automatically and proposed an effective one-shot pruning criterion whose one-shot performance is guaranteed by its good additivity property, surpassing other layer pruning and handcrafted layer removal methods, 2) proposed the normalized feature distillation for retraining, alleviated the imbalance issue. Using the proposed LAPTOP-Diff, we compressed the U-Nets of SDXL and SDM-v1.5 for the most advanced performance, achieving a minimal 4.0% decline in PickScore at a pruning ratio of 50% while the comparative methods' minimal PickScore decline is 8.2%. We will release our code.
Authors: Qiyu Hou, Jun Wang, Meixuan Qiao, Lujun Tian
Abstract: To overcome the limitations and challenges of current automatic table data annotation methods and random table data synthesis approaches, we propose a novel method for synthesizing annotation data specifically designed for table recognition. This method utilizes the structure and content of existing complex tables, facilitating the efficient creation of tables that closely replicate the authentic styles found in the target domain. By leveraging the actual structure and content of tables from Chinese financial announcements, we have developed the first extensive table annotation dataset in this domain. We used this dataset to train several recent deep learning-based end-to-end table recognition models. Additionally, we have established the inaugural benchmark for real-world complex tables in the Chinese financial announcement domain, using it to assess the performance of models trained on our synthetic data, thereby effectively validating our method's practicality and effectiveness. Furthermore, we applied our synthesis method to augment the FinTabNet dataset, extracted from English financial announcements, by increasing the proportion of tables with multiple spanning cells to introduce greater complexity. Our experiments show that models trained on this augmented dataset achieve comprehensive improvements in performance, especially in the recognition of tables with multiple spanning cells.
Authors: Changsuk Oh, Dongseok Shim, Taekbeom Lee, H. Jin Kim
Abstract: Object removal refers to the process of erasing designated objects from an image while preserving the overall appearance, and it is one area where image inpainting is widely used in real-world applications. The performance of an object remover is quantitatively evaluated by measuring the quality of object removal results, similar to how the performance of an image inpainter is gauged. Current works reporting quantitative performance evaluations utilize original images as references. In this letter, to validate the current evaluation methods cannot properly evaluate the performance of an object remover, we create a dataset with object removal ground truth and compare the evaluations made by the current methods using original images to those utilizing object removal ground truth images. The disparities between two evaluation sets validate that the current methods are not suitable for measuring the performance of an object remover. Additionally, we propose new evaluation methods tailored to gauge the performance of an object remover. The proposed methods evaluate the performance through class-wise object removal results and utilize images without the target class objects as a comparison set. We confirm that the proposed methods can make judgments consistent with human evaluators in the COCO dataset, and that they can produce measurements aligning with those using object removal ground truth in the self-acquired dataset.
Authors: Tong Shen, Dong Li, Ziheng Gao, Lu Tian, Emad Barsoum
Abstract: Video Frame Interpolation (VFI) is a crucial technique in various applications such as slow-motion generation, frame rate conversion, video frame restoration etc. This paper introduces an efficient video frame interpolation framework that aims to strike a favorable balance between efficiency and quality. Our framework follows a general paradigm consisting of a flow estimator and a refinement module, while incorporating carefully designed components. First of all, we adopt depth-wise convolution with large kernels in the flow estimator that simultaneously reduces the parameters and enhances the receptive field for encoding rich context and handling complex motion. Secondly, diverging from a common design for the refinement module with a UNet-structure (encoder-decoder structure), which we find redundant, our decoder-only refinement module directly enhances the result from coarse to fine features, offering a more efficient process. In addition, to address the challenge of handling high-definition frames, we also introduce an innovative HD-aware augmentation strategy during training, leading to consistent enhancement on HD images. Extensive experiments are conducted on diverse datasets, Vimeo90K, UCF101, Xiph and SNU-FILM. The results demonstrate that our approach achieves state-of-the-art performance with clear improvement while requiring much less FLOPs and parameters, reaching to a better spot for balancing efficiency and quality.
Authors: Lianyu Hu, Wei Feng, Liqing Gao, Zekang Liu, Liang Wan
Abstract: In sign language, the conveyance of human body trajectories predominantly relies upon the coordinated movements of hands and facial expressions across successive frames. Despite the recent advancements of sign language understanding methods, they often solely focus on individual frames, inevitably overlooking the inter-frame correlations that are essential for effectively modeling human body trajectories. To address this limitation, this paper introduces a spatial-temporal correlation network, denoted as CorrNet+, which explicitly identifies body trajectories across multiple frames. In specific, CorrNet+ employs a correlation module and an identification module to build human body trajectories. Afterwards, a temporal attention module is followed to adaptively evaluate the contributions of different frames. The resultant features offer a holistic perspective on human body movements, facilitating a deeper understanding of sign language. As a unified model, CorrNet+ achieves new state-of-the-art performance on two extensive sign language understanding tasks, including continuous sign language recognition (CSLR) and sign language translation (SLT). Especially, CorrNet+ surpasses previous methods equipped with resource-intensive pose-estimation networks or pre-extracted heatmaps for hand and facial feature extraction. Compared with CorrNet, CorrNet+ achieves a significant performance boost across all benchmarks while halving the computational overhead. A comprehensive comparison with previous spatial-temporal reasoning methods verifies the superiority of CorrNet+. Code is available at https://github.com/hulianyuyy/CorrNet_Plus.
Authors: Xueyuan Gong, Yain-whar Si, Zheng Zhang, Xiaochen Yuan, Ke Wang, Xinyuan Zhang, Cong Lin, Xiaoxiang Liu
Abstract: Face recognition (FR) has seen significant advancements due to the utilization of large-scale datasets. Training deep FR models on large-scale datasets with multiple GPUs is now a common practice. In fact, computing power has evolved into a foundational and indispensable resource in the area of deep learning. It is nearly impossible to train a deep FR model without holding adequate hardware resources. Recognizing this challenge, some FR approaches have started exploring ways to reduce the time complexity of the fully-connected layer in FR models. Unlike other approaches, this paper introduces a simple yet highly effective approach, Moving Haar Learning Rate (MHLR) scheduler, for scheduling the learning rate promptly and accurately in the training process. MHLR supports large-scale FR training with only one GPU, which is able to accelerate the model to 1/4 of its original training time without sacrificing more than 1% accuracy. More specifically, MHLR only needs $30$ hours to train the model ResNet100 on the dataset WebFace12M containing more than 12M face images with 0.6M identities. Extensive experiments validate the efficiency and effectiveness of MHLR.
Authors: Sherry X. Chen, Yaron Vaxman, Elad Ben Baruch, David Asulin, Aviad Moreshet, Kuo-Chin Lien, Misha Sra, Pradeep Sen
Abstract: Despite many attempts to leverage pre-trained text-to-image models (T2I) like Stable Diffusion (SD) for controllable image editing, producing good predictable results remains a challenge. Previous approaches have focused on either fine-tuning pre-trained T2I models on specific datasets to generate certain kinds of images (e.g., with a specific object or person), or on optimizing the weights, text prompts, and/or learning features for each input image in an attempt to coax the image generator to produce the desired result. However, these approaches all have shortcomings and fail to produce good results in a predictable and controllable manner. To address this problem, we present TiNO-Edit, an SD-based method that focuses on optimizing the noise patterns and diffusion timesteps during editing, something previously unexplored in the literature. With this simple change, we are able to generate results that both better align with the original images and reflect the desired result. Furthermore, we propose a set of new loss functions that operate in the latent domain of SD, greatly speeding up the optimization when compared to prior approaches, which operate in the pixel domain. Our method can be easily applied to variations of SD including Textual Inversion and DreamBooth that encode new concepts and incorporate them into the edited results. We present a host of image-editing capabilities enabled by our approach. Our code is publicly available at https://github.com/SherryXTChen/TiNO-Edit.
Authors: Jiaxing Zhao, Peng Zheng, Rui Ma
Abstract: Creating large LiDAR datasets with pixel-level labeling poses significant challenges. While numerous data augmentation methods have been developed to reduce the reliance on manual labeling, these methods predominantly focus on static scenes and they overlook the importance of data augmentation for dynamic scenes, which is critical for autonomous driving. To address this issue, we propose D-Aug, a LiDAR data augmentation method tailored for augmenting dynamic scenes. D-Aug extracts objects and inserts them into dynamic scenes, considering the continuity of these objects across consecutive frames. For seamless insertion into dynamic scenes, we propose a reference-guided method that involves dynamic collision detection and rotation alignment. Additionally, we present a pixel-level road identification strategy to efficiently determine suitable insertion positions. We validated our method using the nuScenes dataset with various 3D detection and tracking methods. Comparative experiments demonstrate the superiority of D-Aug.
Authors: Minghe Gao, Shuang Chen, Liang Pang, Yuan Yao, Jisheng Dang, Wenqiao Zhang, Juncheng Li, Siliang Tang, Yueting Zhuang, Tat-Seng Chua
Abstract: The remarkable performance of Multimodal Large Language Models (MLLMs) has unequivocally demonstrated their proficient understanding capabilities in handling a wide array of visual tasks. Nevertheless, the opaque nature of their black-box reasoning processes persists as an enigma, rendering them uninterpretable and struggling with hallucination. Their ability to execute intricate compositional reasoning tasks is also constrained, culminating in a stagnation of learning progression for these models. In this work, we introduce Fact, a novel paradigm designed to generate multimodal rationales that are faithful, concise, and transferable for teaching MLLMs. This paradigm utilizes verifiable visual programming to generate executable code guaranteeing faithfulness and precision. Subsequently, through a series of operations including pruning, merging, and bridging, the rationale enhances its conciseness. Furthermore, we filter rationales that can be transferred to end-to-end paradigms from programming paradigms to guarantee transferability. Empirical evidence from experiments demonstrates the superiority of our method across models of varying parameter sizes, significantly enhancing their compositional reasoning and generalization ability. Our approach also reduces hallucinations owing to its high correlation between images and text.
Authors: Linfang Zheng, Tze Ho Elden Tse, Chen Wang, Yinghan Sun, Hua Chen, Ales Leonardis, Wei Zhang
Abstract: Object pose refinement is essential for robust object pose estimation. Previous work has made significant progress towards instance-level object pose refinement. Yet, category-level pose refinement is a more challenging problem due to large shape variations within a category and the discrepancies between the target object and the shape prior. To address these challenges, we introduce a novel architecture for category-level object pose refinement. Our approach integrates an HS-layer and learnable affine transformations, which aims to enhance the extraction and alignment of geometric information. Additionally, we introduce a cross-cloud transformation mechanism that efficiently merges diverse data sources. Finally, we push the limits of our model by incorporating the shape prior information for translation and size error prediction. We conducted extensive experiments to demonstrate the effectiveness of the proposed framework. Through extensive quantitative experiments, we demonstrate significant improvement over the baseline method by a large margin across all metrics.
Authors: Chaoyue Song, Jiacheng Wei, Chuan-Sheng Foo, Guosheng Lin, Fayao Liu
Abstract: In this paper, we address the challenge of reconstructing general articulated 3D objects from a single video. Existing works employing dynamic neural radiance fields have advanced the modeling of articulated objects like humans and animals from videos, but face challenges with piece-wise rigid general articulated objects due to limitations in their deformation models. To tackle this, we propose Quasi-Rigid Blend Skinning, a novel deformation model that enhances the rigidity of each part while maintaining flexible deformation of the joints. Our primary insight combines three distinct approaches: 1) an enhanced bone rigging system for improved component modeling, 2) the use of quasi-sparse skinning weights to boost part rigidity and reconstruction fidelity, and 3) the application of geodesic point assignment for precise motion and seamless deformation. Our method outperforms previous works in producing higher-fidelity 3D reconstructions of general articulated objects, as demonstrated on both real and synthetic datasets. Project page: https://chaoyuesong.github.io/REACTO.
Authors: Chi Zhang, Qi Song, Feifei Li, Yongquan Chen, Rui Huang
Abstract: Constructing vectorized high-definition maps from surround-view cameras has garnered significant attention in recent years. However, the commonly employed multi-stage sequential workflow in prevailing approaches often leads to the loss of early-stage information, particularly in perspective-view features. Usually, such loss is observed as an instance missing or shape mismatching in the final birds-eye-view predictions. To address this concern, we propose a novel approach, namely \textbf{HybriMap}, which effectively exploits clues from hybrid features to ensure the delivery of valuable information. Specifically, we design the Dual Enhancement Module, to enable both explicit integration and implicit modification under the guidance of hybrid features. Additionally, the perspective keypoints are utilized as supervision, further directing the feature enhancement process. Extensive experiments conducted on existing benchmarks have demonstrated the state-of-the-art performance of our proposed approach.
Authors: Chunghyun Park, Seungwook Sim, Jaesik Park, Minsu Cho
Abstract: Establishing accurate 3D correspondences between shapes stands as a pivotal challenge with profound implications for computer vision and robotics. However, existing self-supervised methods for this problem assume perfect input shape alignment, restricting their real-world applicability. In this work, we introduce a novel self-supervised Rotation-Invariant 3D correspondence learner with Local Shape Transform, dubbed RIST, that learns to establish dense correspondences between shapes even under challenging intra-class variations and arbitrary orientations. Specifically, RIST learns to dynamically formulate an SO(3)-invariant local shape transform for each point, which maps the SO(3)-equivariant global shape descriptor of the input shape to a local shape descriptor. These local shape descriptors are provided as inputs to our decoder to facilitate point cloud self- and cross-reconstruction. Our proposed self-supervised training pipeline encourages semantically corresponding points from different shapes to be mapped to similar local shape descriptors, enabling RIST to establish dense point-wise correspondences. RIST demonstrates state-of-the-art performances on 3D part label transfer and semantic keypoint transfer given arbitrarily rotated point cloud pairs, outperforming existing methods by significant margins.
Authors: Nicolas Chahine, Marcos V. Conde, Daniela Carfora, Gabriel Pacianotto, Benoit Pochon, Sira Ferradans, Radu Timofte
Abstract: This paper reviews the NTIRE 2024 Portrait Quality Assessment Challenge, highlighting the proposed solutions and results. This challenge aims to obtain an efficient deep neural network capable of estimating the perceptual quality of real portrait photos. The methods must generalize to diverse scenes and diverse lighting conditions (indoor, outdoor, low-light), movement, blur, and other challenging conditions. In the challenge, 140 participants registered, and 35 submitted results during the challenge period. The performance of the top 5 submissions is reviewed and provided here as a gauge for the current state-of-the-art in Portrait Quality Assessment.
Authors: Jun Wang, Yufei Cui, Yu Mao, Nan Guan, Chun Jason Xue
Abstract: Pre-processing for whole slide images can affect classification performance both in the training and inference stages. Our study analyzes the impact of pre-processing parameters on inference and training across single- and multiple-domain datasets. However, searching for an optimal parameter set is time-consuming. To overcome this, we propose a novel Similarity-based Simulated Annealing approach for fast parameter tuning to enhance inference performance on single-domain data. Our method demonstrates significant performance improvements in accuracy, which raise accuracy from 0.512 to 0.847 in a single domain. We further extend our insight into training performance in multi-domain data by employing a novel Bayesian optimization to search optimal pre-processing parameters, resulting in a high AUC of 0.967. We highlight that better pre-processing for WSI can contribute to further accuracy improvement in the histology area.
Authors: Zhenhua Liu, Zhiwei Hao, Kai Han, Yehui Tang, Yunhe Wang
Abstract: Compact neural networks are specially designed for applications on edge devices with faster inference speed yet modest performance. However, training strategies of compact models are borrowed from that of conventional models at present, which ignores their difference in model capacity and thus may impede the performance of compact models. In this paper, by systematically investigating the impact of different training ingredients, we introduce a strong training strategy for compact models. We find that the appropriate designs of re-parameterization and knowledge distillation are crucial for training high-performance compact models, while some commonly used data augmentations for training conventional models, such as Mixup and CutMix, lead to worse performance. Our experiments on ImageNet-1K dataset demonstrate that our specialized training strategy for compact models is applicable to various architectures, including GhostNetV2, MobileNetV2 and ShuffleNetV2. Specifically, equipped with our strategy, GhostNetV3 1.3$\times$ achieves a top-1 accuracy of 79.1% with only 269M FLOPs and a latency of 14.46ms on mobile devices, surpassing its ordinarily trained counterpart by a large margin. Moreover, our observation can also be extended to object detection scenarios. PyTorch code and checkpoints can be found at https://github.com/huawei-noah/Efficient-AI-Backbones/tree/master/ghostnetv3_pytorch.
URLs: https://github.com/huawei-noah/Efficient-AI-Backbones/tree/master/ghostnetv3_pytorch.
Authors: Kavitha Raju, Nandini J. Warrier
Abstract: The Indian classical dance-drama Kathakali has a set of hand gestures called Mudras, which form the fundamental units of all its dance moves and postures. Recognizing the depicted mudra becomes one of the first steps in its digital processing. The work treats the problem as a 24-class classification task and proposes a vector-similarity-based approach using pose estimation, eliminating the need for further training or fine-tuning. This approach overcomes the challenge of data scarcity that limits the application of AI in similar domains. The method attains 92% accuracy which is a similar or better performance as other model-training-based works existing in the domain, with the added advantage that the method can still work with data sizes as small as 1 or 5 samples with a slightly reduced performance. Working with images, videos, and even real-time streams is possible. The system can work with hand-cropped or full-body images alike. We have developed and made public a dataset for the Kathakali Mudra Recognition as part of this work.
Authors: Yichi Zhang, Yinpeng Dong, Siyuan Zhang, Tianzan Min, Hang Su, Jun Zhu
Abstract: Although Multimodal Large Language Models (MLLMs) have demonstrated promising versatile capabilities, their performance is still inferior to specialized models on downstream tasks, which makes adaptation necessary to enhance their utility. However, fine-tuning methods require independent training for every model, leading to huge computation and memory overheads. In this paper, we propose a novel setting where we aim to improve the performance of diverse MLLMs with a group of shared parameters optimized for a downstream task. To achieve this, we propose Transferable Visual Prompting (TVP), a simple and effective approach to generate visual prompts that can transfer to different models and improve their performance on downstream tasks after trained on only one model. We introduce two strategies to address the issue of cross-model feature corruption of existing visual prompting methods and enhance the transferability of the learned prompts, including 1) Feature Consistency Alignment: which imposes constraints to the prompted feature changes to maintain task-agnostic knowledge; 2) Task Semantics Enrichment: which encourages the prompted images to contain richer task-specific semantics with language guidance. We validate the effectiveness of TVP through extensive experiments with 6 modern MLLMs on a wide variety of tasks ranging from object recognition and counting to multimodal reasoning and hallucination correction.
Authors: Chuheng Wei, Guoyuan Wu, Matthew J. Barth
Abstract: A significant challenge in the field of object detection lies in the system's performance under non-ideal imaging conditions, such as rain, fog, low illumination, or raw Bayer images that lack ISP processing. Our study introduces "Feature Corrective Transfer Learning", a novel approach that leverages transfer learning and a bespoke loss function to facilitate the end-to-end detection of objects in these challenging scenarios without the need to convert non-ideal images into their RGB counterparts. In our methodology, we initially train a comprehensive model on a pristine RGB image dataset. Subsequently, non-ideal images are processed by comparing their feature maps against those from the initial ideal RGB model. This comparison employs the Extended Area Novel Structural Discrepancy Loss (EANSDL), a novel loss function designed to quantify similarities and integrate them into the detection loss. This approach refines the model's ability to perform object detection across varying conditions through direct feature map correction, encapsulating the essence of Feature Corrective Transfer Learning. Experimental validation on variants of the KITTI dataset demonstrates a significant improvement in mean Average Precision (mAP), resulting in a 3.8-8.1% relative enhancement in detection under non-ideal conditions compared to the baseline model, and a less marginal performance difference within 1.3% of the mAP@[0.5:0.95] achieved under ideal conditions by the standard Faster RCNN algorithm.
Authors: Munkh-Erdene Otgonbold, Ganzorig Batnasan, Munkhjargal Gochoo
Abstract: Motivated by the need to improve model performance in traffic monitoring tasks with limited labeled samples, we propose a straightforward augmentation technique tailored for object detection datasets, specifically designed for stationary camera-based applications. Our approach focuses on placing objects in the same positions as the originals to ensure its effectiveness. By applying in-place augmentation on objects from the same camera input image, we address the challenge of overlapping with original and previously selected objects. Through extensive testing on two traffic monitoring datasets, we illustrate the efficacy of our augmentation strategy in improving model performance, particularly in scenarios with limited labeled samples and imbalanced class distributions. Notably, our method achieves comparable performance to models trained on the entire dataset while utilizing only 8.5 percent of the original data. Moreover, we report significant improvements, with mAP@.5 increasing from 0.4798 to 0.5025, and the mAP@.5:.95 rising from 0.29 to 0.3138 on the FishEye8K dataset. These results highlight the potential of our augmentation approach in enhancing object detection models for traffic monitoring applications.
Authors: Muhammad Zawish, Paul Albert, Flavio Esposito, Steven Davy, Lizy Abraham
Abstract: Clover fixates nitrogen from the atmosphere to the ground, making grass-clover mixtures highly desirable to reduce external nitrogen fertilization. Herbage containing clover additionally promotes higher food intake, resulting in higher milk production. Herbage probing however remains largely unused as it requires a time-intensive manual laboratory analysis. Without this information, farmers are unable to perform localized clover sowing or take targeted fertilization decisions. Deep learning algorithms have been proposed with the goal to estimate the dry biomass composition from images of the grass directly in the fields. The energy-intensive nature of deep learning however limits deployment to practical edge devices such as smartphones. This paper proposes to fill this gap by applying filter pruning to reduce the energy requirement of existing deep learning solutions. We report that although pruned networks are accurate on controlled, high-quality images of the grass, they struggle to generalize to real-world smartphone images that are blurry or taken from challenging angles. We address this challenge by training filter-pruned models using a variance attenuation loss so they can predict the uncertainty of their predictions. When the uncertainty exceeds a threshold, we re-infer using a more accurate unpruned model. This hybrid approach allows us to reduce energy consumption while retaining a high accuracy. We evaluate our algorithm on two datasets: the GrassClover and the Irish clover using an NVIDIA Jetson Nano edge device. We find that we reduce energy reduction with respect to state-of-the-art solutions by 50% on average with only 4% accuracy loss.
Authors: Nicol\`o Di Domenico, Guido Borghi, Annalisa Franco, Davide Maltoni
Abstract: Nowadays, state-of-the-art AI-based generative models represent a viable solution to overcome privacy issues and biases in the collection of datasets containing personal information, such as faces. Following this intuition, in this paper we introduce ONOT, a synthetic dataset specifically focused on the generation of high-quality faces in adherence to the requirements of the ISO/IEC 39794-5 standards that, following the guidelines of the International Civil Aviation Organization (ICAO), defines the interchange formats of face images in electronic Machine-Readable Travel Documents (eMRTD). The strictly controlled and varied mugshot images included in ONOT are useful in research fields related to the analysis of face images in eMRTD, such as Morphing Attack Detection and Face Quality Assessment. The dataset is publicly released, in combination with the generation procedure details in order to improve the reproducibility and enable future extensions.
Authors: Jo\~ao Gabriel Vinholi, Marco Chini, Anis Amziane, Renato Machado, Danilo Silva, Patrick Matgen
Abstract: We introduce an innovative deep learning-based method that uses a denoising diffusion-based model to translate low-resolution images to high-resolution ones from different optical sensors while preserving the contents and avoiding undesired artifacts. The proposed method is trained and tested on a large and diverse data set of paired Sentinel-II and Planet Dove images. We show that it can solve serious image generation issues observed when the popular classifier-free guided Denoising Diffusion Implicit Model (DDIM) framework is used in the task of Image-to-Image Translation of multi-sensor optical remote sensing images and that it can generate large images with highly consistent patches, both in colors and in features. Moreover, we demonstrate how our method improves heterogeneous change detection results in two urban areas: Beirut, Lebanon, and Austin, USA. Our contributions are: i) a new training and testing algorithm based on denoising diffusion models for optical image translation; ii) a comprehensive image quality evaluation and ablation study; iii) a comparison with the classifier-free guided DDIM framework; and iv) change detection experiments on heterogeneous data.
Authors: Wenbo Zhang, Yifan Zhang, Jianfeng Lin, Binqiang Huang, Jinlu Zhang, Wenhao Yu
Abstract: Pre-trained vision-language (V-L) models such as CLIP have shown excellent performance in many downstream cross-modal tasks. However, most of them are only applicable to the English context. Subsequent research has focused on this problem and proposed improved models, such as CN-CLIP and AltCLIP, to facilitate their applicability to Chinese and even other languages. Nevertheless, these models suffer from high latency and a large memory footprint in inference, which limits their further deployment on resource-constrained edge devices. In this work, we propose a conceptually simple yet effective multilingual CLIP Compression framework and train a lightweight multilingual vision-language model, called DC-CLIP, for both Chinese and English context. In this framework, we collect high-quality Chinese and English text-image pairs and design two training stages, including multilingual vision-language feature distillation and alignment. During the first stage, lightweight image/text student models are designed to learn robust visual/multilingual textual feature representation ability from corresponding teacher models, respectively. Subsequently, the multilingual vision-language alignment stage enables effective alignment of visual and multilingual textual features to further improve the model's multilingual performance. Comprehensive experiments in zero-shot image classification, conducted based on the ELEVATER benchmark, showcase that DC-CLIP achieves superior performance in the English context and competitive performance in the Chinese context, even with less training data, when compared to existing models of similar parameter magnitude. The evaluation demonstrates the effectiveness of our designed training mechanism.
Authors: Xuesong Li, Zeeshan Hayder, Ali Zia, Connor Cassidy, Shiming Liu, Warwick Stiller, Eric Stone, Warren Conaty, Lars Petersson, Vivien Rolland
Abstract: Crop biomass, a critical indicator of plant growth, health, and productivity, is invaluable for crop breeding programs and agronomic research. However, the accurate and scalable quantification of crop biomass remains inaccessible due to limitations in existing measurement methods. One of the obstacles impeding the advancement of current crop biomass prediction methodologies is the scarcity of publicly available datasets. Addressing this gap, we introduce a new dataset in this domain, i.e. Multi-modality dataset for crop biomass estimation (MMCBE). Comprising 216 sets of multi-view drone images, coupled with LiDAR point clouds, and hand-labelled ground truth, MMCBE represents the first multi-modality one in the field. This dataset aims to establish benchmark methods for crop biomass quantification and foster the development of vision-based approaches. We have rigorously evaluated state-of-the-art crop biomass estimation methods using MMCBE and ventured into additional potential applications, such as 3D crop reconstruction from drone imagery and novel-view rendering. With this publication, we are making our comprehensive dataset available to the broader community.
Authors: Zixuan Zhu, Rui Wang, Cong Zou, Lihua Jing
Abstract: Recently, backdoor attacks have posed a serious security threat to the training process of deep neural networks (DNNs). The attacked model behaves normally on benign samples but outputs a specific result when the trigger is present. However, compared with the rocketing progress of backdoor attacks, existing defenses are difficult to deal with these threats effectively or require benign samples to work, which may be unavailable in real scenarios. In this paper, we find that the poisoned samples and benign samples can be distinguished with prediction entropy. This inspires us to propose a novel dual-network training framework: The Victim and The Beneficiary (V&B), which exploits a poisoned model to train a clean model without extra benign samples. Firstly, we sacrifice the Victim network to be a powerful poisoned sample detector by training on suspicious samples. Secondly, we train the Beneficiary network on the credible samples selected by the Victim to inhibit backdoor injection. Thirdly, a semi-supervised suppression strategy is adopted for erasing potential backdoors and improving model performance. Furthermore, to better inhibit missed poisoned samples, we propose a strong data augmentation method, AttentionMix, which works well with our proposed V&B framework. Extensive experiments on two widely used datasets against 6 state-of-the-art attacks demonstrate that our framework is effective in preventing backdoor injection and robust to various attacks while maintaining the performance on benign samples. Our code is available at https://github.com/Zixuan-Zhu/VaB.
Authors: Florian Heidecker, Ahmad El-Khateeb, Maarten Bieshaar, Bernhard Sick
Abstract: The operating environment of a highly automated vehicle is subject to change, e.g., weather, illumination, or the scenario containing different objects and other participants in which the highly automated vehicle has to navigate its passengers safely. These situations must be considered when developing and validating highly automated driving functions. This already poses a problem for training and evaluating deep learning models because without the costly labeling of thousands of recordings, not knowing whether the data contains relevant, interesting data for further model training, it is a guess under which conditions and situations the model performs poorly. For this purpose, we present corner case criteria based on the predictive uncertainty. With our corner case criteria, we are able to detect uncertainty-based corner cases of an object instance segmentation model without relying on ground truth (GT) data. We evaluated each corner case criterion using the COCO and the NuImages dataset to analyze the potential of our approach. We also provide a corner case decision function that allows us to distinguish each object into True Positive (TP), localization and/or classification corner case, or False Positive (FP). We also present our first results of an iterative training cycle that outperforms the baseline and where the data added to the training dataset is selected based on the corner case decision function.
Authors: Buzhen Huang, Chen Li, Chongyang Xu, Liang Pan, Yangang Wang, Gim Hee Lee
Abstract: Existing multi-person human reconstruction approaches mainly focus on recovering accurate poses or avoiding penetration, but overlook the modeling of close interactions. In this work, we tackle the task of reconstructing closely interactive humans from a monocular video. The main challenge of this task comes from insufficient visual information caused by depth ambiguity and severe inter-person occlusion. In view of this, we propose to leverage knowledge from proxemic behavior and physics to compensate the lack of visual information. This is based on the observation that human interaction has specific patterns following the social proxemics. Specifically, we first design a latent representation based on Vector Quantised-Variational AutoEncoder (VQ-VAE) to model human interaction. A proxemics and physics guided diffusion model is then introduced to denoise the initial distribution. We design the diffusion model as dual branch with each branch representing one individual such that the interaction can be modeled via cross attention. With the learned priors of VQ-VAE and physical constraint as the additional information, our proposed approach is capable of estimating accurate poses that are also proxemics and physics plausible. Experimental results on Hi4D, 3DPW, and CHI3D demonstrate that our method outperforms existing approaches. The code is available at \url{https://github.com/boycehbz/HumanInteraction}.
Authors: Nikolaos Dionelis, Francesco Pro, Luca Maiano, Irene Amerini, Bertrand Le Saux
Abstract: Data from satellites or aerial vehicles are most of the times unlabelled. Annotating such data accurately is difficult, requires expertise, and is costly in terms of time. Even if Earth Observation (EO) data were correctly labelled, labels might change over time. Learning from unlabelled data within a semi-supervised learning framework for segmentation of aerial images is challenging. In this paper, we develop a new model for semantic segmentation of unlabelled images, the Non-annotated Earth Observation Semantic Segmentation (NEOS) model. NEOS performs domain adaptation as the target domain does not have ground truth semantic segmentation masks. The distribution inconsistencies between the target and source domains are due to differences in acquisition scenes, environment conditions, sensors, and times. Our model aligns the learned representations of the different domains to make them coincide. The evaluation results show that NEOS is successful and outperforms other models for semantic segmentation of unlabelled data.
Authors: Francesco Pro, Nikolaos Dionelis, Luca Maiano, Bertrand Le Saux, Irene Amerini
Abstract: Nowadays the accurate geo-localization of ground-view images has an important role across domains as diverse as journalism, forensics analysis, transports, and Earth Observation. This work addresses the problem of matching a query ground-view image with the corresponding satellite image without GPS data. This is done by comparing the features from a ground-view image and a satellite one, innovatively leveraging the corresponding latter's segmentation mask through a three-stream Siamese-like network. The proposed method, Semantic Align Net (SAN), focuses on limited Field-of-View (FoV) and ground panorama images (images with a FoV of 360{\deg}). The novelty lies in the fusion of satellite images in combination with their semantic segmentation masks, aimed at ensuring that the model can extract useful features and focus on the significant parts of the images. This work shows how SAN through semantic analysis of images improves the performance on the unlabelled CVUSA dataset for all the tested FoVs.
Authors: Hanlin Mo, Guoying Zhao
Abstract: Achieving rotation invariance in deep neural networks without relying on data has always been a hot research topic. Intrinsic rotation invariance can enhance the model's feature representation capability, enabling better performance in tasks such as multi-orientation object recognition and detection. Based on various types of non-learnable operators, including gradient, sort, local binary pattern, maximum, etc., this paper designs a set of new convolution operations that are natually invariant to arbitrary rotations. Unlike most previous studies, these rotation-invariant convolutions (RIConvs) have the same number of learnable parameters and a similar computational process as conventional convolution operations, allowing them to be interchangeable. Using the MNIST-Rot dataset, we first verify the invariance of these RIConvs under various rotation angles and compare their performance with previous rotation-invariant convolutional neural networks (RI-CNNs). Two types of RIConvs based on gradient operators achieve state-of-the-art results. Subsequently, we combine RIConvs with different types and depths of classic CNN backbones. Using the OuTex_00012, MTARSI, and NWPU-RESISC-45 datasets, we test their performance on texture recognition, aircraft type recognition, and remote sensing image classification tasks. The results show that RIConvs significantly improve the accuracy of these CNN backbones, especially when the training data is limited. Furthermore, we find that even with data augmentation, RIConvs can further enhance model performance.
Authors: Zhangchi Feng, Richong Zhang, Zhijie Nie
Abstract: The Composed Image Retrieval (CIR) task aims to retrieve target images using a composed query consisting of a reference image and a modified text. Advanced methods often utilize contrastive learning as the optimization objective, which benefits from adequate positive and negative examples. However, the triplet for CIR incurs high manual annotation costs, resulting in limited positive examples. Furthermore, existing methods commonly use in-batch negative sampling, which reduces the negative number available for the model. To address the problem of lack of positives, we propose a data generation method by leveraging a multi-modal large language model to construct triplets for CIR. To introduce more negatives during fine-tuning, we design a two-stage fine-tuning framework for CIR, whose second stage introduces plenty of static representations of negatives to optimize the representation space rapidly. The above two improvements can be effectively stacked and designed to be plug-and-play, easily applied to existing CIR models without changing their original architectures. Extensive experiments and ablation analysis demonstrate that our method effectively scales positives and negatives and achieves state-of-the-art results on both FashionIQ and CIRR datasets. In addition, our methods also perform well in zero-shot composed image retrieval, providing a new CIR solution for the low-resources scenario.
Authors: Qiangang Du, Jinlong Peng, Changan Wang, Xu Chen, Qingdong He, Wenbing Zhu, Mingmin Chi, Yabiao Wang, Chengjie Wang
Abstract: Change detection aims to identify remote sense object changes by analyzing data between bitemporal image pairs. Due to the large temporal and spatial span of data collection in change detection image pairs, there are often a significant amount of task-specific and task-agnostic noise. Previous effort has focused excessively on denoising, with this goes a great deal of loss of fine-grained information. In this paper, we revisit the importance of fine-grained features in change detection and propose a series of operations for fine-grained information compensation and noise decoupling (FINO). First, the context is utilized to compensate for the fine-grained information in the feature space. Next, a shape-aware and a brightness-aware module are designed to improve the capacity for representation learning. The shape-aware module guides the backbone for more precise shape estimation, guiding the backbone network in extracting object shape features. The brightness-aware module learns a overall brightness estimation to improve the model's robustness to task-agnostic noise. Finally, a task-specific noise decoupling structure is designed as a way to improve the model's ability to separate noise interference from feature similarity. With these training schemes, our proposed method achieves new state-of-the-art (SOTA) results in multiple change detection benchmarks. The code will be made available.
Authors: Leonardo Brizi, Emanuele Giacomini, Luca Di Giammarino, Simone Ferrari, Omar Salem, Lorenzo De Rebotti, Giorgio Grisetti
Abstract: This paper presents a vision and perception research dataset collected in Rome, featuring RGB data, 3D point clouds, IMU, and GPS data. We introduce a new benchmark targeting visual odometry and SLAM, to advance the research in autonomous robotics and computer vision. This work complements existing datasets by simultaneously addressing several issues, such as environment diversity, motion patterns, and sensor frequency. It uses up-to-date devices and presents effective procedures to accurately calibrate the intrinsic and extrinsic of the sensors while addressing temporal synchronization. During recording, we cover multi-floor buildings, gardens, urban and highway scenarios. Combining handheld and car-based data collections, our setup can simulate any robot (quadrupeds, quadrotors, autonomous vehicles). The dataset includes an accurate 6-dof ground truth based on a novel methodology that refines the RTK-GPS estimate with LiDAR point clouds through Bundle Adjustment. All sequences divided in training and testing are accessible through our website.
Authors: Qiangang Du, Jinlong Peng, Xu Chen, Qingdong He, Qiang Nie, Wenbing Zhu, Mingmin Chi, Yabiao Wang, Chengjie Wang
Abstract: Change detection is widely applied in remote sensing image analysis. Existing methods require training models separately for each dataset, which leads to poor domain generalization. Moreover, these methods rely heavily on large amounts of high-quality pair-labelled data for training, which is expensive and impractical. In this paper, we propose a multimodal contrastive learning (ChangeCLIP) based on visual-language pre-training for change detection domain generalization. Additionally, we propose a dynamic context optimization for prompt learning. Meanwhile, to address the data dependency issue of existing methods, we introduce a single-temporal and controllable AI-generated training strategy (SAIN). This allows us to train the model using a large number of single-temporal images without image pairs in the real world, achieving excellent generalization. Extensive experiments on series of real change detection datasets validate the superiority and strong generalization of ChangeCLIP, outperforming state-of-the-art change detection methods. Code will be available.
Authors: Vladimir Somers, Victor Joos, Anthony Cioppa, Silvio Giancola, Seyed Abolfazl Ghasemzadeh, Floriane Magera, Baptiste Standaert, Amir Mohammad Mansourian, Xin Zhou, Shohreh Kasaei, Bernard Ghanem, Alexandre Alahi, Marc Van Droogenbroeck, Christophe De Vleeschouwer
Abstract: Tracking and identifying athletes on the pitch holds a central role in collecting essential insights from the game, such as estimating the total distance covered by players or understanding team tactics. This tracking and identification process is crucial for reconstructing the game state, defined by the athletes' positions and identities on a 2D top-view of the pitch, (i.e. a minimap). However, reconstructing the game state from videos captured by a single camera is challenging. It requires understanding the position of the athletes and the viewpoint of the camera to localize and identify players within the field. In this work, we formalize the task of Game State Reconstruction and introduce SoccerNet-GSR, a novel Game State Reconstruction dataset focusing on football videos. SoccerNet-GSR is composed of 200 video sequences of 30 seconds, annotated with 9.37 million line points for pitch localization and camera calibration, as well as over 2.36 million athlete positions on the pitch with their respective role, team, and jersey number. Furthermore, we introduce GS-HOTA, a novel metric to evaluate game state reconstruction methods. Finally, we propose and release an end-to-end baseline for game state reconstruction, bootstrapping the research on this task. Our experiments show that GSR is a challenging novel task, which opens the field for future research. Our dataset and codebase are publicly available at https://github.com/SoccerNet/sn-gamestate.
Authors: George Retsinas, Giorgos Sfikas, Basilis Gatos, Christophoros Nikou
Abstract: Handwritten text recognition has been developed rapidly in the recent years, following the rise of deep learning and its applications. Though deep learning methods provide notable boost in performance concerning text recognition, non-trivial deviation in performance can be detected even when small pre-processing or architectural/optimization elements are changed. This work follows a ``best practice'' rationale; highlight simple yet effective empirical practices that can further help training and provide well-performing handwritten text recognition systems. Specifically, we considered three basic aspects of a deep HTR system and we proposed simple yet effective solutions: 1) retain the aspect ratio of the images in the preprocessing step, 2) use max-pooling for converting the 3D feature map of CNN output into a sequence of features and 3) assist the training procedure via an additional CTC loss which acts as a shortcut on the max-pooled sequential features. Using these proposed simple modifications, one can attain close to state-of-the-art results, while considering a basic convolutional-recurrent (CNN+LSTM) architecture, for both IAM and RIMES datasets. Code is available at https://github.com/georgeretsi/HTR-best-practices/.
Authors: Ziyu Zhou, Wenyuan Shen, Chang Liu
Abstract: Colorectal cancer (CRC), which frequently originates from initially benign polyps, remains a significant contributor to global cancer-related mortality. Early and accurate detection of these polyps via colonoscopy is crucial for CRC prevention. However, traditional colonoscopy methods depend heavily on the operator's experience, leading to suboptimal polyp detection rates. Besides, the public database are limited in polyp size and shape diversity. To enhance the available data for polyp detection, we introduce Consisaug, an innovative and effective methodology to augment data that leverages deep learning. We utilize the constraint that when the image is flipped the class label should be equal and the bonding boxes should be consistent. We implement our Consisaug on five public polyp datasets and at three backbones, and the results show the effectiveness of our method.
Authors: Hangtao Zhang, Shengshan Hu, Yichen Wang, Leo Yu Zhang, Ziqi Zhou, Xianlong Wang, Yanjun Zhang, Chao Chen
Abstract: Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techniques have primarily been adapted from classification tasks, overlooking deeper vulnerabilities specific to object detection. This paper is dedicated to bridging this gap by introducing Detector Collapse} (DC), a brand-new backdoor attack paradigm tailored for object detection. DC is designed to instantly incapacitate detectors (i.e., severely impairing detector's performance and culminating in a denial-of-service). To this end, we develop two innovative attack schemes: Sponge for triggering widespread misidentifications and Blinding for rendering objects invisible. Remarkably, we introduce a novel poisoning strategy exploiting natural objects, enabling DC to act as a practical backdoor in real-world environments. Our experiments on different detectors across several benchmarks show a significant improvement ($\sim$10\%-60\% absolute and $\sim$2-7$\times$ relative) in attack efficacy over state-of-the-art attacks.
Authors: Jeongtaek Oh, Jaeyoung Chung, Dongwoo Lee, Kyoung Mu Lee
Abstract: Although significant progress has been made in reconstructing sharp 3D scenes from motion-blurred images, a transition to real-world applications remains challenging. The primary obstacle stems from the severe blur which leads to inaccuracies in the acquisition of initial camera poses through Structure-from-Motion, a critical aspect often overlooked by previous approaches. To address this challenge, we propose DeblurGS, a method to optimize sharp 3D Gaussian Splatting from motion-blurred images, even with the noisy camera pose initialization. We restore a fine-grained sharp scene by leveraging the remarkable reconstruction capability of 3D Gaussian Splatting. Our approach estimates the 6-Degree-of-Freedom camera motion for each blurry observation and synthesizes corresponding blurry renderings for the optimization process. Furthermore, we propose Gaussian Densification Annealing strategy to prevent the generation of inaccurate Gaussians at erroneous locations during the early training stages when camera motion is still imprecise. Comprehensive experiments demonstrate that our DeblurGS achieves state-of-the-art performance in deblurring and novel view synthesis for real-world and synthetic benchmark datasets, as well as field-captured blurry smartphone videos.
Authors: Xinghan Wang, Zixi Kang, Yadong Mu
Abstract: Human motion understanding is a fundamental task with diverse practical applications, facilitated by the availability of large-scale motion capture datasets. Recent studies focus on text-motion tasks, such as text-based motion generation, editing and question answering. In this study, we introduce the novel task of text-based human motion grounding (THMG), aimed at precisely localizing temporal segments corresponding to given textual descriptions within untrimmed motion sequences. Capturing global temporal information is crucial for the THMG task. However, transformer-based models that rely on global temporal self-attention face challenges when handling long untrimmed sequences due to the quadratic computational cost. We address these challenges by proposing Text-controlled Motion Mamba (TM-Mamba), a unified model that integrates temporal global context, language query control, and spatial graph topology with only linear memory cost. The core of the model is a text-controlled selection mechanism which dynamically incorporates global temporal information based on text query. The model is further enhanced to be topology-aware through the integration of relational embeddings. For evaluation, we introduce BABEL-Grounding, the first text-motion dataset that provides detailed textual descriptions of human actions along with their corresponding temporal segments. Extensive evaluations demonstrate the effectiveness of TM-Mamba on BABEL-Grounding.
Authors: Xianqiang Lyu, Hui Liu, Junhui Hou
Abstract: We propose RainyScape, an unsupervised framework for reconstructing clean scenes from a collection of multi-view rainy images. RainyScape consists of two main modules: a neural rendering module and a rain-prediction module that incorporates a predictor network and a learnable latent embedding that captures the rain characteristics of the scene. Specifically, based on the spectral bias property of neural networks, we first optimize the neural rendering pipeline to obtain a low-frequency scene representation. Subsequently, we jointly optimize the two modules, driven by the proposed adaptive direction-sensitive gradient-based reconstruction loss, which encourages the network to distinguish between scene details and rain streaks, facilitating the propagation of gradients to the relevant components. Extensive experiments on both the classic neural radiance field and the recently proposed 3D Gaussian splatting demonstrate the superiority of our method in effectively eliminating rain streaks and rendering clean images, achieving state-of-the-art performance. The constructed high-quality dataset and source code will be publicly available.
Authors: Zihan Cao, Xiao Wu, Liang-Jian Deng
Abstract: Recent diffusion probabilistic models (DPM) in the field of pansharpening have been gradually gaining attention and have achieved state-of-the-art (SOTA) performance. In this paper, we identify shortcomings in directly applying DPMs to the task of pansharpening as an inverse problem: 1) initiating sampling directly from Gaussian noise neglects the low-resolution multispectral image (LRMS) as a prior; 2) low sampling efficiency often necessitates a higher number of sampling steps. We first reformulate pansharpening into the stochastic differential equation (SDE) form of an inverse problem. Building upon this, we propose a Schr\"odinger bridge matching method that addresses both issues. We design an efficient deep neural network architecture tailored for the proposed SB matching. In comparison to the well-established DL-regressive-based framework and the recent DPM framework, our method demonstrates SOTA performance with fewer sampling steps. Moreover, we discuss the relationship between SB matching and other methods based on SDEs and ordinary differential equations (ODEs), as well as its connection with optimal transport. Code will be available.
Authors: Vincent Cartillier, Grant Schindler, Irfan Essa
Abstract: We present SLAIM - Simultaneous Localization and Implicit Mapping. We propose a novel coarse-to-fine tracking model tailored for Neural Radiance Field SLAM (NeRF-SLAM) to achieve state-of-the-art tracking performance. Notably, existing NeRF-SLAM systems consistently exhibit inferior tracking performance compared to traditional SLAM algorithms. NeRF-SLAM methods solve camera tracking via image alignment and photometric bundle-adjustment. Such optimization processes are difficult to optimize due to the narrow basin of attraction of the optimization loss in image space (local minima) and the lack of initial correspondences. We mitigate these limitations by implementing a Gaussian pyramid filter on top of NeRF, facilitating a coarse-to-fine tracking optimization strategy. Furthermore, NeRF systems encounter challenges in converging to the right geometry with limited input views. While prior approaches use a Signed-Distance Function (SDF)-based NeRF and directly supervise SDF values by approximating ground truth SDF through depth measurements, this often results in suboptimal geometry. In contrast, our method employs a volume density representation and introduces a novel KL regularizer on the ray termination distribution, constraining scene geometry to consist of empty space and opaque surfaces. Our solution implements both local and global bundle-adjustment to produce a robust (coarse-to-fine) and accurate (KL regularizer) SLAM solution. We conduct experiments on multiple datasets (ScanNet, TUM, Replica) showing state-of-the-art results in tracking and in reconstruction accuracy.
Authors: Orcun Cetintas, Tim Meinhardt, Guillem Bras\'o, Laura Leal-Taix\'e
Abstract: Increasing the annotation efficiency of trajectory annotations from videos has the potential to enable the next generation of data-hungry tracking algorithms to thrive on large-scale datasets. Despite the importance of this task, there are currently very few works exploring how to efficiently label tracking datasets comprehensively. In this work, we introduce SPAM, a tracking data engine that provides high-quality labels with minimal human intervention. SPAM is built around two key insights: i) most tracking scenarios can be easily resolved. To take advantage of this, we utilize a pre-trained model to generate high-quality pseudo-labels, reserving human involvement for a smaller subset of more difficult instances; ii) handling the spatiotemporal dependencies of track annotations across time can be elegantly and efficiently formulated through graphs. Therefore, we use a unified graph formulation to address the annotation of both detections and identity association for tracks across time. Based on these insights, SPAM produces high-quality annotations with a fraction of ground truth labeling cost. We demonstrate that trackers trained on SPAM labels achieve comparable performance to those trained on human annotations while requiring only 3-20% of the human labeling effort. Hence, SPAM paves the way towards highly efficient labeling of large-scale tracking datasets. Our code and models will be available upon acceptance.
Authors: Minh Tran, Sang Truong, Arthur F. A. Fernandes, Michael T. Kidd, Ngan Le
Abstract: In the food industry, assessing the quality of poultry carcasses during processing is a crucial step. This study proposes an effective approach for automating the assessment of carcass quality without requiring skilled labor or inspector involvement. The proposed system is based on machine learning (ML) and computer vision (CV) techniques, enabling automated defect detection and carcass quality assessment. To this end, an end-to-end framework called CarcassFormer is introduced. It is built upon a Transformer-based architecture designed to effectively extract visual representations while simultaneously detecting, segmenting, and classifying poultry carcass defects. Our proposed framework is capable of analyzing imperfections resulting from production and transport welfare issues, as well as processing plant stunner, scalder, picker, and other equipment malfunctions. To benchmark the framework, a dataset of 7,321 images was initially acquired, which contained both single and multiple carcasses per image. In this study, the performance of the CarcassFormer system is compared with other state-of-the-art (SOTA) approaches for both classification, detection, and segmentation tasks. Through extensive quantitative experiments, our framework consistently outperforms existing methods, demonstrating remarkable improvements across various evaluation metrics such as AP, AP@50, and AP@75. Furthermore, the qualitative results highlight the strengths of CarcassFormer in capturing fine details, including feathers, and accurately localizing and segmenting carcasses with high precision. To facilitate further research and collaboration, the pre-trained model and source code of CarcassFormer is available for research purposes at: \url{https://github.com/UARK-AICV/CarcassFormer}.
Authors: Johannes Hoster, Sara Al-Sayed, Felix Biessmann, Alexander Glaser, Kristian Hildebrand, Igor Moric, Tuong Vy Nguyen
Abstract: Satellite imagery is regarded as a great opportunity for citizen-based monitoring of activities of interest. Relevant imagery may however not be available at sufficiently high resolution, quality, or cadence -- let alone be uniformly accessible to open-source analysts. This limits an assessment of the true long-term potential of citizen-based monitoring of nuclear activities using publicly available satellite imagery. In this article, we demonstrate how modern game engines combined with advanced machine-learning techniques can be used to generate synthetic imagery of sites of interest with the ability to choose relevant parameters upon request; these include time of day, cloud cover, season, or level of activity onsite. At the same time, resolution and off-nadir angle can be adjusted to simulate different characteristics of the satellite. While there are several possible use-cases for synthetic imagery, here we focus on its usefulness to support tabletop exercises in which simple monitoring scenarios can be examined to better understand verification capabilities enabled by new satellite constellations and very short revisit times.
Authors: Zhanjie Zhang, Quanwei Zhang, Huaizhong Lin, Wei Xing, Juncheng Mo, Shuaicheng Huang, Jinheng Xie, Guangyuan Li, Junsheng Luan, Lei Zhao, Dalong Zhang, Lixia Chen
Abstract: Artistic style transfer aims to transfer the learned artistic style onto an arbitrary content image, generating artistic stylized images. Existing generative adversarial network-based methods fail to generate highly realistic stylized images and always introduce obvious artifacts and disharmonious patterns. Recently, large-scale pre-trained diffusion models opened up a new way for generating highly realistic artistic stylized images. However, diffusion model-based methods generally fail to preserve the content structure of input content images well, introducing some undesired content structure and style patterns. To address the above problems, we propose a novel pre-trained diffusion-based artistic style transfer method, called LSAST, which can generate highly realistic artistic stylized images while preserving the content structure of input content images well, without bringing obvious artifacts and disharmonious style patterns. Specifically, we introduce a Step-aware and Layer-aware Prompt Space, a set of learnable prompts, which can learn the style information from the collection of artworks and dynamically adjusts the input images' content structure and style pattern. To train our prompt space, we propose a novel inversion method, called Step-ware and Layer-aware Prompt Inversion, which allows the prompt space to learn the style information of the artworks collection. In addition, we inject a pre-trained conditional branch of ControlNet into our LSAST, which further improved our framework's ability to maintain content structure. Extensive experiments demonstrate that our proposed method can generate more highly realistic artistic stylized images than the state-of-the-art artistic style transfer methods.
Authors: Hao-Wei Chen, Yu-Syuan Xu, Kelvin C. K. Chan, Hsien-Kai Kuo, Chun-Yi Lee, Ming-Hsuan Yang
Abstract: Existing image restoration approaches typically employ extensive networks specifically trained for designated degradations. Despite being effective, such methods inevitably entail considerable storage costs and computational overheads due to the reliance on task-specific networks. In this work, we go beyond this well-established framework and exploit the inherent commonalities among image restoration tasks. The primary objective is to identify components that are shareable across restoration tasks and augment the shared components with modules specifically trained for individual tasks. Towards this goal, we propose AdaIR, a novel framework that enables low storage cost and efficient training without sacrificing performance. Specifically, a generic restoration network is first constructed through self-supervised pre-training using synthetic degradations. Subsequent to the pre-training phase, adapters are trained to adapt the pre-trained network to specific degradations. AdaIR requires solely the training of lightweight, task-specific modules, ensuring a more efficient storage and training regimen. We have conducted extensive experiments to validate the effectiveness of AdaIR and analyze the influence of the pre-training strategy on discovering shareable components. Extensive experimental results show that AdaIR achieves outstanding results on multi-task restoration while utilizing significantly fewer parameters (1.9 MB) and less training time (7 hours) for each restoration task. The source codes and trained models will be released.
Authors: Luca Bompani, Manuele Rusci, Daniele Palossi, Francesco Conti, Luca Benini
Abstract: This paper introduces Multi-Resolution Rescored Byte-Track (MR2-ByteTrack), a novel video object detection framework for ultra-low-power embedded processors. This method reduces the average compute load of an off-the-shelf Deep Neural Network (DNN) based object detector by up to 2.25$\times$ by alternating the processing of high-resolution images (320$\times$320 pixels) with multiple down-sized frames (192$\times$192 pixels). To tackle the accuracy degradation due to the reduced image input size, MR2-ByteTrack correlates the output detections over time using the ByteTrack tracker and corrects potential misclassification using a novel probabilistic Rescore algorithm. By interleaving two down-sized images for every high-resolution one as the input of different state-of-the-art DNN object detectors with our MR2-ByteTrack, we demonstrate an average accuracy increase of 2.16% and a latency reduction of 43% on the GAP9 microcontroller compared to a baseline frame-by-frame inference scheme using exclusively full-resolution images. Code available at: https://github.com/Bomps4/Multi_Resolution_Rescored_ByteTrack
URLs: https://github.com/Bomps4/Multi_Resolution_Rescored_ByteTrack
Authors: Alexandre Quintart, Magnus Haw, Federico Semeraro
Abstract: arcjetCV is an open-source Python software designed to automate time-resolved measurements of heatshield material recession and recession rates from arcjet test video footage. This new automated and accessible capability greatly exceeds previous manual extraction methods, enabling rapid and detailed characterization of material recession for any sample with a profile video. arcjetCV automates the video segmentation process using machine learning models, including a one-dimensional (1D) Convolutional Neural Network (CNN) to infer the time-window of interest, a two-dimensional (2D) CNN for image and edge segmentation, and a Local Outlier Factor (LOF) for outlier filtering. A graphical user interface (GUI) simplifies the user experience and an application programming interface (API) allows users to call the core functions from scripts, enabling video batch processing. arcjetCV's capability to measure time-resolved recession in turn enables characterization of non-linear processes (shrinkage, swelling, melt flows, etc.), contributing to higher fidelity validation and improved modeling of heatshield material performance. The source code associated with this article can be found at https://github.com/magnus-haw/arcjetCV.
Authors: Zeyu Zhang, Xuyin Qi, Mingxi Chen, Guangxi Li, Ryan Pham, Ayub Zuhair, Ella Berry, Zhibin Liao, Owen Siggs, Robert Mclaughlin, Jamie Craig, Minh-Son To
Abstract: The oxygen saturation level in the blood (SaO2) is crucial for health, particularly in relation to sleep-related breathing disorders. However, continuous monitoring of SaO2 is time-consuming and highly variable depending on patients' conditions. Recently, optical coherence tomography angiography (OCTA) has shown promising development in rapidly and effectively screening eye-related lesions, offering the potential for diagnosing sleep-related disorders. To bridge this gap, our paper presents three key contributions. Firstly, we propose JointViT, a novel model based on the Vision Transformer architecture, incorporating a joint loss function for supervision. Secondly, we introduce a balancing augmentation technique during data preprocessing to improve the model's performance, particularly on the long-tail distribution within the OCTA dataset. Lastly, through comprehensive experiments on the OCTA dataset, our proposed method significantly outperforms other state-of-the-art methods, achieving improvements of up to 12.28% in overall accuracy. This advancement lays the groundwork for the future utilization of OCTA in diagnosing sleep-related disorders. See project website https://steve-zeyu-zhang.github.io/JointViT
Authors: Yu Zhong, Xiao Wu, Liang-Jian Deng, Zihan Cao
Abstract: Pansharpening is a significant image fusion technique that merges the spatial content and spectral characteristics of remote sensing images to generate high-resolution multispectral images. Recently, denoising diffusion probabilistic models have been gradually applied to visual tasks, enhancing controllable image generation through low-rank adaptation (LoRA). In this paper, we introduce a spatial-spectral integrated diffusion model for the remote sensing pansharpening task, called SSDiff, which considers the pansharpening process as the fusion process of spatial and spectral components from the perspective of subspace decomposition. Specifically, SSDiff utilizes spatial and spectral branches to learn spatial details and spectral features separately, then employs a designed alternating projection fusion module (APFM) to accomplish the fusion. Furthermore, we propose a frequency modulation inter-branch module (FMIM) to modulate the frequency distribution between branches. The two components of SSDiff can perform favorably against the APFM when utilizing a LoRA-like branch-wise alternative fine-tuning method. It refines SSDiff to capture component-discriminating features more sufficiently. Finally, extensive experiments on four commonly used datasets, i.e., WorldView-3, WorldView-2, GaoFen-2, and QuickBird, demonstrate the superiority of SSDiff both visually and quantitatively. The code will be made open source after possible acceptance.
Authors: Tarasha Khurana, Deva Ramanan
Abstract: Our work explores the task of generating future sensor observations conditioned on the past. We are motivated by `predictive coding' concepts from neuroscience as well as robotic applications such as self-driving vehicles. Predictive video modeling is challenging because the future may be multi-modal and learning at scale remains computationally expensive for video processing. To address both challenges, our key insight is to leverage the large-scale pretraining of image diffusion models which can handle multi-modality. We repurpose image models for video prediction by conditioning on new frame timestamps. Such models can be trained with videos of both static and dynamic scenes. To allow them to be trained with modestly-sized datasets, we introduce invariances by factoring out illumination and texture by forcing the model to predict (pseudo) depth, readily obtained for in-the-wild videos via off-the-shelf monocular depth networks. In fact, we show that simply modifying networks to predict grayscale pixels already improves the accuracy of video prediction. Given the extra controllability with timestamp conditioning, we propose sampling schedules that work better than the traditional autoregressive and hierarchical sampling strategies. Motivated by probabilistic metrics from the object forecasting literature, we create a benchmark for video prediction on a diverse set of videos spanning indoor and outdoor scenes and a large vocabulary of objects. Our experiments illustrate the effectiveness of learning to condition on timestamps, and show the importance of predicting the future with invariant modalities.
Authors: Kuan-Chieh (Jackson), Wang, Daniil Ostashev, Yuwei Fang, Sergey Tulyakov, Kfir Aberman
Abstract: We introduce a new architecture for personalization of text-to-image diffusion models, coined Mixture-of-Attention (MoA). Inspired by the Mixture-of-Experts mechanism utilized in large language models (LLMs), MoA distributes the generation workload between two attention pathways: a personalized branch and a non-personalized prior branch. MoA is designed to retain the original model's prior by fixing its attention layers in the prior branch, while minimally intervening in the generation process with the personalized branch that learns to embed subjects in the layout and context generated by the prior branch. A novel routing mechanism manages the distribution of pixels in each layer across these branches to optimize the blend of personalized and generic content creation. Once trained, MoA facilitates the creation of high-quality, personalized images featuring multiple subjects with compositions and interactions as diverse as those generated by the original model. Crucially, MoA enhances the distinction between the model's pre-existing capability and the newly augmented personalized intervention, thereby offering a more disentangled subject-context control that was previously unattainable. Project page: https://snap-research.github.io/mixture-of-attention
Authors: Omar Elezabi, Marcos V. Conde, Radu Timofte
Abstract: In modern smartphone cameras, the Image Signal Processor (ISP) is the core element that converts the RAW readings from the sensor into perceptually pleasant RGB images for the end users. The ISP is typically proprietary and handcrafted and consists of several blocks such as white balance, color correction, and tone mapping. Deep learning-based ISPs aim to transform RAW images into DSLR-like RGB images using deep neural networks. However, most learned ISPs are trained using patches (small regions) due to computational limitations. Such methods lack global context, which limits their efficacy on full-resolution images and harms their ability to capture global properties such as color constancy or illumination. First, we propose a novel module that can be integrated into any neural ISP to capture the global context information from the full RAW images. Second, we propose an efficient and simple neural ISP that utilizes our proposed module. Our model achieves state-of-the-art results on different benchmarks using diverse and real smartphone images.
Authors: Fei Cui, Jiaojiao Fang, Xiaojiang Wu, Zelong Lai, Mengke Yang, Menghan Jia, Guizhong Liu
Abstract: Stochastic video prediction enables the consideration of uncertainty in future motion, thereby providing a better reflection of the dynamic nature of the environment. Stochastic video prediction methods based on image auto-regressive recurrent models need to feed their predictions back into the latent space. Conversely, the state-space models, which decouple frame synthesis and temporal prediction, proves to be more efficient. However, inferring long-term temporal information about motion and generalizing to dynamic scenarios under non-stationary assumptions remains an unresolved challenge. In this paper, we propose a state-space decomposition stochastic video prediction model that decomposes the overall video frame generation into deterministic appearance prediction and stochastic motion prediction. Through adaptive decomposition, the model's generalization capability to dynamic scenarios is enhanced. In the context of motion prediction, obtaining a prior on the long-term trend of future motion is crucial. Thus, in the stochastic motion prediction branch, we infer the long-term motion trend from conditional frames to guide the generation of future frames that exhibit high consistency with the conditional frames. Experimental results demonstrate that our model outperforms baselines on multiple datasets.
Authors: Zezhong Fan, Xiaohan Li, Chenhao Fang, Topojoy Biswas, Kaushiki Nag, Jianpeng Xu, Kannan Achan
Abstract: The rapid evolution of text-to-image diffusion models has opened the door of generative AI, enabling the translation of textual descriptions into visually compelling images with remarkable quality. However, a persistent challenge within this domain is the optimization of prompts to effectively convey abstract concepts into concrete objects. For example, text encoders can hardly express "peace", while can easily illustrate olive branches and white doves. This paper introduces a novel approach named Prompt Optimizer for Abstract Concepts (POAC) specifically designed to enhance the performance of text-to-image diffusion models in interpreting and generating images from abstract concepts. We propose a Prompt Language Model (PLM), which is initialized from a pre-trained language model, and then fine-tuned with a curated dataset of abstract concept prompts. The dataset is created with GPT-4 to extend the abstract concept to a scene and concrete objects. Our framework employs a Reinforcement Learning (RL)-based optimization strategy, focusing on the alignment between the generated images by a stable diffusion model and optimized prompts. Through extensive experiments, we demonstrate that our proposed POAC significantly improves the accuracy and aesthetic quality of generated images, particularly in the description of abstract concepts and alignment with optimized prompts. We also present a comprehensive analysis of our model's performance across diffusion models under different settings, showcasing its versatility and effectiveness in enhancing abstract concept representation.
Authors: Feng Yu, Teng Zhang, Gilad Lerman
Abstract: We present the subspace-constrained Tyler's estimator (STE) designed for recovering a low-dimensional subspace within a dataset that may be highly corrupted with outliers. STE is a fusion of the Tyler's M-estimator (TME) and a variant of the fast median subspace. Our theoretical analysis suggests that, under a common inlier-outlier model, STE can effectively recover the underlying subspace, even when it contains a smaller fraction of inliers relative to other methods in the field of robust subspace recovery. We apply STE in the context of Structure from Motion (SfM) in two ways: for robust estimation of the fundamental matrix and for the removal of outlying cameras, enhancing the robustness of the SfM pipeline. Numerical experiments confirm the state-of-the-art performance of our method in these applications. This research makes significant contributions to the field of robust subspace recovery, particularly in the context of computer vision and 3D reconstruction.
Authors: Xi Chen (Zhejiang University), Sida Peng (Zhejiang University), Dongchen Yang (Zhejiang University), Yuan Liu (The University of Hong Kong), Bowen Pan (Tao Technology Department, Alibaba Group), Chengfei Lv (Tao Technology Department, Alibaba Group), Xiaowei Zhou (Zhejiang University)
Abstract: This paper aims to recover object materials from posed images captured under an unknown static lighting condition. Recent methods solve this task by optimizing material parameters through differentiable physically based rendering. However, due to the coupling between object geometry, materials, and environment lighting, there is inherent ambiguity during the inverse rendering process, preventing previous methods from obtaining accurate results. To overcome this ill-posed problem, our key idea is to learn the material prior with a generative model for regularizing the optimization process. We observe that the general rendering equation can be split into diffuse and specular shading terms, and thus formulate the material prior as diffusion models of albedo and specular. Thanks to this design, our model can be trained using the existing abundant 3D object data, and naturally acts as a versatile tool to resolve the ambiguity when recovering material representations from RGB images. In addition, we develop a coarse-to-fine training strategy that leverages estimated materials to guide diffusion models to satisfy multi-view consistent constraints, leading to more stable and accurate results. Extensive experiments on real-world and synthetic datasets demonstrate that our approach achieves state-of-the-art performance on material recovery. The code will be available at https://zju3dv.github.io/IntrinsicAnything.
Authors: Zhichao Deng, Xiangtai Li, Xia Li, Yunhai Tong, Shen Zhao, Mengyuan Liu
Abstract: Understanding the real world through point cloud video is a crucial aspect of robotics and autonomous driving systems. However, prevailing methods for 4D point cloud recognition have limitations due to sensor resolution, which leads to a lack of detailed information. Recent advances have shown that Vision-Language Models (VLM) pre-trained on web-scale text-image datasets can learn fine-grained visual concepts that can be transferred to various downstream tasks. However, effectively integrating VLM into the domain of 4D point clouds remains an unresolved problem. In this work, we propose the Vision-Language Models Goes 4D (VG4D) framework to transfer VLM knowledge from visual-text pre-trained models to a 4D point cloud network. Our approach involves aligning the 4D encoder's representation with a VLM to learn a shared visual and text space from training on large-scale image-text pairs. By transferring the knowledge of the VLM to the 4D encoder and combining the VLM, our VG4D achieves improved recognition performance. To enhance the 4D encoder, we modernize the classic dynamic point cloud backbone and propose an improved version of PSTNet, im-PSTNet, which can efficiently model point cloud videos. Experiments demonstrate that our method achieves state-of-the-art performance for action recognition on both the NTU RGB+D 60 dataset and the NTU RGB+D 120 dataset. Code is available at \url{https://github.com/Shark0-0/VG4D}.
Authors: Zhiheng Liu, Hao Ouyang, Qiuyu Wang, Ka Leong Cheng, Jie Xiao, Kai Zhu, Nan Xue, Yu Liu, Yujun Shen, Yang Cao
Abstract: 3D Gaussians have recently emerged as an efficient representation for novel view synthesis. This work studies its editability with a particular focus on the inpainting task, which aims to supplement an incomplete set of 3D Gaussians with additional points for visually harmonious rendering. Compared to 2D inpainting, the crux of inpainting 3D Gaussians is to figure out the rendering-relevant properties of the introduced points, whose optimization largely benefits from their initial 3D positions. To this end, we propose to guide the point initialization with an image-conditioned depth completion model, which learns to directly restore the depth map based on the observed image. Such a design allows our model to fill in depth values at an aligned scale with the original depth, and also to harness strong generalizability from largescale diffusion prior. Thanks to the more accurate depth completion, our approach, dubbed InFusion, surpasses existing alternatives with sufficiently better fidelity and efficiency under various complex scenarios. We further demonstrate the effectiveness of InFusion with several practical applications, such as inpainting with user-specific texture or with novel object insertion.
Authors: Zichen Liu, Yihao Meng, Hao Ouyang, Yue Yu, Bolin Zhao, Daniel Cohen-Or, Huamin Qu
Abstract: Text animation serves as an expressive medium, transforming static communication into dynamic experiences by infusing words with motion to evoke emotions, emphasize meanings, and construct compelling narratives. Crafting animations that are semantically aware poses significant challenges, demanding expertise in graphic design and animation. We present an automated text animation scheme, termed "Dynamic Typography", which combines two challenging tasks. It deforms letters to convey semantic meaning and infuses them with vibrant movements based on user prompts. Our technique harnesses vector graphics representations and an end-to-end optimization-based framework. This framework employs neural displacement fields to convert letters into base shapes and applies per-frame motion, encouraging coherence with the intended textual concept. Shape preservation techniques and perceptual loss regularization are employed to maintain legibility and structural integrity throughout the animation process. We demonstrate the generalizability of our approach across various text-to-video models and highlight the superiority of our end-to-end methodology over baseline methods, which might comprise separate tasks. Through quantitative and qualitative evaluations, we demonstrate the effectiveness of our framework in generating coherent text animations that faithfully interpret user prompts while maintaining readability. Our code is available at: https://animate-your-word.github.io/demo/.
Authors: Daniel Geng, Inbum Park, Andrew Owens
Abstract: Given a factorization of an image into a sum of linear components, we present a zero-shot method to control each individual component through diffusion model sampling. For example, we can decompose an image into low and high spatial frequencies and condition these components on different text prompts. This produces hybrid images, which change appearance depending on viewing distance. By decomposing an image into three frequency subbands, we can generate hybrid images with three prompts. We also use a decomposition into grayscale and color components to produce images whose appearance changes when they are viewed in grayscale, a phenomena that naturally occurs under dim lighting. And we explore a decomposition by a motion blur kernel, which produces images that change appearance under motion blurring. Our method works by denoising with a composite noise estimate, built from the components of noise estimates conditioned on different prompts. We also show that for certain decompositions, our method recovers prior approaches to compositional generation and spatial control. Finally, we show that we can extend our approach to generate hybrid images from real images. We do this by holding one component fixed and generating the remaining components, effectively solving an inverse problem.
Authors: Kshitij Goel, Wennie Tabib
Abstract: This paper introduces the open-source framework, GIRA, which implements fundamental robotics algorithms for reconstruction, pose estimation, and occupancy modeling using compact generative models. Compactness enables perception in the large by ensuring that the perceptual models can be communicated through low-bandwidth channels during large-scale mobile robot deployments. The generative property enables perception in the small by providing high-resolution reconstruction capability. These properties address perception needs for diverse robotic applications, including multi-robot exploration and dexterous manipulation. State-of-the-art perception systems construct perceptual models via multiple disparate pipelines that reuse the same underlying sensor data, which leads to increased computation, redundancy, and complexity. GIRA bridges this gap by providing a unified perceptual modeling framework using Gaussian mixture models (GMMs) as well as a novel systems contribution, which consists of GPU-accelerated functions to learn GMMs 10-100x faster compared to existing CPU implementations. Because few GMM-based frameworks are open-sourced, this work seeks to accelerate innovation and broaden adoption of these techniques.
Authors: Furkan Mumcu, Yasin Yilmaz
Abstract: Adversarial machine learning attacks on video action recognition models is a growing research area and many effective attacks were introduced in recent years. These attacks show that action recognition models can be breached in many ways. Hence using these models in practice raises significant security concerns. However, there are very few works which focus on defending against or detecting attacks. In this work, we propose a novel universal detection method which is compatible with any action recognition model. In our extensive experiments, we show that our method consistently detects various attacks against different target models with high true positive rates while satisfying very low false positive rates. Tested against four state-of-the-art attacks targeting four action recognition models, the proposed detector achieves an average AUC of 0.911 over 16 test cases while the best performance achieved by the existing detectors is 0.645 average AUC. This 41.2% improvement is enabled by the robustness of the proposed detector to varying attack methods and target models. The lowest AUC achieved by our detector across the 16 test cases is 0.837 while the competing detector's performance drops as low as 0.211. We also show that the proposed detector is robust to varying attack strengths. In addition, we analyze our method's real-time performance with different hardware setups to demonstrate its potential as a practical defense mechanism.
Authors: Deepa Krishnaswamy, B\'alint Kov\'acs, Stefan Denner, Steve Pieper, David Clunie, Christopher P. Bridge, Tina Kapur, Klaus H. Maier-Hein, Andrey Fedorov
Abstract: With the wealth of medical image data, efficient curation is essential. Assigning the sequence type to magnetic resonance images is necessary for scientific studies and artificial intelligence-based analysis. However, incomplete or missing metadata prevents effective automation. We therefore propose a deep-learning method for classification of prostate cancer scanning sequences based on a combination of image data and DICOM metadata. We demonstrate superior results compared to metadata or image data alone, and make our code publicly available at https://github.com/deepakri201/DICOMScanClassification.
URLs: https://github.com/deepakri201/DICOMScanClassification.
Authors: Hao Yan, Yuhong Guo
Abstract: Federated learning aims to tackle the ``isolated data island" problem, where it trains a collective model from physically isolated clients while safeguarding the privacy of users' data. However, supervised federated learning necessitates that each client labels their data for training, which can be both time-consuming and resource-intensive, and may even be impractical for edge devices. Moreover, the training and transmission of deep models present challenges to the computation and communication capabilities of the clients. To address these two inherent challenges in supervised federated learning, we propose a novel lightweight unsupervised federated learning approach that leverages unlabeled data on each client to perform lightweight model training and communication by harnessing pretrained vision-language models, such as CLIP. By capitalizing on the zero-shot prediction capability and the well-trained image encoder of the pre-trained CLIP model, we have carefully crafted an efficient and resilient self-training approach. This method refines the initial zero-shot predicted pseudo-labels of unlabeled instances through the sole training of a linear classifier on top of the fixed image encoder. Additionally, to address data heterogeneity within each client, we propose a class-balanced text feature sampling strategy for generating synthetic instances in the feature space to support local training. Experiments are conducted on multiple benchmark datasets. The experimental results demonstrate that our proposed method greatly enhances model performance in comparison to CLIP's zero-shot predictions and even outperforms supervised federated learning benchmark methods given limited computational and communication overhead.
Authors: Abdullah F. Al-Battal, Soan T. M. Duong, Van Ha Tang, Quang Duc Tran, Steven Q. H. Truong, Chien Phan, Truong Q. Nguyen, Cheolhong An
Abstract: Multi-phase computed tomography (CT) scans use contrast agents to highlight different anatomical structures within the body to improve the probability of identifying and detecting anatomical structures of interest and abnormalities such as liver lesions. Yet, detecting these lesions remains a challenging task as these lesions vary significantly in their size, shape, texture, and contrast with respect to surrounding tissue. Therefore, radiologists need to have an extensive experience to be able to identify and detect these lesions. Segmentation-based neural networks can assist radiologists with this task. Current state-of-the-art lesion segmentation networks use the encoder-decoder design paradigm based on the UNet architecture where the multi-phase CT scan volume is fed to the network as a multi-channel input. Although this approach utilizes information from all the phases and outperform single-phase segmentation networks, we demonstrate that their performance is not optimal and can be further improved by incorporating the learning from models trained on each single-phase individually. Our approach comprises three stages. The first stage identifies the regions within the liver where there might be lesions at three different scales (4, 8, and 16 mm). The second stage includes the main segmentation model trained using all the phases as well as a segmentation model trained on each of the phases individually. The third stage uses the multi-phase CT volumes together with the predictions from each of the segmentation models to generate the final segmentation map. Overall, our approach improves relative liver lesion segmentation performance by 1.6% while reducing performance variability across subjects by 8% when compared to the current state-of-the-art models.
Authors: Hongzhao Li, Hongyu Wang, Xia Sun, Hua He, Jun Feng
Abstract: Medical report generation automates radiology descriptions from images, easing the burden on physicians and minimizing errors. However, current methods lack structured outputs and physician interactivity for clear, clinically relevant reports. Our method introduces a prompt-guided approach to generate structured chest X-ray reports using a pre-trained large language model (LLM). First, we identify anatomical regions in chest X-rays to generate focused sentences that center on key visual elements, thereby establishing a structured report foundation with anatomy-based sentences. We also convert the detected anatomy into textual prompts conveying anatomical comprehension to the LLM. Additionally, the clinical context prompts guide the LLM to emphasize interactivity and clinical requirements. By integrating anatomy-focused sentences and anatomy/clinical prompts, the pre-trained LLM can generate structured chest X-ray reports tailored to prompted anatomical regions and clinical contexts. We evaluate using language generation and clinical effectiveness metrics, demonstrating strong performance.
Authors: Cansu Korkmaz, A. Murat Tekalp
Abstract: Transformer-based models have achieved remarkable results in low-level vision tasks including image super-resolution (SR). However, early Transformer-based approaches that rely on self-attention within non-overlapping windows encounter challenges in acquiring global information. To activate more input pixels globally, hybrid attention models have been proposed. Moreover, training by solely minimizing pixel-wise RGB losses, such as L1, have been found inadequate for capturing essential high-frequency details. This paper presents two contributions: i) We introduce convolutional non-local sparse attention (NLSA) blocks to extend the hybrid transformer architecture in order to further enhance its receptive field. ii) We employ wavelet losses to train Transformer models to improve quantitative and subjective performance. While wavelet losses have been explored previously, showing their power in training Transformer-based SR models is novel. Our experimental results demonstrate that the proposed model provides state-of-the-art PSNR results as well as superior visual performance across various benchmark datasets.
Authors: Luca Scofano, Alessio Sampieri, Tommaso Campari, Valentino Sacco, Indro Spinelli, Lamberto Ballan, Fabio Galasso
Abstract: The success of collaboration between humans and robots in shared environments relies on the robot's real-time adaptation to human motion. Specifically, in Social Navigation, the agent should be close enough to assist but ready to back up to let the human move freely, avoiding collisions. Human trajectories emerge as crucial cues in Social Navigation, but they are partially observable from the robot's egocentric view and computationally complex to process. We propose the first Social Dynamics Adaptation model (SDA) based on the robot's state-action history to infer the social dynamics. We propose a two-stage Reinforcement Learning framework: the first learns to encode the human trajectories into social dynamics and learns a motion policy conditioned on this encoded information, the current status, and the previous action. Here, the trajectories are fully visible, i.e., assumed as privileged information. In the second stage, the trained policy operates without direct access to trajectories. Instead, the model infers the social dynamics solely from the history of previous actions and statuses in real-time. Tested on the novel Habitat 3.0 platform, SDA sets a novel state of the art (SoA) performance in finding and following humans.
Authors: Haohua Dong
Abstract: This work addresses the landing problem of an aerial vehicle, exemplified by a simple quadrotor, on a moving platform using image-based visual servo control. First, the mathematical model of the quadrotor aircraft is introduced, followed by the design of the inner-loop control. At the second stage, the image features on the textured target plane are exploited to derive a vision-based control law. The image of the spherical centroid of a set of landmarks present in the landing target is used as a position measurement, whereas the translational optical flow is used as velocity measurement. The kinematics of the vision-based system is expressed in terms of the observable features, and the proposed control law guarantees convergence without estimating the unknown distance between the vision system and the target, which is also guaranteed to remain strictly positive, avoiding undesired collisions. The performance of the proposed control law is evaluated in MATLAB and 3-D simulation software Gazebo. Simulation results for a quadrotor UAV are provided for different velocity profiles of the moving target, showcasing the robustness of the proposed controller.
Authors: Seyed M. R. Modaresi, Aomar Osmani, Mohammadreza Razzazi, Abdelghani Chibani
Abstract: Medical image segmentation plays a vital role in various clinical applications, enabling accurate delineation and analysis of anatomical structures or pathological regions. Traditional CNNs have achieved remarkable success in this field. However, they often rely on fixed kernel sizes, which can limit their performance and adaptability in medical images where features exhibit diverse scales and configurations due to variability in equipment, target sizes, and expert interpretations. In this paper, we propose an adaptive layer placed ahead of leading deep-learning models such as UCTransNet, which dynamically adjusts the kernel size based on the local context of the input image. By adaptively capturing and fusing features at multiple scales, our approach enhances the network's ability to handle diverse anatomical structures and subtle image details, even for recently performing architectures that internally implement intra-scale modules, such as UCTransnet. Extensive experiments are conducted on benchmark medical image datasets to evaluate the effectiveness of our proposal. It consistently outperforms traditional \glspl{CNN} with fixed kernel sizes with a similar number of parameters, achieving superior segmentation Accuracy, Dice, and IoU in popular datasets such as SegPC2021 and ISIC2018. The model and data are published in the open-source repository, ensuring transparency and reproducibility of our promising results.
Authors: Tanzina Taher Ifty, Saleh Ahmed Shafin, Shoeb Mohammad Shahriar, Tashfia Towhid
Abstract: Lung diseases remain a critical global health concern, and it's crucial to have accurate and quick ways to diagnose them. This work focuses on classifying different lung diseases into five groups: viral pneumonia, bacterial pneumonia, COVID, tuberculosis, and normal lungs. Employing advanced deep learning techniques, we explore a diverse range of models including CNN, hybrid models, ensembles, transformers, and Big Transfer. The research encompasses comprehensive methodologies such as hyperparameter tuning, stratified k-fold cross-validation, and transfer learning with fine-tuning.Remarkably, our findings reveal that the Xception model, fine-tuned through 5-fold cross-validation, achieves the highest accuracy of 96.21\%. This success shows that our methods work well in accurately identifying different lung diseases. The exploration of explainable artificial intelligence (XAI) methodologies further enhances our understanding of the decision-making processes employed by these models, contributing to increased trust in their clinical applications.
Authors: Wei Chen, Zhiyuan Li
Abstract: A multimodal AI agent is characterized by its ability to process and learn from various types of data, including natural language, visual, and audio inputs, to inform its actions. Despite advancements in large language models that incorporate visual data, such as GPT-4V, effectively translating image-based data into actionable outcomes for AI agents continues to be challenging. In this paper, we introduce a multimodal model that incorporates the concept of functional token specifically designed for AI agent applications. To ensure compatibility with edge devices, our model is optimized to a compact size of less than 1B parameters. Like GPT-4, our model can process both English and Chinese. We demonstrate that this model is capable of operating efficiently on a wide range of edge devices, including as constrained as a Raspberry Pi.
Authors: Manasi Muglikar, Siddharth Somasundaram, Akshat Dave, Edoardo Charbon, Ramesh Raskar, Davide Scaramuzza
Abstract: Traditional cameras face a trade-off between low-light performance and high-speed imaging: longer exposure times to capture sufficient light results in motion blur, whereas shorter exposures result in Poisson-corrupted noisy images. While burst photography techniques help mitigate this tradeoff, conventional cameras are fundamentally limited in their sensor noise characteristics. Event cameras and single-photon avalanche diode (SPAD) sensors have emerged as promising alternatives to conventional cameras due to their desirable properties. SPADs are capable of single-photon sensitivity with microsecond temporal resolution, and event cameras can measure brightness changes up to 1 MHz with low bandwidth requirements. We show that these properties are complementary, and can help achieve low-light, high-speed image reconstruction with low bandwidth requirements. We introduce a sensor fusion framework to combine SPADs with event cameras to improves the reconstruction of high-speed, low-light scenes while reducing the high bandwidth cost associated with using every SPAD frame. Our evaluation, on both synthetic and real sensor data, demonstrates significant enhancements ( > 5 dB PSNR) in reconstructing low-light scenes at high temporal resolution (100 kHz) compared to conventional cameras. Event-SPAD fusion shows great promise for real-world applications, such as robotics or medical imaging.
Authors: James Harrison, John Willes, Jasper Snoek
Abstract: We introduce a deterministic variational formulation for training Bayesian last layer neural networks. This yields a sampling-free, single-pass model and loss that effectively improves uncertainty estimation. Our variational Bayesian last layer (VBLL) can be trained and evaluated with only quadratic complexity in last layer width, and is thus (nearly) computationally free to add to standard architectures. We experimentally investigate VBLLs, and show that they improve predictive accuracy, calibration, and out of distribution detection over baselines across both regression and classification. Finally, we investigate combining VBLL layers with variational Bayesian feature learning, yielding a lower variance collapsed variational inference method for Bayesian neural networks.
Authors: Rui-Jie Zhu, Malu Zhang, Qihang Zhao, Haoyu Deng, Yule Duan, Liang-Jian Deng
Abstract: Spiking Neural Networks (SNNs) are attracting widespread interest due to their biological plausibility, energy efficiency, and powerful spatio-temporal information representation ability. Given the critical role of attention mechanisms in enhancing neural network performance, the integration of SNNs and attention mechanisms exhibits potential to deliver energy-efficient and high-performance computing paradigms. We present a novel Temporal-Channel Joint Attention mechanism for SNNs, referred to as TCJA-SNN. The proposed TCJA-SNN framework can effectively assess the significance of spike sequence from both spatial and temporal dimensions. More specifically, our essential technical contribution lies on: 1) We employ the squeeze operation to compress the spike stream into an average matrix. Then, we leverage two local attention mechanisms based on efficient 1D convolutions to facilitate comprehensive feature extraction at the temporal and channel levels independently. 2) We introduce the Cross Convolutional Fusion (CCF) layer as a novel approach to model the inter-dependencies between the temporal and channel scopes. This layer breaks the independence of these two dimensions and enables the interaction between features. Experimental results demonstrate that the proposed TCJA-SNN outperforms SOTA by up to 15.7% accuracy on standard static and neuromorphic datasets, including Fashion-MNIST, CIFAR10-DVS, N-Caltech 101, and DVS128 Gesture. Furthermore, we apply the TCJA-SNN framework to image generation tasks by leveraging a variation autoencoder. To the best of our knowledge, this study is the first instance where the SNN-attention mechanism has been employed for image classification and generation tasks. Notably, our approach has achieved SOTA performance in both domains, establishing a significant advancement in the field. Codes are available at https://github.com/ridgerchu/TCJA.
Authors: Yonghao Dang, Jianqin Yin, Shaojie Zhang, Jiping Liu, Yanzhu Hu
Abstract: Estimating human poses from videos is critical in human-computer interaction. Joints cooperate rather than move independently during human movement. There are both spatial and temporal correlations between joints. Despite the positive results of previous approaches, most focus on modeling the spatial correlation between joints while only straightforwardly integrating features along the temporal dimension, ignoring the temporal correlation between joints. In this work, we propose a plug-and-play kinematics modeling module (KMM) to explicitly model temporal correlations between joints across different frames by calculating their temporal similarity. In this way, KMM can capture motion cues of the current joint relative to all joints in different time. Besides, we formulate video-based human pose estimation as a Markov Decision Process and design a novel kinematics modeling network (KIMNet) to simulate the Markov Chain, allowing KIMNet to locate joints recursively. Our approach achieves state-of-the-art results on two challenging benchmarks. In particular, KIMNet shows robustness to the occlusion. The code will be released at https://github.com/YHDang/KIMNet.
Authors: Matthew Inkawhich, Nathan Inkawhich, Hai Li, Yiran Chen
Abstract: Current state-of-the-art object proposal networks are trained with a closed-world assumption, meaning they learn to only detect objects of the training classes. These models fail to provide high recall in open-world environments where important novel objects may be encountered. While a handful of recent works attempt to tackle this problem, they fail to consider that the optimal behavior of a proposal network can vary significantly depending on the data and application. Our goal is to provide a flexible proposal solution that can be easily tuned to suit a variety of open-world settings. To this end, we design a Tunable Hybrid Proposal Network (THPN) that leverages an adjustable hybrid architecture, a novel self-training procedure, and dynamic loss components to optimize the tradeoff between known and unknown object detection performance. To thoroughly evaluate our method, we devise several new challenges which invoke varying degrees of label bias by altering known class diversity and label count. We find that in every task, THPN easily outperforms existing baselines (e.g., RPN, OLN). Our method is also highly data efficient, surpassing baseline recall with a fraction of the labeled data.
Authors: David Korcak, Jiri Matas
Abstract: We present a method for estimating the shutter angle, a.k.a. exposure fraction - the ratio of the exposure time and the reciprocal of frame rate - of videoclips containing motion. The approach exploits the relation of the exposure fraction, optical flow, and linear motion blur. Robustness is achieved by selecting image patches where both the optical flow and blur estimates are reliable, checking their consistency. The method was evaluated on the publicly available Beam-Splitter Dataset with a range of exposure fractions from 0.015 to 0.36. The best achieved mean absolute error of estimates was 0.039. We successfully test the suitability of the method for a forensic application of detection of video tampering by frame removal or insertion
Authors: Haoheng Lan, Jindong Gu, Philip Torr, Hengshuang Zhao
Abstract: When a small number of poisoned samples are injected into the training dataset of a deep neural network, the network can be induced to exhibit malicious behavior during inferences, which poses potential threats to real-world applications. While they have been intensively studied in classification, backdoor attacks on semantic segmentation have been largely overlooked. Unlike classification, semantic segmentation aims to classify every pixel within a given image. In this work, we explore backdoor attacks on segmentation models to misclassify all pixels of a victim class by injecting a specific trigger on non-victim pixels during inferences, which is dubbed Influencer Backdoor Attack (IBA). IBA is expected to maintain the classification accuracy of non-victim pixels and mislead classifications of all victim pixels in every single inference and could be easily applied to real-world scenes. Based on the context aggregation ability of segmentation models, we proposed a simple, yet effective, Nearest-Neighbor trigger injection strategy. We also introduce an innovative Pixel Random Labeling strategy which maintains optimal performance even when the trigger is placed far from the victim pixels. Our extensive experiments reveal that current segmentation models do suffer from backdoor attacks, demonstrate IBA real-world applicability, and show that our proposed techniques can further increase attack performance.
Authors: Zihao Zhao, Sheng Wang, Jinchen Gu, Yitao Zhu, Lanzhuju Mei, Zixu Zhuang, Zhiming Cui, Qian Wang, Dinggang Shen
Abstract: The integration of Computer-Aided Diagnosis (CAD) with Large Language Models (LLMs) presents a promising frontier in clinical applications, notably in automating diagnostic processes akin to those performed by radiologists and providing consultations similar to a virtual family doctor. Despite the promising potential of this integration, current works face at least two limitations: (1) From the perspective of a radiologist, existing studies typically have a restricted scope of applicable imaging domains, failing to meet the diagnostic needs of different patients. Also, the insufficient diagnostic capability of LLMs further undermine the quality and reliability of the generated medical reports. (2) Current LLMs lack the requisite depth in medical expertise, rendering them less effective as virtual family doctors due to the potential unreliability of the advice provided during patient consultations. To address these limitations, we introduce ChatCAD+, to be universal and reliable. Specifically, it is featured by two main modules: (1) Reliable Report Generation and (2) Reliable Interaction. The Reliable Report Generation module is capable of interpreting medical images from diverse domains and generate high-quality medical reports via our proposed hierarchical in-context learning. Concurrently, the interaction module leverages up-to-date information from reputable medical websites to provide reliable medical advice. Together, these designed modules synergize to closely align with the expertise of human medical professionals, offering enhanced consistency and reliability for interpretation and advice. The source code is available at https://github.com/zhaozh10/ChatCAD.
Authors: Hanxi Li, Jingqi Wu, Hao Chen, Mingwen Wang, Chunhua Shen
Abstract: Anomaly Detection is challenging as usually only the normal samples are seen during training and the detector needs to discover anomalies on-the-fly. The recently proposed deep-learning-based approaches could somehow alleviate the problem but there is still a long way to go in obtaining an industrial-class anomaly detector for real-world applications. On the other hand, in some particular AD tasks, a few anomalous samples are labeled manually for achieving higher accuracy. However, this performance gain is at the cost of considerable annotation efforts, which can be intractable in many practical scenarios. In this work, the above two problems are addressed in a unified framework. Firstly, inspired by the success of the patch-matching-based AD algorithms, we train a sliding vision transformer over the residuals generated by a novel position-constrained patch-matching. Secondly, the conventional pixel-wise segmentation problem is cast into a block-wise classification problem. Thus the sliding transformer can attain even higher accuracy with much less annotation labor. Thirdly, to further reduce the labeling cost, we propose to label the anomalous regions using only bounding boxes. The unlabeled regions caused by the weak labels are effectively exploited using a highly-customized semi-supervised learning scheme equipped with two novel data augmentation methods. The proposed method outperforms all the state-of-the-art approaches using all the evaluation metrics in both the unsupervised and supervised scenarios. On the popular MVTec-AD dataset, our SemiREST algorithm obtains the Average Precision (AP) of 81.2% in the unsupervised condition and 84.4% AP for supervised anomaly detection. Surprisingly, with the bounding-box-based semi-supervisions, SemiREST still outperforms the SOTA methods with full supervision (83.8% AP) on MVTec-AD.
Authors: Jieren Deng, Xin Zhou, Hao Tian, Zhihong Pan, Derek Aguiar
Abstract: The bokeh effect is an artistic technique that blurs out-of-focus areas in a photograph and has gained interest due to recent developments in text-to-image synthesis and the ubiquity of smart-phone cameras and photo-sharing apps. Prior work on rendering bokeh effects have focused on post hoc image manipulation to produce similar blurring effects in existing photographs using classical computer graphics or neural rendering techniques, but have either depth discontinuity artifacts or are restricted to reproducing bokeh effects that are present in the training data. More recent diffusion based models can synthesize images with an artistic style, but either require the generation of high-dimensional masks, expensive fine-tuning, or affect global image characteristics. In this paper, we present GBSD, the first generative text-to-image model that synthesizes photorealistic images with a bokeh style. Motivated by how image synthesis occurs progressively in diffusion models, our approach combines latent diffusion models with a 2-stage conditioning algorithm to render bokeh effects on semantically defined objects. Since we can focus the effect on objects, this semantic bokeh effect is more versatile than classical rendering techniques. We evaluate GBSD both quantitatively and qualitatively and demonstrate its ability to be applied in both text-to-image and image-to-image settings.
Authors: Avinash Madasu, Vasudev Lal
Abstract: Video retrieval (VR) involves retrieving the ground truth video from the video database given a text caption or vice-versa. The two important components of compositionality: objects & attributes and actions are joined using correct syntax to form a proper text query. These components (objects & attributes, actions and syntax) each play an important role to help distinguish among videos and retrieve the correct ground truth video. However, it is unclear what is the effect of these components on the video retrieval performance. We therefore, conduct a systematic study to evaluate the compositional and syntactic understanding of video retrieval models on standard benchmarks such as MSRVTT, MSVD and DIDEMO. The study is performed on two categories of video retrieval models: (i) which are pre-trained on video-text pairs and fine-tuned on downstream video retrieval datasets (Eg. Frozen-in-Time, Violet, MCQ etc.) (ii) which adapt pre-trained image-text representations like CLIP for video retrieval (Eg. CLIP4Clip, XCLIP, CLIP2Video etc.). Our experiments reveal that actions and syntax play a minor role compared to objects & attributes in video understanding. Moreover, video retrieval models that use pre-trained image-text representations (CLIP) have better syntactic and compositional understanding as compared to models pre-trained on video-text data. The code is available at https://github.com/IntelLabs/multimodal_cognitive_ai/tree/main/ICSVR
URLs: https://github.com/IntelLabs/multimodal_cognitive_ai/tree/main/ICSVR
Authors: Matthias Freiberger, Peter Kun, Christian Igel, Anders Sundnes L{\o}vlie, Sebastian Risi
Abstract: Models leveraging both visual and textual data such as Contrastive Language-Image Pre-training (CLIP), are the backbone of many recent advances in artificial intelligence. In this work, we show that despite their versatility, such models are vulnerable to what we refer to as fooling master images. Fooling master images are capable of maximizing the confidence score of a CLIP model for a significant number of widely varying prompts, while being either unrecognizable or unrelated to the attacked prompts for humans. The existence of such images is problematic as it could be used by bad actors to maliciously interfere with CLIP-trained image retrieval models in production with comparably small effort as a single image can attack many different prompts. We demonstrate how fooling master images for CLIP (CLIPMasterPrints) can be mined using stochastic gradient descent, projected gradient descent, or blackbox optimization. Contrary to many common adversarial attacks, the blackbox optimization approach allows us to mine CLIPMasterPrints even when the weights of the model are not accessible. We investigate the properties of the mined images, and find that images trained on a small number of image captions generalize to a much larger number of semantically related captions. We evaluate possible mitigation strategies, where we increase the robustness of the model and introduce an approach to automatically detect CLIPMasterPrints to sanitize the input of vulnerable models. Finally, we find that vulnerability to CLIPMasterPrints is related to a modality gap in contrastive pre-trained multi-modal networks. Code available at https://github.com/matfrei/CLIPMasterPrints.
Authors: Zhibo Tain, Xiaolin Zhang, Peng Zhang, Kun Zhan
Abstract: Semi-supervised semantic segmentation (SSS) is an important task that utilizes both labeled and unlabeled data to reduce expenses on labeling training examples. However, the effectiveness of SSS algorithms is limited by the difficulty of fully exploiting the potential of unlabeled data. To address this, we propose a dual-level Siamese structure network (DSSN) for pixel-wise contrastive learning. By aligning positive pairs with a pixel-wise contrastive loss using strong augmented views in both low-level image space and high-level feature space, the proposed DSSN is designed to maximize the utilization of available unlabeled data. Additionally, we introduce a novel class-aware pseudo-label selection strategy for weak-to-strong supervision, which addresses the limitations of most existing methods that do not perform selection or apply a predefined threshold for all classes. Specifically, our strategy selects the top high-confidence prediction of the weak view for each class to generate pseudo labels that supervise the strong augmented views. This strategy is capable of taking into account the class imbalance and improving the performance of long-tailed classes. Our proposed method achieves state-of-the-art results on two datasets, PASCAL VOC 2012 and Cityscapes, outperforming other SSS algorithms by a significant margin. The source code is available at https://github.com/kunzhan/DSSN.
Authors: Etienne Meunier, Patrick Bouthemy
Abstract: Human beings have the ability to continuously analyze a video and immediately extract the motion components. We want to adopt this paradigm to provide a coherent and stable motion segmentation over the video sequence. In this perspective, we propose a novel long-term spatio-temporal model operating in a totally unsupervised way. It takes as input the volume of consecutive optical flow (OF) fields, and delivers a volume of segments of coherent motion over the video. More specifically, we have designed a transformer-based network, where we leverage a mathematically well-founded framework, the Evidence Lower Bound (ELBO), to derive the loss function. The loss function combines a flow reconstruction term involving spatio-temporal parametric motion models combining, in a novel way, polynomial (quadratic) motion models for the spatial dimensions and B-splines for the time dimension of the video sequence, and a regularization term enforcing temporal consistency on the segments. We report experiments on four VOS benchmarks, demonstrating competitive quantitative results, while performing motion segmentation on a whole sequence in one go. We also highlight through visual results the key contributions on temporal consistency brought by our method.
Authors: Yuze He, Yushi Bai, Matthieu Lin, Wang Zhao, Yubin Hu, Jenny Sheng, Ran Yi, Juanzi Li, Yong-Jin Liu
Abstract: Recent methods in text-to-3D leverage powerful pretrained diffusion models to optimize NeRF. Notably, these methods are able to produce high-quality 3D scenes without training on 3D data. Due to the open-ended nature of the task, most studies evaluate their results with subjective case studies and user experiments, thereby presenting a challenge in quantitatively addressing the question: How has current progress in Text-to-3D gone so far? In this paper, we introduce T$^3$Bench, the first comprehensive text-to-3D benchmark containing diverse text prompts of three increasing complexity levels that are specially designed for 3D generation. To assess both the subjective quality and the text alignment, we propose two automatic metrics based on multi-view images produced by the 3D contents. The quality metric combines multi-view text-image scores and regional convolution to detect quality and view inconsistency. The alignment metric uses multi-view captioning and GPT-4 evaluation to measure text-3D consistency. Both metrics closely correlate with different dimensions of human judgments, providing a paradigm for efficiently evaluating text-to-3D models. The benchmarking results, shown in Fig. 1, reveal performance differences among an extensive 10 prevalent text-to-3D methods. Our analysis further highlights the common struggles for current methods on generating surroundings and multi-object scenes, as well as the bottleneck of leveraging 2D guidance for 3D generation. Our project page is available at: https://t3bench.com.
URLs: https://t3bench.com.
Authors: Biyuan Liu, Huaixin Chen, Kun Li, Michael Ying Yang
Abstract: Change detection plays a fundamental role in Earth observation for analyzing temporal iterations over time. However, recent studies have largely neglected the utilization of multimodal data that presents significant practical and technical advantages compared to single-modal approaches. This research focuses on leveraging {pre-event} digital surface model (DSM) data and {post-event} digital aerial images captured at different times for detecting change beyond 2D. We observe that the current change detection methods struggle with the multitask conflicts between semantic and height change detection tasks. To address this challenge, we propose an efficient Transformer-based network that learns shared representation between cross-dimensional inputs through cross-attention. {It adopts a consistency constraint to establish the multimodal relationship. Initially, pseudo-changes are derived by employing height change thresholding. Subsequently, the $L2$ distance between semantic and pseudo-changes within their overlapping regions is minimized. This explicitly endows the height change detection (regression task) and semantic change detection (classification task) with representation consistency.} A DSM-to-image multimodal dataset encompassing three cities in the Netherlands was constructed. It lays a new foundation for beyond-2D change detection from cross-dimensional inputs. Compared to five state-of-the-art change detection methods, our model demonstrates consistent multitask superiority in terms of semantic and height change detection. Furthermore, the consistency strategy can be seamlessly adapted to the other methods, yielding promising improvements.
Authors: Tomohiro Suzuki, Kazushi Tsutsui, Kazuya Takeda, Keisuke Fujii
Abstract: In many sports, player re-identification is crucial for automatic video processing and analysis. However, most of the current studies on player re-identification in multi- or single-view sports videos focus on re-identification in the closed-world setting using labeled image dataset, and player re-identification in the open-world setting for automatic video analysis is not well developed. In this paper, we propose a runner re-identification system that directly processes single-view video to address the open-world setting. In the open-world setting, we cannot use labeled dataset and have to process video directly. The proposed system automatically processes raw video as input to identify runners, and it can identify runners even when they are framed out multiple times. For the automatic processing, we first detect the runners in the video using the pre-trained YOLOv8 and the fine-tuned EfficientNet. We then track the runners using ByteTrack and detect their shoes with the fine-tuned YOLOv8. Finally, we extract the image features of the runners using an unsupervised method with the gated recurrent unit autoencoder and global and local features mixing. To improve the accuracy of runner re-identification, we use shoe images as local image features and dynamic features of running sequence images. We evaluated the system on a running practice video dataset and showed that the proposed method identified runners with higher accuracy than some state-of-the-art models in unsupervised re-identification. We also showed that our proposed local image feature and running dynamic feature were effective for runner re-identification. Our runner re-identification system can be useful for the automatic analysis of running videos.
Authors: Andrea Ciamarra, Roberto Caldelli, Federico Becattini, Lorenzo Seidenari, Alberto Del Bimbo
Abstract: The ever-increasing use of synthetically generated content in different sectors of our everyday life, one for all media information, poses a strong need for deepfake detection tools in order to avoid the proliferation of altered messages. The process to identify manipulated content, in particular images and videos, is basically performed by looking for the presence of some inconsistencies and/or anomalies specifically due to the fake generation process. Different techniques exist in the scientific literature that exploit diverse ad-hoc features in order to highlight possible modifications. In this paper, we propose to investigate how deepfake creation can impact on the characteristics that the whole scene had at the time of the acquisition. In particular, when an image (video) is captured the overall geometry of the scene (e.g. surfaces) and the acquisition process (e.g. illumination) determine a univocal environment that is directly represented by the image pixel values; all these intrinsic relations are possibly changed by the deepfake generation process. By resorting to the analysis of the characteristics of the surfaces depicted in the image it is possible to obtain a descriptor usable to train a CNN for deepfake detection: we refer to such an approach as SurFake. Experimental results carried out on the FF++ dataset for different kinds of deepfake forgeries and diverse deep learning models confirm that such a feature can be adopted to discriminate between pristine and altered images; furthermore, experiments witness that it can also be combined with visual data to provide a certain improvement in terms of detection accuracy.
Authors: Geunhyeok Yu, Hyoseok Hwang
Abstract: Deep Neural Networks (DNNs) have become pivotal in various fields, especially in computer vision, outperforming previous methodologies. A critical challenge in their deployment is the bias inherent in data across different domains, such as image style and environmental conditions, leading to domain gaps. This necessitates techniques for learning general representations from biased training data, known as domain generalization. This paper presents Attend to eXpert Prompts (A2XP), a novel approach for domain generalization that preserves the privacy and integrity of the network architecture. A2XP consists of two phases: Expert Adaptation and Domain Generalization. In the first phase, prompts for each source domain are optimized to guide the model towards the optimal direction. In the second phase, two embedder networks are trained to effectively amalgamate these expert prompts, aiming for an optimal output. Our extensive experiments demonstrate that A2XP achieves state-of-the-art results over existing non-private domain generalization methods. The experimental results validate that the proposed approach not only tackles the domain generalization challenge in DNNs but also offers a privacy-preserving, efficient solution to the broader field of computer vision.
Authors: Baolu Li, Ping Liu, Lan Fu, Jinlong Li, Jianwu Fang, Zhigang Xu, Hongkai Yu
Abstract: Vehicle Re-identification (Re-ID) has been broadly studied in the last decade; however, the different camera view angle leading to confused discrimination in the feature subspace for the vehicles of various poses, is still challenging for the Vehicle Re-ID models in the real world. To promote the Vehicle Re-ID models, this paper proposes to synthesize a large number of vehicle images in the target pose, whose idea is to project the vehicles of diverse poses into the unified target pose so as to enhance feature discrimination. Considering that the paired data of the same vehicles in different traffic surveillance cameras might be not available in the real world, we propose the first Pair-flexible Pose Guided Image Synthesis method for Vehicle Re-ID, named as VehicleGAN in this paper, which works for both supervised and unsupervised settings without the knowledge of geometric 3D models. Because of the feature distribution difference between real and synthetic data, simply training a traditional metric learning based Re-ID model with data-level fusion (i.e., data augmentation) is not satisfactory, therefore we propose a new Joint Metric Learning (JML) via effective feature-level fusion from both real and synthetic data. Intensive experimental results on the public VeRi-776 and VehicleID datasets prove the accuracy and effectiveness of our proposed VehicleGAN and JML.
Authors: Jacob Schnell, Jieke Wang, Lu Qi, Vincent Tao Hu, Meng Tang
Abstract: Recent advances in generative models, such as diffusion models, have made generating high-quality synthetic images widely accessible. Prior works have shown that training on synthetic images improves many perception tasks, such as image classification, object detection, and semantic segmentation. We are the first to explore generative data augmentations for scribble-supervised semantic segmentation. We propose ScribbleGen, a generative data augmentation method that leverages a ControlNet diffusion model conditioned on semantic scribbles to produce high-quality training data. However, naive implementations of generative data augmentations may inadvertently harm the performance of the downstream segmentor rather than improve it. We leverage classifier-free diffusion guidance to enforce class consistency and introduce encode ratios to trade off data diversity for data realism. Using the guidance scale and encode ratio, we can generate a spectrum of high-quality training images. We propose multiple augmentation schemes and find that these schemes significantly impact model performance, especially in the low-data regime. Our framework further reduces the gap between the performance of scribble-supervised segmentation and that of fully-supervised segmentation. We also show that our framework significantly improves segmentation performance on small datasets, even surpassing fully-supervised segmentation. The code is available at https://github.com/mengtang-lab/scribblegen.
Authors: Dan Song, Xinwei Fu, Weizhi Nie, Wenhui Li, Lanjun Wang, You Yang, Anan Liu
Abstract: Large-scale pre-trained models have demonstrated impressive performance in vision and language tasks within open-world scenarios. Due to the lack of comparable pre-trained models for 3D shapes, recent methods utilize language-image pre-training to realize zero-shot 3D shape recognition. However, due to the modality gap, pretrained language-image models are not confident enough in the generalization to 3D shape recognition. Consequently, this paper aims to improve the confidence with view selection and hierarchical prompts. Leveraging the CLIP model as an example, we employ view selection on the vision side by identifying views with high prediction confidence from multiple rendered views of a 3D shape. On the textual side, the strategy of hierarchical prompts is proposed for the first time. The first layer prompts several classification candidates with traditional class-level descriptions, while the second layer refines the prediction based on function-level descriptions or further distinctions between the candidates. Remarkably, without the need for additional training, our proposed method achieves impressive zero-shot 3D classification accuracies of 84.44%, 91.51%, and 66.17% on ModelNet40, ModelNet10, and ShapeNet Core55, respectively. Furthermore, we will make the code publicly available to facilitate reproducibility and further research in this area.
Authors: Tobias Kirschstein, Simon Giebenhain, Matthias Nie{\ss}ner
Abstract: DiffusionAvatars synthesizes a high-fidelity 3D head avatar of a person, offering intuitive control over both pose and expression. We propose a diffusion-based neural renderer that leverages generic 2D priors to produce compelling images of faces. For coarse guidance of the expression and head pose, we render a neural parametric head model (NPHM) from the target viewpoint, which acts as a proxy geometry of the person. Additionally, to enhance the modeling of intricate facial expressions, we condition DiffusionAvatars directly on the expression codes obtained from NPHM via cross-attention. Finally, to synthesize consistent surface details across different viewpoints and expressions, we rig learnable spatial features to the head's surface via TriPlane lookup in NPHM's canonical space. We train DiffusionAvatars on RGB videos and corresponding fitted NPHM meshes of a person and test the obtained avatars in both self-reenactment and animation scenarios. Our experiments demonstrate that DiffusionAvatars generates temporally consistent and visually appealing videos for novel poses and expressions of a person, outperforming existing approaches.
Authors: Zidu Wang, Xiangyu Zhu, Tianshuo Zhang, Baiqin Wang, Zhen Lei
Abstract: 3D Morphable Models (3DMMs) provide promising 3D face reconstructions in various applications. However, existing methods struggle to reconstruct faces with extreme expressions due to deficiencies in supervisory signals, such as sparse or inaccurate landmarks. Segmentation information contains effective geometric contexts for face reconstruction. Certain attempts intuitively depend on differentiable renderers to compare the rendered silhouettes of reconstruction with segmentation, which is prone to issues like local optima and gradient instability. In this paper, we fully utilize the facial part segmentation geometry by introducing Part Re-projection Distance Loss (PRDL). Specifically, PRDL transforms facial part segmentation into 2D points and re-projects the reconstruction onto the image plane. Subsequently, by introducing grid anchors and computing different statistical distances from these anchors to the point sets, PRDL establishes geometry descriptors to optimize the distribution of the point sets for face reconstruction. PRDL exhibits a clear gradient compared to the renderer-based methods and presents state-of-the-art reconstruction performance in extensive quantitative and qualitative experiments. Our project is available at https://github.com/wang-zidu/3DDFA-V3 .
Authors: Pietro Bonazzi, Sizhen Bian, Giovanni Lippolis, Yawei Li, Sadique Sheik, Michele Magno
Abstract: This paper introduces a neuromorphic methodology for eye tracking, harnessing pure event data captured by a Dynamic Vision Sensor (DVS) camera. The framework integrates a directly trained Spiking Neuron Network (SNN) regression model and leverages a state-of-the-art low power edge neuromorphic processor - Speck, collectively aiming to advance the precision and efficiency of eye-tracking systems. First, we introduce a representative event-based eye-tracking dataset, "Ini-30", which was collected with two glass-mounted DVS cameras from thirty volunteers. Then,a SNN model, based on Integrate And Fire (IAF) neurons, named "Retina", is described , featuring only 64k parameters (6.63x fewer than the latest) and achieving pupil tracking error of only 3.24 pixels in a 64x64 DVS input. The continous regression output is obtained by means of convolution using a non-spiking temporal 1D filter slided across the output spiking layer. Finally, we evaluate Retina on the neuromorphic processor, showing an end-to-end power between 2.89-4.8 mW and a latency of 5.57-8.01 mS dependent on the time window. We also benchmark our model against the latest event-based eye-tracking method, "3ET", which was built upon event frames. Results show that Retina achieves superior precision with 1.24px less pupil centroid error and reduced computational complexity with 35 times fewer MAC operations. We hope this work will open avenues for further investigation of close-loop neuromorphic solutions and true event-based training pursuing edge performance.
Authors: Wenjie Pei, Qizhong Tan, Guangming Lu, Jiandong Tian
Abstract: Adapting large pre-trained image models to few-shot action recognition has proven to be an effective and efficient strategy for learning robust feature extractors, which is essential for few-shot learning. Typical fine-tuning based adaptation paradigm is prone to overfitting in the few-shot learning scenarios and offers little modeling flexibility for learning temporal features in video data. In this work we present the Disentangled-and-Deformable Spatio-Temporal Adapter (D$^2$ST-Adapter), which is a novel adapter tuning framework well-suited for few-shot action recognition due to lightweight design and low parameter-learning overhead. It is designed in a dual-pathway architecture to encode spatial and temporal features in a disentangled manner. In particular, we devise the anisotropic Deformable Spatio-Temporal Attention module as the core component of D$^2$ST-Adapter, which can be tailored with anisotropic sampling densities along spatial and temporal domains to learn spatial and temporal features specifically in corresponding pathways, allowing our D$^2$ST-Adapter to encode features in a global view in 3D spatio-temporal space while maintaining a lightweight design. Extensive experiments with instantiations of our method on both pre-trained ResNet and ViT demonstrate the superiority of our method over state-of-the-art methods for few-shot action recognition. Our method is particularly well-suited to challenging scenarios where temporal dynamics are critical for action recognition.
Authors: Felix Tristram, Stefano Gasperini, Nassir Navab, Federico Tombari
Abstract: Neural Radiance Fields (NeRFs) have shown remarkable novel view synthesis capabilities even in large-scale, unbounded scenes, albeit requiring hundreds of views or introducing artifacts in sparser settings. Their optimization suffers from shape-radiance ambiguities wherever only a small visual overlap is available. This leads to erroneous scene geometry and artifacts. In this paper, we propose Re-Nerfing, a simple and general multi-stage data augmentation approach that leverages NeRF's own view synthesis ability to address these limitations. With Re-Nerfing, we enhance the geometric consistency of novel views as follows: First, we train a NeRF with the available views. Then, we use the optimized NeRF to synthesize pseudo-views around the original ones with a view selection strategy to improve coverage and preserve view quality. Finally, we train a second NeRF with both the original images and the pseudo views masking out uncertain regions. Extensive experiments applying Re-Nerfing on various pipelines on the mip-NeRF 360 dataset, including Gaussian Splatting, provide valuable insights into the improvements achievable without external data or supervision, on denser and sparser input scenarios. Project page: https://renerfing.github.io
Authors: Lennart Bastian, Yizheng Xie, Nassir Navab, Zorah L\"ahner
Abstract: Non-isometric shape correspondence remains a fundamental challenge in computer vision. Traditional methods using Laplace-Beltrami operator (LBO) eigenmodes face limitations in characterizing high-frequency extrinsic shape changes like bending and creases. We propose a novel approach of combining the non-orthogonal extrinsic basis of eigenfunctions of the elastic thin-shell hessian with the intrinsic ones of the LBO, creating a hybrid spectral space in which we construct functional maps. To this end, we present a theoretical framework to effectively integrate non-orthogonal basis functions into descriptor- and learning-based functional map methods. Our approach can be incorporated easily into existing functional map pipelines across varying applications and is able to handle complex deformations beyond isometries. We show extensive evaluations across various supervised and unsupervised settings and demonstrate significant improvements. Notably, our approach achieves up to 15% better mean geodesic error for non-isometric correspondence settings and up to 45% improvement in scenarios with topological noise.
Authors: Kirill Mazur, Gwangbin Bae, Andrew J. Davison
Abstract: Joint camera pose and dense geometry estimation from a set of images or a monocular video remains a challenging problem due to its computational complexity and inherent visual ambiguities. Most dense incremental reconstruction systems operate directly on image pixels and solve for their 3D positions using multi-view geometry cues. Such pixel-level approaches suffer from ambiguities or violations of multi-view consistency (e.g. caused by textureless or specular surfaces). We address this issue with a new image representation which we call a SuperPrimitive. SuperPrimitives are obtained by splitting images into semantically correlated local regions and enhancing them with estimated surface normal directions, both of which are predicted by state-of-the-art single image neural networks. This provides a local geometry estimate per SuperPrimitive, while their relative positions are adjusted based on multi-view observations. We demonstrate the versatility of our new representation by addressing three 3D reconstruction tasks: depth completion, few-view structure from motion, and monocular dense visual odometry.
Authors: Yi Chen, Yuying Ge, Yixiao Ge, Mingyu Ding, Bohao Li, Rui Wang, Ruifeng Xu, Ying Shan, Xihui Liu
Abstract: Multimodal Large Language Models, combining the remarkable reasoning and generalization capabilities of Large Language Models (LLMs) with the ability to comprehend visual inputs, have opened up new avenues for embodied task planning. Given diverse environmental inputs, including real-time task progress, visual observations, and open-form language instructions, a proficient task planner is expected to predict feasible actions, which is a feat inherently achievable by Multimodal Large Language Models (MLLMs). In this paper, we aim to quantitatively investigate the potential of MLLMs as embodied task planners in real-world scenarios by introducing a benchmark with human annotations named EgoPlan-Bench. Our benchmark is distinguished by realistic tasks derived from real-world videos, a diverse set of actions involving interactions with hundreds of different objects, and complex visual observations from varied scenes. We evaluate a wide range of MLLMs, revealing that these models have not yet evolved into embodied planning generalists (even GPT-4V). We further construct an instruction-tuning dataset EgoPlan-IT from videos with human-object interactions, to facilitate the learning of high-level task planning in intricate real-world situations. The experiment results demonstrate that the model tuned on EgoPlan-IT not only significantly improves performance on our benchmark, but can also be applied as a task planner for guiding embodied agents in simulations.
Authors: Saeed Saadatnejad, Yang Gao, Kaouther Messaoud, Alexandre Alahi
Abstract: Accurate human trajectory prediction is crucial for applications such as autonomous vehicles, robotics, and surveillance systems. Yet, existing models often fail to fully leverage the non-verbal social cues human subconsciously communicate when navigating the space. To address this, we introduce Social-Transmotion, a generic Transformer-based model that exploits diverse and numerous visual cues to predict human behavior. We translate the idea of a prompt from Natural Language Processing (NLP) to the task of human trajectory prediction, where a prompt can be a sequence of x-y coordinates on the ground, bounding boxes in the image plane, or body pose keypoints in either 2D or 3D. This, in turn, augments trajectory data, leading to enhanced human trajectory prediction. Using masking technique, our model exhibits flexibility and adaptability by capturing spatiotemporal interactions between agents based on the available visual cues. We delve into the merits of using 2D versus 3D poses, and a limited set of poses. Additionally, we investigate the spatial and temporal attention map to identify which keypoints and time-steps in the sequence are vital for optimizing human trajectory prediction. Our approach is validated on multiple datasets, including JTA, JRDB, Pedestrians and Cyclists in Road Traffic, and ETH-UCY. The code is publicly available: https://github.com/vita-epfl/social-transmotion.
Authors: Minglong Xue, Jinhong He, Wenhai Wang, Mingliang Zhou
Abstract: Low-light image enhancement techniques have significantly progressed, but unstable image quality recovery and unsatisfactory visual perception are still significant challenges. To solve these problems, we propose a novel and robust low-light image enhancement method via CLIP-Fourier Guided Wavelet Diffusion, abbreviated as CFWD. Specifically, CFWD leverages multimodal visual-language information in the frequency domain space created by multiple wavelet transforms to guide the enhancement process. Multi-scale supervision across different modalities facilitates the alignment of image features with semantic features during the wavelet diffusion process, effectively bridging the gap between degraded and normal domains. Moreover, to further promote the effective recovery of the image details, we combine the Fourier transform based on the wavelet transform and construct a Hybrid High Frequency Perception Module (HFPM) with a significant perception of the detailed features. This module avoids the diversity confusion of the wavelet diffusion process by guiding the fine-grained structure recovery of the enhancement results to achieve favourable metric and perceptually oriented enhancement. Extensive quantitative and qualitative experiments on publicly available real-world benchmarks show that our approach outperforms existing state-of-the-art methods, achieving significant progress in image quality and noise suppression. The project code is available at https://github.com/hejh8/CFWD.
Authors: Ziying Song, Guoxing Zhang, Lin Liu, Lei Yang, Shaoqing Xu, Caiyan Jia, Feiyang Jia, Li Wang
Abstract: Multi-modal 3D object detectors are dedicated to exploring secure and reliable perception systems for autonomous driving (AD). However, while achieving state-of-the-art (SOTA) performance on clean benchmark datasets, they tend to overlook the complexity and harsh conditions of real-world environments. Meanwhile, with the emergence of visual foundation models (VFMs), opportunities and challenges are presented for improving the robustness and generalization of multi-modal 3D object detection in autonomous driving. Therefore, we propose RoboFusion, a robust framework that leverages VFMs like SAM to tackle out-of-distribution (OOD) noise scenarios. We first adapt the original SAM for autonomous driving scenarios named SAM-AD. To align SAM or SAM-AD with multi-modal methods, we then introduce AD-FPN for upsampling the image features extracted by SAM. We employ wavelet decomposition to denoise the depth-guided images for further noise reduction and weather interference. Lastly, we employ self-attention mechanisms to adaptively reweight the fused features, enhancing informative features while suppressing excess noise. In summary, our RoboFusion gradually reduces noise by leveraging the generalization and robustness of VFMs, thereby enhancing the resilience of multi-modal 3D object detection. Consequently, our RoboFusion achieves state-of-the-art performance in noisy scenarios, as demonstrated by the KITTI-C and nuScenes-C benchmarks.
Authors: Merey Ramazanova, Alejandro Pardo, Humam Alwassel, Bernard Ghanem
Abstract: Multimodal video understanding is crucial for analyzing egocentric videos, where integrating multiple sensory signals significantly enhances action recognition and moment localization. However, practical applications often grapple with incomplete modalities due to factors like privacy concerns, efficiency demands, or hardware malfunctions. Addressing this, our study delves into the impact of missing modalities on egocentric action recognition, particularly within transformer-based models. We introduce a novel concept -Missing Modality Token (MMT)-to maintain performance even when modalities are absent, a strategy that proves effective in the Ego4D, Epic-Kitchens, and Epic-Sounds datasets. Our method mitigates the performance loss, reducing it from its original $\sim 30\%$ drop to only $\sim 10\%$ when half of the test set is modal-incomplete. Through extensive experimentation, we demonstrate the adaptability of MMT to different training scenarios and its superiority in handling missing modalities compared to current methods. Our research contributes a comprehensive analysis and an innovative approach, opening avenues for more resilient multimodal systems in real-world settings.
Authors: Yanhua Zhang, Ke Zhang, Jingyu Wang, Yulin Wu, Wuwei Wang
Abstract: Real-time semantic segmentation is a crucial research for real-world applications. However, many methods lay particular emphasis on reducing the computational complexity and model size, while largely sacrificing the accuracy. To tackle this problem, we propose a parallel inference network customized for semantic segmentation tasks to achieve a good trade-off between speed and accuracy. We employ a shallow backbone to ensure real-time speed, and propose three core components to compensate for the reduced model capacity to improve accuracy. Specifically, we first design a dual-pyramidal path architecture (Multi-level Feature Aggregation Module, MFAM) to aggregate multi-level features from the encoder to each scale, providing hierarchical clues for subsequent spatial alignment and corresponding in-network inference. Then, we build Recursive Alignment Module (RAM) by combining the flow-based alignment module with recursive upsampling architecture for accurate spatial alignment between multi-scale feature maps with half the computational complexity of the straightforward alignment method. Finally, we perform independent parallel inference on the aligned features to obtain multi-scale scores, and adaptively fuse them through an attention-based Adaptive Scores Fusion Module (ASFM) so that the final prediction can favor objects of multiple scales. Our framework shows a better balance between speed and accuracy than state-of-the-art real-time methods on Cityscapes and CamVid datasets. We also conducted systematic ablation studies to gain insight into our motivation and architectural design. Code is available at: https://github.com/Yanhua-Zhang/MFARANet.
Authors: Dayou Mao, Yuhao Chen, Yifan Wu, Maximilian Gilles, Alexander Wong
Abstract: One of the main motivations of MTL is to develop neural networks capable of inferring multiple tasks simultaneously. While countless methods have been proposed in the past decade investigating robust model architectures and efficient training algorithms, there is still lack of understanding of these methods when applied on smaller feature extraction backbones, the generalizability of the commonly used fast approximation technique of replacing parameter-level gradients with feature level gradients, and lack of comprehensive understanding of MTL challenges and how one can efficiently and effectively identify the challenges. In this paper, we focus on the aforementioned efficiency aspects of existing MTL methods. We first carry out large-scale experiments of the methods with smaller backbones and on a the MetaGraspNet dataset as a new test ground. We also compare the existing methods with and without using the fast gradient surrogate and empirically study the generalizability of this technique. Lastly, we propose Feature Disentanglement measure as a novel and efficient identifier of the challenges in MTL, and propose Ranking Similarity score as an evaluation metric for different identifiers to prove the faithfulness of our method.
Authors: Luca Crupi, Alessandro Giusti, Daniele Palossi
Abstract: Relative drone-to-drone localization is a fundamental building block for any swarm operations. We address this task in the context of miniaturized nano-drones, i.e., 10cm in diameter, which show an ever-growing interest due to novel use cases enabled by their reduced form factor. The price for their versatility comes with limited onboard resources, i.e., sensors, processing units, and memory, which limits the complexity of the onboard algorithms. A traditional solution to overcome these limitations is represented by lightweight deep learning models directly deployed aboard nano-drones. This work tackles the challenging relative pose estimation between nano-drones using only a gray-scale low-resolution camera and an ultra-low-power System-on-Chip (SoC) hosted onboard. We present a vertically integrated system based on a novel vision-based fully convolutional neural network (FCNN), which runs at 39Hz within 101mW onboard a Crazyflie nano-drone extended with the GWT GAP8 SoC. We compare our FCNN against three State-of-the-Art (SoA) systems. Considering the best-performing SoA approach, our model results in an R-squared improvement from 32 to 47% on the horizontal image coordinate and from 18 to 55% on the vertical image coordinate, on a real-world dataset of 30k images. Finally, our in-field tests show a reduction of the average tracking error of 37% compared to a previous SoA work and an endurance performance up to the entire battery lifetime of 4 minutes.
Authors: Chunyi Li, Guo Lu, Donghui Feng, Haoning Wu, Zicheng Zhang, Xiaohong Liu, Guangtao Zhai, Weisi Lin, Wenjun Zhang
Abstract: With the evolution of storage and communication protocols, ultra-low bitrate image compression has become a highly demanding topic. However, existing compression algorithms must sacrifice either consistency with the ground truth or perceptual quality at ultra-low bitrate. In recent years, the rapid development of the Large Multimodal Model (LMM) has made it possible to balance these two goals. To solve this problem, this paper proposes a method called Multimodal Image Semantic Compression (MISC), which consists of an LMM encoder for extracting the semantic information of the image, a map encoder to locate the region corresponding to the semantic, an image encoder generates an extremely compressed bitstream, and a decoder reconstructs the image based on the above information. Experimental results show that our proposed MISC is suitable for compressing both traditional Natural Sense Images (NSIs) and emerging AI-Generated Images (AIGIs) content. It can achieve optimal consistency and perception results while saving 50% bitrate, which has strong potential applications in the next generation of storage and communication. The code will be released on https://github.com/lcysyzxdxc/MISC.
Authors: Ziyue Feng, Huangying Zhan, Zheng Chen, Qingan Yan, Xiangyu Xu, Changjiang Cai, Bing Li, Qilun Zhu, Yi Xu
Abstract: We present NARUTO, a neural active reconstruction system that combines a hybrid neural representation with uncertainty learning, enabling high-fidelity surface reconstruction. Our approach leverages a multi-resolution hash-grid as the mapping backbone, chosen for its exceptional convergence speed and capacity to capture high-frequency local features.The centerpiece of our work is the incorporation of an uncertainty learning module that dynamically quantifies reconstruction uncertainty while actively reconstructing the environment. By harnessing learned uncertainty, we propose a novel uncertainty aggregation strategy for goal searching and efficient path planning. Our system autonomously explores by targeting uncertain observations and reconstructs environments with remarkable completeness and fidelity. We also demonstrate the utility of this uncertainty-aware approach by enhancing SOTA neural SLAM systems through an active ray sampling strategy. Extensive evaluations of NARUTO in various environments, using an indoor scene simulator, confirm its superior performance and state-of-the-art status in active reconstruction, as evidenced by its impressive results on benchmark datasets like Replica and MP3D.
Authors: Weiyun Wang, Yiming Ren, Haowen Luo, Tiantong Li, Chenxiang Yan, Zhe Chen, Wenhai Wang, Qingyun Li, Lewei Lu, Xizhou Zhu, Yu Qiao, Jifeng Dai
Abstract: We present the All-Seeing Project V2: a new model and dataset designed for understanding object relations in images. Specifically, we propose the All-Seeing Model V2 (ASMv2) that integrates the formulation of text generation, object localization, and relation comprehension into a relation conversation (ReC) task. Leveraging this unified task, our model excels not only in perceiving and recognizing all objects within the image but also in grasping the intricate relation graph between them, diminishing the relation hallucination often encountered by Multi-modal Large Language Models (MLLMs). To facilitate training and evaluation of MLLMs in relation understanding, we created the first high-quality ReC dataset ({AS-V2) which is aligned with the format of standard instruction tuning data. In addition, we design a new benchmark, termed Circular-based Relation Probing Evaluation (CRPE) for comprehensively evaluating the relation comprehension capabilities of MLLMs. Notably, our ASMv2 achieves an overall accuracy of 52.04 on this relation-aware benchmark, surpassing the 43.14 of LLaVA-1.5 by a large margin. We hope that our work can inspire more future research and contribute to the evolution towards artificial general intelligence. Our project is released at https://github.com/OpenGVLab/all-seeing.
Authors: Chen Duan, Pei Fu, Shan Guo, Qianyi Jiang, Xiaoming Wei
Abstract: In recent years, text-image joint pre-training techniques have shown promising results in various tasks. However, in Optical Character Recognition (OCR) tasks, aligning text instances with their corresponding text regions in images poses a challenge, as it requires effective alignment between text and OCR-Text (referring to the text in images as OCR-Text to distinguish from the text in natural language) rather than a holistic understanding of the overall image content. In this paper, we propose a new pre-training method called OCR-Text Destylization Modeling (ODM) that transfers diverse styles of text found in images to a uniform style based on the text prompt. With ODM, we achieve better alignment between text and OCR-Text and enable pre-trained models to adapt to the complex and diverse styles of scene text detection and spotting tasks. Additionally, we have designed a new labeling generation method specifically for ODM and combined it with our proposed Text-Controller module to address the challenge of annotation costs in OCR tasks, allowing a larger amount of unlabeled data to participate in pre-training. Extensive experiments on multiple public datasets demonstrate that our method significantly improves performance and outperforms current pre-training methods in scene text detection and spotting tasks. Code is available at https://github.com/PriNing/ODM.
Authors: Stefan Denner, David Zimmerer, Dimitrios Bounias, Markus Bujotzek, Shuhan Xiao, Lisa Kausch, Philipp Schader, Tobias Penzkofer, Paul F. J\"ager, Klaus Maier-Hein
Abstract: Content-based image retrieval (CBIR) has the potential to significantly improve diagnostic aid and medical research in radiology. Current CBIR systems face limitations due to their specialization to certain pathologies, limiting their utility. In response, we propose using vision foundation models as powerful and versatile off-the-shelf feature extractors for content-based medical image retrieval. By benchmarking these models on a comprehensive dataset of 1.6 million 2D radiological images spanning four modalities and 161 pathologies, we identify weakly-supervised models as superior, achieving a P@1 of up to 0.594. This performance not only competes with a specialized model but does so without the need for fine-tuning. Our analysis further explores the challenges in retrieving pathological versus anatomical structures, indicating that accurate retrieval of pathological features presents greater difficulty. Despite these challenges, our research underscores the vast potential of foundation models for CBIR in radiology, proposing a shift towards versatile, general-purpose medical image retrieval systems that do not require specific tuning.
Authors: Tomas Hodan, Martin Sundermeyer, Yann Labbe, Van Nguyen Nguyen, Gu Wang, Eric Brachmann, Bertram Drost, Vincent Lepetit, Carsten Rother, Jiri Matas
Abstract: We present the evaluation methodology, datasets and results of the BOP Challenge 2023, the fifth in a series of public competitions organized to capture the state of the art in model-based 6D object pose estimation from an RGB/RGB-D image and related tasks. Besides the three tasks from 2022 (model-based 2D detection, 2D segmentation, and 6D localization of objects seen during training), the 2023 challenge introduced new variants of these tasks focused on objects unseen during training. In the new tasks, methods were required to learn new objects during a short onboarding stage (max 5 minutes, 1 GPU) from provided 3D object models. The best 2023 method for 6D localization of unseen objects (GenFlow) notably reached the accuracy of the best 2020 method for seen objects (CosyPose), although being noticeably slower. The best 2023 method for seen objects (GPose) achieved a moderate accuracy improvement but a significant 43% run-time improvement compared to the best 2022 counterpart (GDRNPP). Since 2017, the accuracy of 6D localization of seen objects has improved by more than 50% (from 56.9 to 85.6 AR_C). The online evaluation system stays open and is available at: http://bop.felk.cvut.cz/.
Authors: Minh Tran, Winston Bounsavy, Khoa Vo, Anh Nguyen, Tri Nguyen, Ngan Le
Abstract: Amodal Instance Segmentation (AIS) presents a challenging task as it involves predicting both visible and occluded parts of objects within images. Existing AIS methods rely on a bidirectional approach, encompassing both the transition from amodal features to visible features (amodal-to-visible) and from visible features to amodal features (visible-to-amodal). Our observation shows that the utilization of amodal features through the amodal-to-visible can confuse the visible features due to the extra information of occluded/hidden segments not presented in visible display. Consequently, this compromised quality of visible features during the subsequent visible-to-amodal transition. To tackle this issue, we introduce ShapeFormer, a decoupled Transformer-based model with a visible-to-amodal transition. It facilitates the explicit relationship between output segmentations and avoids the need for amodal-to-visible transitions. ShapeFormer comprises three key modules: (i) Visible-Occluding Mask Head for predicting visible segmentation with occlusion awareness, (ii) Shape-Prior Amodal Mask Head for predicting amodal and occluded masks, and (iii) Category-Specific Shape Prior Retriever aims to provide shape prior knowledge. Comprehensive experiments and extensive ablation studies across various AIS benchmarks demonstrate the effectiveness of our ShapeFormer. The code is available at: \url{https://github.com/UARK-AICV/ShapeFormer}
Authors: Yuda Song, Zehao Sun, Xuanwu Yin
Abstract: Recent advancements in diffusion models have positioned them at the forefront of image generation. Despite their superior performance, diffusion models are not without drawbacks; they are characterized by complex architectures and substantial computational demands, resulting in significant latency due to their iterative sampling process. To mitigate these limitations, we introduce a dual approach involving model miniaturization and a reduction in sampling steps, aimed at significantly decreasing model latency. Our methodology leverages knowledge distillation to streamline the U-Net and image decoder architectures, and introduces an innovative one-step DM training technique that utilizes feature matching and score distillation. We present two models, SDXS-512 and SDXS-1024, achieving inference speeds of approximately 100 FPS (30x faster than SD v1.5) and 30 FPS (60x faster than SDXL) on a single GPU, respectively. Moreover, our training approach offers promising applications in image-conditioned control, facilitating efficient image-to-image translation.
Authors: Suraj Patni, Aradhye Agarwal, Chetan Arora
Abstract: In the absence of parallax cues, a learning-based single image depth estimation (SIDE) model relies heavily on shading and contextual cues in the image. While this simplicity is attractive, it is necessary to train such models on large and varied datasets, which are difficult to capture. It has been shown that using embeddings from pre-trained foundational models, such as CLIP, improves zero shot transfer in several applications. Taking inspiration from this, in our paper we explore the use of global image priors generated from a pre-trained ViT model to provide more detailed contextual information. We argue that the embedding vector from a ViT model, pre-trained on a large dataset, captures greater relevant information for SIDE than the usual route of generating pseudo image captions, followed by CLIP based text embeddings. Based on this idea, we propose a new SIDE model using a diffusion backbone which is conditioned on ViT embeddings. Our proposed design establishes a new state-of-the-art (SOTA) for SIDE on NYUv2 dataset, achieving Abs Rel error of 0.059 (14% improvement) compared to 0.069 by the current SOTA (VPD). And on KITTI dataset, achieving Sq Rel error of 0.139 (2% improvement) compared to 0.142 by the current SOTA (GEDepth). For zero-shot transfer with a model trained on NYUv2, we report mean relative improvement of (20%, 23%, 81%, 25%) over NeWCRFs on (Sun-RGBD, iBims1, DIODE, HyperSim) datasets, compared to (16%, 18%, 45%, 9%) by ZoeDepth. The project page is available at https://ecodepth-iitd.github.io
Authors: Chenhao Zheng, Jieyu Zhang, Aniruddha Kembhavi, Ranjay Krishna
Abstract: A fundamental characteristic common to both human vision and natural language is their compositional nature. Yet, despite the performance gains contributed by large vision and language pretraining, recent investigations find that most-if not all-our state-of-the-art vision-language models struggle at compositionality. They are unable to distinguish between images of " a girl in white facing a man in black" and "a girl in black facing a man in white". Moreover, prior work suggests that compositionality doesn't arise with scale: larger model sizes or training data don't help. This paper develops a new iterated training algorithm that incentivizes compositionality. We draw on decades of cognitive science research that identifies cultural transmission-the need to teach a new generation-as a necessary inductive prior that incentivizes humans to develop compositional languages. Specifically, we reframe vision-language contrastive learning as the Lewis Signaling Game between a vision agent and a language agent, and operationalize cultural transmission by iteratively resetting one of the agent's weights during training. After every iteration, this training paradigm induces representations that become "easier to learn", a property of compositional languages: e.g. our model trained on CC3M and CC12M improves standard CLIP by 4.7%, 4.0% respectfully in the SugarCrepe benchmark.
Authors: Joshua Ahn, Haochen Wang, Raymond A. Yeh, Greg Shakhnarovich
Abstract: Scale-ambiguity in 3D scene dimensions leads to magnitude-ambiguity of volumetric densities in neural radiance fields, i.e., the densities double when scene size is halved, and vice versa. We call this property alpha invariance. For NeRFs to better maintain alpha invariance, we recommend 1) parameterizing both distance and volume densities in log space, and 2) a discretization-agnostic initialization strategy to guarantee high ray transmittance. We revisit a few popular radiance field models and find that these systems use various heuristics to deal with issues arising from scene scaling. We test their behaviors and show our recipe to be more robust.
Authors: Zhonglin Liu, Shujie Chen, Jianfeng Dong, Xun Wang, Di Zhou
Abstract: Achieving high-performance in multi-object tracking algorithms heavily relies on modeling spatio-temporal relationships during the data association stage. Mainstream approaches encompass rule-based and deep learning-based methods for spatio-temporal relationship modeling. While the former relies on physical motion laws, offering wider applicability but yielding suboptimal results for complex object movements, the latter, though achieving high-performance, lacks interpretability and involves complex module designs. This work aims to simplify deep learning-based spatio-temporal relationship models and introduce interpretability into features for data association. Specifically, a lightweight single-layer transformer encoder is utilized to model spatio-temporal relationships. To make features more interpretative, two contrastive regularization losses based on representation alignment are proposed, derived from spatio-temporal consistency rules. By applying weighted summation to affinity matrices, the aligned features can seamlessly integrate into the data association stage of the original tracking workflow. Experimental results showcase that our model enhances the majority of existing tracking networks' performance without excessive complexity, with minimal increase in training overhead and nearly negligible computational and storage costs.
Authors: Lifan Jiang, Zhihui Wang, Changmiao Wang, Ming Li, Jiaxu Leng, Xindong Wu
Abstract: Object detection, a quintessential task in the realm of perceptual computing, can be tackled using a generative methodology. In the present study, we introduce a novel framework designed to articulate object detection as a denoising diffusion process, which operates on the perturbed bounding boxes of annotated entities. This framework, termed ConsistencyDet, leverages an innovative denoising concept known as the Consistency Model. The hallmark of this model is its self-consistency feature, which empowers the model to map distorted information from any temporal stage back to its pristine state, thereby realizing a "one-step denoising" mechanism. Such an attribute markedly elevates the operational efficiency of the model, setting it apart from the conventional Diffusion Model. Throughout the training phase, ConsistencyDet initiates the diffusion sequence with noise-infused boxes derived from the ground-truth annotations and conditions the model to perform the denoising task. Subsequently, in the inference stage, the model employs a denoising sampling strategy that commences with bounding boxes randomly sampled from a normal distribution. Through iterative refinement, the model transforms an assortment of arbitrarily generated boxes into definitive detections. Comprehensive evaluations employing standard benchmarks, such as MS-COCO and LVIS, corroborate that ConsistencyDet surpasses other leading-edge detectors in performance metrics. Our code is available at https://github.com/Tankowa/ConsistencyDet.
Authors: Yidan Liu, Jun Yue, Shaobo Xia, Pedram Ghamisi, Weiying Xie, Leyuan Fang
Abstract: As a newly emerging advance in deep generative models, diffusion models have achieved state-of-the-art results in many fields, including computer vision, natural language processing, and molecule design. The remote sensing community has also noticed the powerful ability of diffusion models and quickly applied them to a variety of tasks for image processing. Given the rapid increase in research on diffusion models in the field of remote sensing, it is necessary to conduct a comprehensive review of existing diffusion model-based remote sensing papers, to help researchers recognize the potential of diffusion models and provide some directions for further exploration. Specifically, this paper first introduces the theoretical background of diffusion models, and then systematically reviews the applications of diffusion models in remote sensing, including image generation, enhancement, and interpretation. Finally, the limitations of existing remote sensing diffusion models and worthy research directions for further exploration are discussed and summarized.
Authors: Bor-Shiun Wang, Chien-Yi Wang, Wei-Chen Chiu
Abstract: Recent advancements in post-hoc and inherently interpretable methods have markedly enhanced the explanations of black box classifier models. These methods operate either through post-analysis or by integrating concept learning during model training. Although being effective in bridging the semantic gap between a model's latent space and human interpretation, these explanation methods only partially reveal the model's decision-making process. The outcome is typically limited to high-level semantics derived from the last feature map. We argue that the explanations lacking insights into the decision processes at low and mid-level features are neither fully faithful nor useful. Addressing this gap, we introduce the Multi-Level Concept Prototypes Classifier (MCPNet), an inherently interpretable model. MCPNet autonomously learns meaningful concept prototypes across multiple feature map levels using Centered Kernel Alignment (CKA) loss and an energy-based weighted PCA mechanism, and it does so without reliance on predefined concept labels. Further, we propose a novel classifier paradigm that learns and aligns multi-level concept prototype distributions for classification purposes via Class-aware Concept Distribution (CCD) loss. Our experiments reveal that our proposed MCPNet while being adaptable to various model architectures, offers comprehensive multi-level explanations while maintaining classification accuracy. Additionally, its concept distribution-based classification approach shows improved generalization capabilities in few-shot classification scenarios.
Authors: Diana-Nicoleta Grigore, Mariana-Iuliana Georgescu, Jon Alvarez Justo, Tor Johansen, Andreea Iuliana Ionescu, Radu Tudor Ionescu
Abstract: Few-shot knowledge distillation recently emerged as a viable approach to harness the knowledge of large-scale pre-trained models, using limited data and computational resources. In this paper, we propose a novel few-shot feature distillation approach for vision transformers. Our approach is based on two key steps. Leveraging the fact that vision transformers have a consistent depth-wise structure, we first copy the weights from intermittent layers of existing pre-trained vision transformers (teachers) into shallower architectures (students), where the intermittence factor controls the complexity of the student transformer with respect to its teacher. Next, we employ an enhanced version of Low-Rank Adaptation (LoRA) to distill knowledge into the student in a few-shot scenario, aiming to recover the information processing carried out by the skipped teacher layers. We present comprehensive experiments with supervised and self-supervised transformers as teachers, on five data sets from various domains, including natural, medical and satellite images. The empirical results confirm the superiority of our approach over competitive baselines. Moreover, the ablation results demonstrate the usefulness of each component of the proposed pipeline.
Authors: Jiyuan Wang, Chunyu Lin, Lang Nie, Kang Liao, Shuwei Shao, Yao Zhao
Abstract: Recently, diffusion-based depth estimation methods have drawn widespread attention due to their elegant denoising patterns and promising performance. However, they are typically unreliable under adverse conditions prevalent in real-world scenarios, such as rainy, snowy, etc. In this paper, we propose a novel robust depth estimation method called D4RD, featuring a custom contrastive learning mode tailored for diffusion models to mitigate performance degradation in complex environments. Concretely, we integrate the strength of knowledge distillation into contrastive learning, building the `trinity' contrastive scheme. This scheme utilizes the sampled noise of the forward diffusion process as a natural reference, guiding the predicted noise in diverse scenes toward a more stable and precise optimum. Moreover, we extend noise-level trinity to encompass more generic feature and image levels, establishing a multi-level contrast to distribute the burden of robust perception across the overall network. Before addressing complex scenarios, we enhance the stability of the baseline diffusion model with three straightforward yet effective improvements, which facilitate convergence and remove depth outliers. Extensive experiments demonstrate that D4RD surpasses existing state-of-the-art solutions on synthetic corruption datasets and real-world weather conditions. The code for D4RD will be made available for further exploration and adoption.
Authors: Yiqiao Yin
Abstract: Recent advancements in sequence prediction have significantly improved the accuracy of video data interpretation; however, existing models often overlook the potential of attention-based mechanisms for next-frame prediction. This study introduces the Vision Augmentation Prediction Autoencoder with Attention Design (VAPAAD), an innovative approach that integrates attention mechanisms into sequence prediction, enabling nuanced analysis and understanding of temporal dynamics in video sequences. Utilizing the Moving MNIST dataset, we demonstrate VAPAAD's robust performance and superior handling of complex temporal data compared to traditional methods. VAPAAD combines data augmentation, ConvLSTM2D layers, and a custom-built self-attention mechanism to effectively focus on salient features within a sequence, enhancing predictive accuracy and context-aware analysis. This methodology not only adheres to human cognitive processes during video interpretation but also addresses limitations in conventional models, which often struggle with the variability inherent in video sequences. The experimental results confirm that VAPAAD outperforms existing models, especially in integrating attention mechanisms, which significantly improve predictive performance.
Authors: Runyi Li, Xuhan Sheng, Weiqi Li, Jian Zhang
Abstract: Omnidirectional images (ODIs) are commonly used in real-world visual tasks, and high-resolution ODIs help improve the performance of related visual tasks. Most existing super-resolution methods for ODIs use end-to-end learning strategies, resulting in inferior realness of generated images and a lack of effective out-of-domain generalization capabilities in training methods. Image generation methods represented by diffusion model provide strong priors for visual tasks and have been proven to be effectively applied to image restoration tasks. Leveraging the image priors of the Stable Diffusion (SD) model, we achieve omnidirectional image super-resolution with both fidelity and realness, dubbed as OmniSSR. Firstly, we transform the equirectangular projection (ERP) images into tangent projection (TP) images, whose distribution approximates the planar image domain. Then, we use SD to iteratively sample initial high-resolution results. At each denoising iteration, we further correct and update the initial results using the proposed Octadecaplex Tangent Information Interaction (OTII) and Gradient Decomposition (GD) technique to ensure better consistency. Finally, the TP images are transformed back to obtain the final high-resolution results. Our method is zero-shot, requiring no training or fine-tuning. Experiments of our method on two benchmark datasets demonstrate the effectiveness of our proposed method.
Authors: Enming Zhang, Bingke Zhu, Yingying Chen, Qinghai Miao, Ming Tang, Jinqiao Wang
Abstract: Vision-Language Models (VLMs), such as CLIP, play a foundational role in various cross-modal applications. To fully leverage VLMs' potential in adapting to downstream tasks, context optimization methods like Prompt Tuning are essential. However, one key limitation is the lack of diversity in prompt templates, whether they are hand-crafted or learned through additional modules. This limitation restricts the capabilities of pretrained VLMs and can result in incorrect predictions in downstream tasks. To address this challenge, we propose Context Optimization with Multi-Knowledge Representation (CoKnow), a framework that enhances Prompt Learning for VLMs with rich contextual knowledge. To facilitate CoKnow during inference, we trained lightweight semantic knowledge mappers, which are capable of generating Multi-Knowledge Representation for an input image without requiring additional priors. Experimentally, We conducted extensive experiments on 11 publicly available datasets, demonstrating that CoKnow outperforms a series of previous methods. We will make all resources open-source: https://github.com/EMZucas/CoKnow.
Authors: Hongli Wen, Yang Xu
Abstract: Human action recognition and performance assessment have been hot research topics in recent years. Recognition problems have mature solutions in the field of sign language, but past research in performance analysis has focused on competitive sports and medical training, overlooking the scoring assessment ,which is an important part of sign language teaching digitalization. In this paper, we analyze the existing technologies for performance assessment and adopt methods that perform well in human pose reconstruction tasks combined with motion rotation embedded expressions, proposing a two-stage sign language performance evaluation pipeline. Our analysis shows that choosing reconstruction tasks in the first stage can provide more expressive features, and using smoothing methods can provide an effective reference for assessment. Experiments show that our method provides good score feedback mechanisms and high consistency with professional assessments compared to end-to-end evaluations.
Authors: Siyuan Li, Zicheng Liu, Zelin Zang, Di Wu, Zhiyuan Chen, Stan Z. Li
Abstract: Unsupervised representation learning (URL), which learns compact embeddings of high-dimensional data without supervision, has made remarkable progress recently. However, the development of URLs for different requirements is independent, which limits the generalization of the algorithms, especially prohibitive as the number of tasks grows. For example, dimension reduction methods, t-SNE, and UMAP optimize pair-wise data relationships by preserving the global geometric structure, while self-supervised learning, SimCLR, and BYOL focus on mining the local statistics of instances under specific augmentations. To address this dilemma, we summarize and propose a unified similarity-based URL framework, GenURL, which can smoothly adapt to various URL tasks. In this paper, we regard URL tasks as different implicit constraints on the data geometric structure that help to seek optimal low-dimensional representations that boil down to data structural modeling (DSM) and low-dimensional transformation (LDT). Specifically, DMS provides a structure-based submodule to describe the global structures, and LDT learns compact low-dimensional embeddings with given pretext tasks. Moreover, an objective function, General Kullback-Leibler divergence (GKL), is proposed to connect DMS and LDT naturally. Comprehensive experiments demonstrate that GenURL achieves consistent state-of-the-art performance in self-supervised visual learning, unsupervised knowledge distillation (KD), graph embeddings (GE), and dimension reduction.
Authors: Bhakti Baheti, Satrajit Chakrabarty, Hamed Akbari, Michel Bilello, Benedikt Wiestler, Julian Schwarting, Evan Calabrese, Jeffrey Rudie, Syed Abidi, Mina Mousa, Javier Villanueva-Meyer, Brandon K. K. Fields, Florian Kofler, Russell Takeshi Shinohara, Juan Eugenio Iglesias, Tony C. W. Mok, Albert C. S. Chung, Marek Wodzinski, Artur Jurgas, Niccolo Marini, Manfredo Atzori, Henning Muller, Christoph Grobroehmer, Hanna Siebert, Lasse Hansen, Mattias P. Heinrich, Luca Canalini, Jan Klein, Annika Gerken, Stefan Heldmann, Alessa Hering, Horst K. Hahn, Mingyuan Meng, Lei Bi, Dagan Feng, Jinman Kim, Ramy A. Zeineldin, Mohamed E. Karar, Franziska Mathis-Ullrich, Oliver Burgert, Javid Abderezaei, Aymeric Pionteck, Agamdeep Chopra, Mehmet Kurt, Kewei Yan, Yonghong Yan, Zhe Tang, Jianqiang Ma, Sahar Almahfouz Nasser, Nikhil Cherian Kurian, Mohit Meena, Saqib Shamsi, Amit Sethi, Nicholas J. Tustison, Brian B. Avants, Philip Cook, James C. Gee, Lin Tian, Hastings Greer, Marc Niethammer, Andrew Hoopes, Malte Hoffmann, Adrian V. Dalca, Stergios Christodoulidis, Theo Estiene, Maria Vakalopoulou, Nikos Paragios, Daniel S. Marcus, Christos Davatzikos, Aristeidis Sotiras, Bjoern Menze, Spyridon Bakas, Diana Waldmannstetter
Abstract: Registration of longitudinal brain MRI scans containing pathologies is challenging due to dramatic changes in tissue appearance. Although there has been progress in developing general-purpose medical image registration techniques, they have not yet attained the requisite precision and reliability for this task, highlighting its inherent complexity. Here we describe the Brain Tumor Sequence Registration (BraTS-Reg) challenge, as the first public benchmark environment for deformable registration algorithms focusing on estimating correspondences between pre-operative and follow-up scans of the same patient diagnosed with a diffuse brain glioma. The BraTS-Reg data comprise de-identified multi-institutional multi-parametric MRI (mpMRI) scans, curated for size and resolution according to a canonical anatomical template, and divided into training, validation, and testing sets. Clinical experts annotated ground truth (GT) landmark points of anatomical locations distinct across the temporal domain. Quantitative evaluation and ranking were based on the Median Euclidean Error (MEE), Robustness, and the determinant of the Jacobian of the displacement field. The top-ranked methodologies yielded similar performance across all evaluation metrics and shared several methodological commonalities, including pre-alignment, deep neural networks, inverse consistency analysis, and test-time instance optimization per-case basis as a post-processing step. The top-ranked method attained the MEE at or below that of the inter-rater variability for approximately 60% of the evaluated landmarks, underscoring the scope for further accuracy and robustness improvements, especially relative to human experts. The aim of BraTS-Reg is to continue to serve as an active resource for research, with the data and online evaluation tools accessible at https://bratsreg.github.io/.
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 dataset to evaluate localization algorithms, which utilizes vision, audio, and radio sensors: the Lund University Vision, Radio, and Audio (LuViRA) Dataset. The dataset includes RGB images, corresponding depth maps, IMU readings, channel response between a massive MIMO channel sounder and a user equipment, audio recorded by 12 microphones, and 0.5 mm accurate 6DoF pose ground truth. We synchronize these sensors to make sure that all data are recorded simultaneously. A camera, speaker, and transmit antenna are placed on top of a slowly moving service robot and 88 trajectories are recorded. Each trajectory includes 20 to 50 seconds of recorded sensor data and ground truth labels. The data from different sensors can be used separately or jointly to conduct localization tasks and a motion capture system is used to verify the results obtained by the localization algorithms. The main aim of this dataset is to enable research on fusing the most commonly used sensors for localization tasks. However, the full dataset or some parts of it can also be used for other research areas such as channel estimation, image classification, etc. Fusing sensor data can lead to increased localization accuracy and reliability, as well as decreased latency and power consumption. The created dataset will be made public at a later date.
Authors: Junde Wu, Jiayuan Zhu, Yueming Jin, Min Xu
Abstract: Large foundation models, known for their strong zero-shot generalization, have excelled in visual and language applications. However, applying them to medical image segmentation, a domain with diverse imaging types and target labels, remains an open challenge. Current approaches, such as adapting interactive segmentation models like Segment Anything Model (SAM), require user prompts for each sample during inference. Alternatively, transfer learning methods like few/one-shot models demand labeled samples, leading to high costs. This paper introduces a new paradigm toward the universal medical image segmentation, termed 'One-Prompt Segmentation.' One-Prompt Segmentation combines the strengths of one-shot and interactive methods. In the inference stage, with just \textbf{one prompted sample}, it can adeptly handle the unseen task in a single forward pass. We train One-Prompt Model on 64 open-source medical datasets, accompanied by the collection of over 3,000 clinician-labeled prompts. Tested on 14 previously unseen datasets, the One-Prompt Model showcases superior zero-shot segmentation capabilities, outperforming a wide range of related methods. The code and data is released as https://github.com/KidsWithTokens/one-prompt.
Authors: Shaoyan Pan, Elham Abouei, Junbo Peng, Joshua Qian, Jacob F Wynne, Tonghe Wang, Chih-Wei Chang, Justin Roper, Jonathon A Nye, Hui Mao, Xiaofeng Yang
Abstract: Objective: Positron Emission Tomography (PET) has been a commonly used imaging modality in broad clinical applications. One of the most important tradeoffs in PET imaging is between image quality and radiation dose: high image quality comes with high radiation exposure. Improving image quality is desirable for all clinical applications while minimizing radiation exposure is needed to reduce risk to patients. Approach: We introduce PET Consistency Model (PET-CM), an efficient diffusion-based method for generating high-quality full-dose PET images from low-dose PET images. It employs a two-step process, adding Gaussian noise to full-dose PET images in the forward diffusion, and then denoising them using a PET Shifted-window Vision Transformer (PET-VIT) network in the reverse diffusion. The PET-VIT network learns a consistency function that enables direct denoising of Gaussian noise into clean full-dose PET images. PET-CM achieves state-of-the-art image quality while requiring significantly less computation time than other methods. Results: In experiments comparing eighth-dose to full-dose images, PET-CM demonstrated impressive performance with NMAE of 1.278+/-0.122%, PSNR of 33.783+/-0.824dB, SSIM of 0.964+/-0.009, NCC of 0.968+/-0.011, HRS of 4.543, and SUV Error of 0.255+/-0.318%, with an average generation time of 62 seconds per patient. This is a significant improvement compared to the state-of-the-art diffusion-based model with PET-CM reaching this result 12x faster. Similarly, in the quarter-dose to full-dose image experiments, PET-CM delivered competitive outcomes, achieving an NMAE of 0.973+/-0.066%, PSNR of 36.172+/-0.801dB, SSIM of 0.984+/-0.004, NCC of 0.990+/-0.005, HRS of 4.428, and SUV Error of 0.151+/-0.192% using the same generation process, which underlining its high quantitative and clinical precision in both denoising scenario.
Authors: Bo Ye, Kai Gan, Tong Wei, Min-Ling Zhang
Abstract: In open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlabeled data while maintaining performance on seen categories from labeled data. The central challenge is the substantial learning gap between seen and novel categories, as the model learns the former faster due to accurate supervisory information. Moreover, capturing the semantics of unlabeled novel category samples is also challenging due to the missing label information. To address the above issues, we introduce 1) the adaptive synchronizing marginal loss which imposes class-specific negative margins to alleviate the model bias towards seen classes, and 2) the pseudo-label contrastive clustering which exploits pseudo-labels predicted by the model to group unlabeled data from the same category together in the output space. Extensive experiments on benchmark datasets demonstrate that previous approaches may significantly hinder novel class learning, whereas our method strikingly balances the learning pace between seen and novel classes, achieving a remarkable 3% average accuracy increase on the ImageNet dataset. Importantly, we find that fine-tuning the self-supervised pre-trained model significantly boosts the performance, which is overlooked in prior literature. Our code is available at https://github.com/yebo0216best/LPS-main.
Authors: Aviad Levis, Andrew A. Chael, Katherine L. Bouman, Maciek Wielgus, Pratul P. Srinivasan
Abstract: The interaction between the supermassive black hole at the center of the Milky Way, Sagittarius A*, and its accretion disk occasionally produces high-energy flares seen in X-ray, infrared, and radio. One proposed mechanism that produces flares is the formation of compact, bright regions that appear within the accretion disk and close to the event horizon. Understanding these flares provides a window into accretion processes. Although sophisticated simulations predict the formation of these flares, their structure has yet to be recovered by observations. Here we show the first three-dimensional (3D) reconstruction of an emission flare recovered from ALMA light curves observed on April 11, 2017. Our recovery shows compact, bright regions at a distance of roughly six times the event horizon. Moreover, it suggests a clockwise rotation in a low-inclination orbital plane, consistent with prior studies by GRAVITY and EHT. To recover this emission structure, we solve an ill-posed tomography problem by integrating a neural 3D representation with a gravitational model for black holes. Although the recovery is subject to, and sometimes sensitive to, the model assumptions, under physically motivated choices, our results are stable, and our approach is successful on simulated data.
Authors: Quoc-Huy Trinh, Minh-Van Nguyen, Phuoc-Thao Vo Thi
Abstract: Polyp segmentation, a contentious issue in medical imaging, has seen numerous proposed methods aimed at improving the quality of segmented masks. While current state-of-the-art techniques yield impressive results, the size and computational cost of these models create challenges for practical industry applications. To address this challenge, we present KDAS, a Knowledge Distillation framework that incorporates attention supervision, and our proposed Symmetrical Guiding Module. This framework is designed to facilitate a compact student model with fewer parameters, allowing it to learn the strengths of the teacher model and mitigate the inconsistency between teacher features and student features, a common challenge in Knowledge Distillation, via the Symmetrical Guiding Module. Through extensive experiments, our compact models demonstrate their strength by achieving competitive results with state-of-the-art methods, offering a promising approach to creating compact models with high accuracy for polyp segmentation and in the medical imaging field. The implementation is available on https://github.com/huyquoctrinh/KDAS.
Authors: Kshitij Goel, Wennie Tabib
Abstract: This paper describes continuous-space methodologies to estimate the collision probability, Euclidean distance and gradient between an ellipsoidal robot model and an environment surface modeled as a set of Gaussian distributions. Continuous-space collision probability estimation is critical for uncertainty-aware motion planning. Most collision detection and avoidance approaches assume the robot is modeled as a sphere, but ellipsoidal representations provide tighter approximations and enable navigation in cluttered and narrow spaces. State-of-the-art methods derive the Euclidean distance and gradient by processing raw point clouds, which is computationally expensive for large workspaces. Recent advances in Gaussian surface modeling (e.g. mixture models, splatting) enable compressed and high-fidelity surface representations. Few methods exist to estimate continuous-space occupancy from such models. They require Gaussians to model free space and are unable to estimate the collision probability, Euclidean distance and gradient for an ellipsoidal robot. The proposed methods bridge this gap by extending prior work in ellipsoid-to-ellipsoid Euclidean distance and collision probability estimation to Gaussian surface models. A geometric blending approach is also proposed to improve collision probability estimation. The approaches are evaluated with numerical 2D and 3D experiments using real-world point cloud data. Methods for efficient calculation of these quantities are demonstrated to execute within a few microseconds per ellipsoid pair using a single-thread on low-power CPUs of modern embedded computers
Authors: Yi-Fu Wu, Minseung Lee, Sungjin Ahn
Abstract: The Language of Thought Hypothesis suggests that human cognition operates on a structured, language-like system of mental representations. While neural language models can naturally benefit from the compositional structure inherently and explicitly expressed in language data, learning such representations from non-linguistic general observations, like images, remains a challenge. In this work, we introduce the Neural Language of Thought Model (NLoTM), a novel approach for unsupervised learning of LoTH-inspired representation and generation. NLoTM comprises two key components: (1) the Semantic Vector-Quantized Variational Autoencoder, which learns hierarchical, composable discrete representations aligned with objects and their properties, and (2) the Autoregressive LoT Prior, an autoregressive transformer that learns to generate semantic concept tokens compositionally, capturing the underlying data distribution. We evaluate NLoTM on several 2D and 3D image datasets, demonstrating superior performance in downstream tasks, out-of-distribution generalization, and image generation quality compared to patch-based VQ-VAE and continuous object-centric representations. Our work presents a significant step towards creating neural networks exhibiting more human-like understanding by developing LoT-like representations and offers insights into the intersection of cognitive science and machine learning.
Authors: Zhaoxin Guo, Zhipeng Wang, Ruiquan Ge, Jianxun Yu, Feiwei Qin, Yuan Tian, Yuqing Peng, Yonghong Li, Changmiao Wang
Abstract: The early detection of a pulmonary embolism (PE) is critical for enhancing patient survival rates. Both image-based and non-image-based features are of utmost importance in medical classification tasks. In a clinical setting, physicians tend to rely on the contextual information provided by Electronic Medical Records (EMR) to interpret medical imaging. However, very few models effectively integrate clinical information with imaging data. To address this shortcoming, we suggest a multimodal fusion methodology, termed PE-MVCNet, which capitalizes on Computed Tomography Pulmonary Angiography imaging and EMR data. This method comprises the Image-only module with an integrated multi-view block, the EMR-only module, and the Cross-modal Attention Fusion (CMAF) module. These modules cooperate to extract comprehensive features that subsequently generate predictions for PE. We conducted experiments using the publicly accessible Stanford University Medical Center dataset, achieving an AUROC of 94.1%, an accuracy rate of 90.2%, and an F1 score of 90.6%. Our proposed model outperforms existing methodologies, corroborating that our multimodal fusion model excels compared to models that use a single data modality. Our source code is available at https://github.com/LeavingStarW/PE-MVCNET.
Authors: Chi Tran, Huong Le Thanh
Abstract: Large Language Models (LLMs) and Multimodal Large language models (MLLMs) have taken the world by storm with impressive abilities in complex reasoning and linguistic comprehension. Meanwhile there are plethora of works related to Vietnamese Large Language Models, the lack of high-quality resources in multimodality limits the progress of Vietnamese MLLMs. In this paper, we pioneer in address this by introducing LaVy, a state-of-the-art Vietnamese MLLM, and we also introduce LaVy-Bench benchmark designated for evaluating MLLMs's understanding on Vietnamese visual language tasks. Our project is public at https://github.com/baochi0212/LaVy
Authors: Eric Yeats, Cameron Darwin, Eduardo Ortega, Frank Liu, Hai Li
Abstract: We leverage diffusion models to study the robustness-performance tradeoff of robust classifiers. Our approach introduces a simple, pretrained diffusion method to generate low-norm counterfactual examples (CEs): semantically altered data which results in different true class membership. We report that the confidence and accuracy of robust models on their clean training data are associated with the proximity of the data to their CEs. Moreover, robust models perform very poorly when evaluated on the CEs directly, as they become increasingly invariant to the low-norm, semantic changes brought by CEs. The results indicate a significant overlap between non-robust and semantic features, countering the common assumption that non-robust features are not interpretable.
Authors: Yekun Chai, Qingyi Liu, Jingwu Xiao, Shuohuan Wang, Yu Sun, Hua Wu
Abstract: Harnessing visual texts represents a burgeoning frontier in the evolution of language modeling. In this paper, we introduce a novel pre-training framework for a suite of pixel-based autoregressive language models, pre-training on a corpus of over 400 million documents rendered as RGB images. Our approach is characterized by a dual-modality training regimen, engaging both visual data through next patch prediction with a regression head and textual data via next token prediction with a classification head. This study is particularly focused on investigating the synergistic interplay between visual and textual modalities of language. Our comprehensive evaluation across a diverse array of benchmarks reveals that the confluence of visual and textual data substantially augments the efficacy of pixel-based language models. Notably, our findings show that a unidirectional pixel-based model, devoid of textual data during training, can match the performance levels of advanced bidirectional pixel-based models on various language understanding benchmarks. This work highlights the considerable untapped potential of integrating visual and textual information for language modeling purposes. We will release our code, data, and checkpoints to inspire further research advancement.