Authors: T.B. Keesom, P.P. Popov, P. Dhyani, G.B. Jacobs
A method to infer and synthetically extrapolate roughness fields from electron microscope scans of additively manufactured surfaces using an adaptation of Rogallo's synthetic turbulence method [R. S. Rogallo, NASA Technical Memorandum 81315, 1981] based on Fourier modes is presented. The resulting synthetic roughness fields are smooth and are compatible with grid generators in computational fluid dynamics or other numerical simulations. Unlike machine learning methods, which can require over twenty scans of surface roughness for training, the Fourier mode based method can extrapolate homogeneous synthetic roughness fields using a single physical roughness scan to any desired size and range. Five types of synthetic roughness fields are generated using an electron microscope roughness image from literature. A comparison of their spectral energy and two-point correlation spectra show that the synthetic fields closely approximate the roughness structures and spectral energy of the scan.
Authors: Luis Balderas, Miguel Lastra, José M. Benítez
Convolutional Neural Networks (CNN) are widely used to face challenging tasks like speech recognition, natural language processing or computer vision. As CNN architectures get larger and more complex, their computational requirements increase, incurring significant energetic costs and challenging their deployment on resource-restricted devices. In this paper, we propose Optimizing Convolutional Neural Network Architecture (OCNNA), a novel CNN optimization and construction method based on pruning and knowledge distillation designed to establish the importance of convolutional layers. The proposal has been evaluated though a thorough empirical study including the best known datasets (CIFAR-10, CIFAR-100 and Imagenet) and CNN architectures (VGG-16, ResNet-50, DenseNet-40 and MobileNet), setting Accuracy Drop and Remaining Parameters Ratio as objective metrics to compare the performance of OCNNA against the other state-of-art approaches. Our method has been compared with more than 20 convolutional neural network simplification algorithms obtaining outstanding results. As a result, OCNNA is a competitive CNN constructing method which could ease the deployment of neural networks into IoT or resource-limited devices.
Authors: Heba Najm, Khirallah Elferjani, Alhaam Alariyibi
For visually impaired people, it is highly difficult to make independent movement and safely move in both indoors and outdoors environment. Furthermore, these physically and visually challenges prevent them from in day-today live activities. Similarly, they have problem perceiving objects of surrounding environment that may pose a risk to them. The proposed approach suggests detection of objects in real-time video by using a web camera, for the object identification, process. You Look Only Once (YOLO) model is utilized which is CNN-based real-time object detection technique. Additionally, The OpenCV libraries of Python is used to implement the software program as well as deep learning process is performed. Image recognition results are transferred to the visually impaired users in audible form by means of Google text-to-speech library and determine object location relative to its position in the screen. The obtaining result was evaluated by using the mean Average Precision (mAP), and it was found that the proposed approach achieves excellent results when it compared to previous approaches.
Authors: Hankyul Baek, Donghyeon Kim, Joongheon Kim
Spurred by consistent advances and innovation in deep learning, object detection applications have become prevalent, particularly in autonomous driving that leverages various visual data. As convolutional neural networks (CNNs) are being optimized, the performances and computation speeds of object detection in autonomous driving have been significantly improved. However, due to the exponentially rapid growth in the complexity and scale of data used in object detection, there are limitations in terms of computation speeds while conducting object detection solely with classical computing. Motivated by this, quantum convolution-based object detection (QCOD) is proposed to adopt quantum computing to perform object detection at high speed. The QCOD utilizes our proposed fast quantum convolution that uploads input channel information and re-constructs output channels for achieving reduced computational complexity and thus improving performances. Lastly, the extensive experiments with KITTI autonomous driving object detection dataset verify that the proposed fast quantum convolution and QCOD are successfully operated in real object detection applications.
Authors: Pablo Martin-Ramiro, Unai Sainz de la Maza, Roman Orus, Samuel Mugel
Defect detection is one of the most important yet challenging tasks in the quality control stage in the manufacturing sector. In this work, we introduce a Tensor Convolutional Neural Network (T-CNN) and examine its performance on a real defect detection application in one of the components of the ultrasonic sensors produced at Robert Bosch's manufacturing plants. Our quantum-inspired T-CNN operates on a reduced model parameter space to substantially improve the training speed and performance of an equivalent CNN model without sacrificing accuracy. More specifically, we demonstrate how T-CNNs are able to reach the same performance as classical CNNs as measured by quality metrics, with up to fifteen times fewer parameters and 4% to 19% faster training times. Our results demonstrate that the T-CNN greatly outperforms the results of traditional human visual inspection, providing value in a current real application in manufacturing.
Authors: Kaitlyn Wang, Yufang Jin
Effective monitoring of walnut water status and stress level across the whole orchard is an essential step towards precision irrigation management of walnuts, a significant crop in California. This study presents a machine learning approach using Random Forest (RF) models to map stem water potential (SWP) by integrating high-resolution multispectral remote sensing imagery from Unmanned Aerial Vehicle (UAV) flights with weather data. From 2017 to 2018, five flights of an UAV equipped with a seven-band multispectral camera were conducted over a commercial walnut orchard, paired with concurrent ground measurements of sampled walnut plants. The RF regression model, utilizing vegetation indices derived from orthomosaiced UAV imagery and weather data, effectively estimated ground-measured SWPs, achieving an $R^2$ of 0.63 and a mean absolute error (MAE) of 0.80 bars. The integration of weather data was particularly crucial for consolidating data across various flight dates. Significant variables for SWP estimation included wind speed and vegetation indices such as NDVI, NDRE, and PSRI.A reduced RF model excluding red-edge indices of NDRE and PSRI, demonstrated slightly reduced accuracy ($R^2$ = 0.54). Additionally, the RF classification model predicted water stress levels in walnut trees with 85% accuracy, surpassing the 80% accuracy of the reduced classification model. The results affirm the efficacy of UAV-based multispectral imaging combined with machine learning, incorporating thermal data, NDVI, red-edge indices, and weather data, in walnut water stress estimation and assessment. This methodology offers a scalable, cost-effective tool for data-driven precision irrigation management at an individual plant level in walnut orchards.
Authors: Ronghui Li, Yuqin Dai, Yachao Zhang, Jun Li, Jian Yang, Jie Guo, Xiu Li
Existing music-driven 3D dance generation methods mainly concentrate on high-quality dance generation, but lack sufficient control during the generation process. To address these issues, we propose a unified framework capable of generating high-quality dance movements and supporting multi-modal control, including genre control, semantic control, and spatial control. First, we decouple the dance generation network from the dance control network, thereby avoiding the degradation in dance quality when adding additional control information. Second, we design specific control strategies for different control information and integrate them into a unified framework. Experimental results show that the proposed dance generation framework outperforms state-of-the-art methods in terms of motion quality and controllability.
Authors: Michalis Pistos, Islem Rekik
The understanding of the convoluted evolution of infant brain networks during the first postnatal year is pivotal for identifying the dynamics of early brain connectivity development. Existing deep learning solutions suffer from three major limitations. First, they cannot generalize to multi-trajectory prediction tasks, where each graph trajectory corresponds to a particular imaging modality or connectivity type (e.g., T1-w MRI). Second, existing models require extensive training datasets to achieve satisfactory performance which are often challenging to obtain. Third, they do not efficiently utilize incomplete time series data. To address these limitations, we introduce FedGmTE-Net++, a federated graph-based multi-trajectory evolution network. Using the power of federation, we aggregate local learnings among diverse hospitals with limited datasets. As a result, we enhance the performance of each hospital's local generative model, while preserving data privacy. The three key innovations of FedGmTE-Net++ are: (i) presenting the first federated learning framework specifically designed for brain multi-trajectory evolution prediction in a data-scarce environment, (ii) incorporating an auxiliary regularizer in the local objective function to exploit all the longitudinal brain connectivity within the evolution trajectory and maximize data utilization, (iii) introducing a two-step imputation process, comprising a preliminary KNN-based precompletion followed by an imputation refinement step that employs regressors to improve similarity scores and refine imputations. Our comprehensive experimental results showed the outperformance of FedGmTE-Net++ in brain multi-trajectory prediction from a single baseline graph in comparison with benchmark methods.
Authors: Galib Muhammad Shahriar Himel
Traditionally, pathological analysis and diagnosis are performed by manually eyeballing glass slide specimens under a microscope by an expert. The whole slide image is the digital specimen produced from the glass slide. Whole slide image enabled specimens to be observed on a computer screen and led to computational pathology where computer vision and artificial intelligence are utilized for automated analysis and diagnosis. With the current computational advancement, the entire whole slide image can be analyzed autonomously without human supervision. However, the analysis could fail or lead to wrong diagnosis if the whole slide image is affected by tissue artifacts such as tissue fold or air bubbles depending on the severity. Existing artifact detection methods rely on experts for severity assessment to eliminate artifact affected regions from the analysis. This process is time consuming, exhausting and undermines the goal of automated analysis or removal of artifacts without evaluating their severity, which could result in the loss of diagnostically important data. Therefore, it is necessary to detect artifacts and then assess their severity automatically. In this paper, we propose a system that incorporates severity evaluation with artifact detection utilizing convolutional neural networks. The proposed system uses DoubleUNet to segment artifacts and an ensemble network of six fine tuned convolutional neural network models to determine severity. This method outperformed current state of the art in accuracy by 9 percent for artifact segmentation and achieved a strong correlation of 97 percent with the evaluation of pathologists for severity assessment. The robustness of the system was demonstrated using our proposed heterogeneous dataset and practical usability was ensured by integrating it with an automated analysis system.
Authors: Parul Gupta, Tuan Nguyen, Abhinav Dhall, Munawar Hayat, Trung Le, Thanh-Toan Do
The task of Visual Relationship Recognition (VRR) aims to identify relationships between two interacting objects in an image and is particularly challenging due to the widely-spread and highly imbalanced distribution of <subject, relation, object> triplets. To overcome the resultant performance bias in existing VRR approaches, we introduce DiffAugment -- a method which first augments the tail classes in the linguistic space by making use of WordNet and then utilizes the generative prowess of Diffusion Models to expand the visual space for minority classes. We propose a novel hardness-aware component in diffusion which is based upon the hardness of each <S,R,O> triplet and demonstrate the effectiveness of hardness-aware diffusion in generating visual embeddings for the tail classes. We also propose a novel subject and object based seeding strategy for diffusion sampling which improves the discriminative capability of the generated visual embeddings. Extensive experimentation on the GQA-LT dataset shows favorable gains in the subject/object and relation average per-class accuracy using Diffusion augmented samples.
Authors: Julian Strohmayer, Martin Kampel
WiFi Channel State Information (CSI)-based human activity recognition (HAR) enables contactless, long-range sensing in spatially constrained environments while preserving visual privacy. However, despite the presence of numerous WiFi-enabled devices around us, few expose CSI to users, resulting in a lack of sensing hardware options. Variants of the Espressif ESP32 have emerged as potential low-cost and easy-to-deploy solutions for WiFi CSI-based HAR. In this work, four ESP32-S3-based 2.4GHz directional antenna systems are evaluated for their ability to facilitate long-range through-wall HAR. Two promising systems are proposed, one of which combines the ESP32-S3 with a directional biquad antenna. This combination represents, to the best of our knowledge, the first demonstration of such a system in WiFi-based HAR. The second system relies on the built-in printed inverted-F antenna (PIFA) of the ESP32-S3 and achieves directionality through a plane reflector. In a comprehensive evaluation of line-of-sight (LOS) and non-line-of-sight (NLOS) HAR performance, both systems are deployed in an office environment spanning a distance of 18 meters across five rooms. In this experimental setup, the Wallhack1.8k dataset, comprising 1806 CSI amplitude spectrograms of human activities, is collected and made publicly available. Based on Wallhack1.8k, we train activity recognition models using the EfficientNetV2 architecture to assess system performance in LOS and NLOS scenarios. For the core NLOS activity recognition problem, the biquad antenna and PIFA-based systems achieve accuracies of 92.0$\pm$3.5 and 86.8$\pm$4.7, respectively, demonstrating the feasibility of long-range through-wall HAR with the proposed systems.
Authors: Guying Lin, Lei Yang, Yuan Liu, Congyi Zhang, Junhui Hou, Xiaogang Jin, Taku Komura, John Keyser, Wenping Wang
Neural implicit fields, such as the neural signed distance field (SDF) of a shape, have emerged as a powerful representation for many applications, e.g., encoding a 3D shape and performing collision detection. Typically, implicit fields are encoded by Multi-layer Perceptrons (MLP) with positional encoding (PE) to capture high-frequency geometric details. However, a notable side effect of such PE-equipped MLPs is the noisy artifacts present in the learned implicit fields. While increasing the sampling rate could in general mitigate these artifacts, in this paper we aim to explain this adverse phenomenon through the lens of Fourier analysis. We devise a tool to determine the appropriate sampling rate for learning an accurate neural implicit field without undesirable side effects. Specifically, we propose a simple yet effective method to estimate the intrinsic frequency of a given network with randomized weights based on the Fourier analysis of the network's responses. It is observed that a PE-equipped MLP has an intrinsic frequency much higher than the highest frequency component in the PE layer. Sampling against this intrinsic frequency following the Nyquist-Sannon sampling theorem allows us to determine an appropriate training sampling rate. We empirically show in the setting of SDF fitting that this recommended sampling rate is sufficient to secure accurate fitting results, while further increasing the sampling rate would not further noticeably reduce the fitting error. Training PE-equipped MLPs simply with our sampling strategy leads to performances superior to the existing methods.
Authors: Christopher Krapu, Mark Borsuk, Ryan Calder
Land use / land cover (LULC) modeling is a challenging task due to long-range dependencies between geographic features and distinct spatial patterns related to topography, ecology, and human development. We identify a close connection between modeling of spatial patterns of land use and the task of image inpainting from computer vision and conduct a study of a modified PixelCNN architecture with approximately 19 million parameters for modeling LULC. In comparison with a benchmark spatial statistical model, we find that the former is capable of capturing much richer spatial correlation patterns such as roads and water bodies but does not produce a calibrated predictive distribution, suggesting the need for additional tuning. We find evidence of predictive underdispersion with regard to important ecologically-relevant land use statistics such as patch count and adjacency which can be ameliorated to some extent by manipulating sampling variability.
Authors: Alireza Shamsoshoara, Safin B Salih, Pedram Aghazadeh
This paper investigates the high-level decision-making problem in highway scenarios regarding lane changing and over-taking other slower vehicles. In particular, this paper aims to improve the Travel Assist feature for automatic overtaking and lane changes on highways. About 9 million samples including lane images and other dynamic objects are collected in simulation. This data; Overtaking on Simulated HighwAys (OSHA) dataset is released to tackle this challenge. To solve this problem, an architecture called SwapTransformer is designed and implemented as an imitation learning approach on the OSHA dataset. Moreover, auxiliary tasks such as future points and car distance network predictions are proposed to aid the model in better understanding the surrounding environment. The performance of the proposed solution is compared with a multi-layer perceptron (MLP) and multi-head self-attention networks as baselines in a simulation environment. We also demonstrate the performance of the model with and without auxiliary tasks. All models are evaluated based on different metrics such as time to finish each lap, number of overtakes, and speed difference with speed limit. The evaluation shows that the SwapTransformer model outperforms other models in different traffic densities in the inference phase.
Authors: Kasi Viswanath, Peng Jiang, Sujit PB, Srikanth Saripalli
LiDAR is used in autonomous driving to provide 3D spatial information and enable accurate perception in off-road environments, aiding in obstacle detection, mapping, and path planning. Learning-based LiDAR semantic segmentation utilizes machine learning techniques to automatically classify objects and regions in LiDAR point clouds. Learning-based models struggle in off-road environments due to the presence of diverse objects with varying colors, textures, and undefined boundaries, which can lead to difficulties in accurately classifying and segmenting objects using traditional geometric-based features. In this paper, we address this problem by harnessing the LiDAR intensity parameter to enhance object segmentation in off-road environments. Our approach was evaluated in the RELLIS-3D data set and yielded promising results as a preliminary analysis with improved mIoU for classes "puddle" and "grass" compared to more complex deep learning-based benchmarks. The methodology was evaluated for compatibility across both Velodyne and Ouster LiDAR systems, assuring its cross-platform applicability. This analysis advocates for the incorporation of calibrated intensity as a supplementary input, aiming to enhance the prediction accuracy of learning based semantic segmentation frameworks. https://github.com/MOONLABIISERB/lidar-intensity-predictor/tree/main
Authors: Feng Xue, Yicong Chang, Tianxi Wang, Yu Zhou, Anlong Ming
Visual obstacle discovery is a key step towards autonomous navigation of indoor mobile robots. Successful solutions have many applications in multiple scenes. One of the exceptions is the reflective ground. In this case, the reflections on the floor resemble the true world, which confuses the obstacle discovery and leaves navigation unsuccessful. We argue that the key to this problem lies in obtaining discriminative features for reflections and obstacles. Note that obstacle and reflection can be separated by the ground plane in 3D space. With this observation, we firstly introduce a pre-calibration based ground detection scheme that uses robot motion to predict the ground plane. Due to the immunity of robot motion to reflection, this scheme avoids failed ground detection caused by reflection. Given the detected ground, we design a ground-pixel parallax to describe the location of a pixel relative to the ground. Based on this, a unified appearance-geometry feature representation is proposed to describe objects inside rectangular boxes. Eventually, based on segmenting by detection framework, an appearance-geometry fusion regressor is designed to utilize the proposed feature to discover the obstacles. It also prevents our model from concentrating too much on parts of obstacles instead of whole obstacles. For evaluation, we introduce a new dataset for Obstacle on Reflective Ground (ORG), which comprises 15 scenes with various ground reflections, a total of more than 200 image sequences and 3400 RGB images. The pixel-wise annotations of ground and obstacle provide a comparison to our method and other methods. By reducing the misdetection of the reflection, the proposed approach outperforms others. The source code and the dataset will be available at https://github.com/XuefengBUPT/IndoorObstacleDiscovery-RG.
Authors: Ahmad Sajedi, Samir Khaki, Yuri A. Lawryshyn, Konstantinos N. Plataniotis
Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture label dependencies. However, these methods often include complex modules that entail heavy computation and lack interpretability. In this paper, we propose Probabilistic Multi-label Contrastive Learning (ProbMCL), a novel framework to address these challenges in multi-label image classification tasks. Our simple yet effective approach employs supervised contrastive learning, in which samples that share enough labels with an anchor image based on a decision threshold are introduced as a positive set. This structure captures label dependencies by pulling positive pair embeddings together and pushing away negative samples that fall below the threshold. We enhance representation learning by incorporating a mixture density network into contrastive learning and generating Gaussian mixture distributions to explore the epistemic uncertainty of the feature encoder. We validate the effectiveness of our framework through experimentation with datasets from the computer vision and medical imaging domains. Our method outperforms the existing state-of-the-art methods while achieving a low computational footprint on both datasets. Visualization analyses also demonstrate that ProbMCL-learned classifiers maintain a meaningful semantic topology.
Authors: Mingyu Liu, Ekim Yurtsever, Xingcheng Zhou, Jonathan Fossaert, Yuning Cui, Bare Luka Zagar, Alois C. Knoll
Autonomous driving has rapidly developed and shown promising performance with recent advances in hardware and deep learning methods. High-quality datasets are fundamental for developing reliable autonomous driving algorithms. Previous dataset surveys tried to review the datasets but either focused on a limited number or lacked detailed investigation of the characters of datasets. To this end, we present an exhaustive study of over 200 autonomous driving datasets from multiple perspectives, including sensor modalities, data size, tasks, and contextual conditions. We introduce a novel metric to evaluate the impact of each dataset, which can also be a guide for establishing new datasets. We further analyze the annotation process and quality of datasets. Additionally, we conduct an in-depth analysis of the data distribution of several vital datasets. Finally, we discuss the development trend of the future autonomous driving datasets.
Authors: Dingkun Yan, Liang Yuan, Yuma Nishioka, Issei Fujishiro, Suguru Saito
Recently, diffusion models have demonstrated their effectiveness in generating extremely high-quality images and have found wide-ranging applications, including automatic sketch colorization. However, most existing models use text to guide the conditional generation, with fewer attempts exploring the potential advantages of using image tokens as conditional inputs for networks. As such, this paper exhaustively investigates image-guided models, specifically targeting reference-based sketch colorization, which aims to colorize sketch images using reference color images. We investigate three critical aspects of reference-based diffusion models: the shortcomings compared to text-based counterparts, the training strategies, and the capability in zero-shot, sequential text-based manipulation. We introduce two variations of an image-guided latent diffusion model using different image tokens from the pre-trained CLIP image encoder, and we propose corresponding manipulation methods to adjust their results sequentially using weighted text inputs. We conduct comprehensive evaluations of our models through qualitative and quantitative experiments, as well as a user study.
Authors: Xiaotong Wu, Wei-Sheng Lai, YiChang Shih, Charles Herrmann, Michael Krainin, Deqing Sun, Chia-Kai Liang
DSLR cameras can achieve multiple zoom levels via shifting lens distances or swapping lens types. However, these techniques are not possible on smartphone devices due to space constraints. Most smartphone manufacturers adopt a hybrid zoom system: commonly a Wide (W) camera at a low zoom level and a Telephoto (T) camera at a high zoom level. To simulate zoom levels between W and T, these systems crop and digitally upsample images from W, leading to significant detail loss. In this paper, we propose an efficient system for hybrid zoom super-resolution on mobile devices, which captures a synchronous pair of W and T shots and leverages machine learning models to align and transfer details from T to W. We further develop an adaptive blending method that accounts for depth-of-field mismatches, scene occlusion, flow uncertainty, and alignment errors. To minimize the domain gap, we design a dual-phone camera rig to capture real-world inputs and ground-truths for supervised training. Our method generates a 12-megapixel image in 500ms on a mobile platform and compares favorably against state-of-the-art methods under extensive evaluation on real-world scenarios.
Authors: Wentao Zhu
Vision transformers (ViTs) have achieved promising results on a variety of Computer Vision tasks, however their quadratic complexity in the number of input tokens has limited their application specially in resource-constrained settings. Previous approaches that employ gradual token reduction to address this challenge assume that token redundancy in one layer implies redundancy in all the following layers. We empirically demonstrate that this assumption is often not correct, i.e., tokens that are redundant in one layer can be useful in later layers. We employ this key insight to propose a novel token propagation controller (TPC) that incorporates two different token-distributions, i.e., pause probability and restart probability to control the reduction and reuse of tokens respectively, which results in more efficient token utilization. To improve the estimates of token distributions, we propose a smoothing mechanism that acts as a regularizer and helps remove noisy outliers. Furthermore, to improve the training-stability of our proposed TPC, we introduce a model stabilizer that is able to implicitly encode local image structures and minimize accuracy fluctuations during model training. We present extensive experimental results on the ImageNet-1K dataset using DeiT, LV-ViT and Swin models to demonstrate the effectiveness of our proposed method. For example, compared to baseline models, our proposed method improves the inference speed of the DeiT-S by 250% while increasing the classification accuracy by 1.0%.
Authors: Kyle Buettner, Sina Malakouti, Xiang Lorraine Li, Adriana Kovashka
Existing object recognition models have been shown to lack robustness in diverse geographical scenarios due to significant domain shifts in design and context. Class representations need to be adapted to more accurately reflect an object concept under these shifts. In the absence of training data from target geographies, we hypothesize that geography-specific descriptive knowledge of object categories can be leveraged to enhance robustness. For this purpose, we explore the feasibility of probing a large-language model for geography-specific object knowledge, and we investigate integrating knowledge in zero-shot and learnable soft prompting with the CLIP vision-language model. In particular, we propose a geography knowledge regularization method to ensure that soft prompts trained on a source set of geographies generalize to an unseen target set of geographies. Our gains on DollarStreet when generalizing from a model trained only on data from Europe are as large as +2.8 on countries from Africa, and +4.6 on the hardest classes. We further show competitive performance vs. few-shot target training, and provide insights into how descriptive knowledge captures geographical differences.
Authors: Jia Dong, Yao Yao, Yang Dong, Hui Ma
Thyroid cancer is the most common endocrine malignancy, and accurately distinguishing between benign and malignant thyroid tumors is crucial for developing effective treatment plans in clinical practice. Pathologically, thyroid tumors pose diagnostic challenges due to improper specimen sampling. In this study, we have designed a three-stage model using representation learning to integrate pixel-level and slice-level annotations for distinguishing thyroid tumors. This structure includes a pathology structure recognition method to predict structures related to thyroid tumors, an encoder-decoder network to extract pixel-level annotation information by learning the feature representations of image blocks, and an attention-based learning mechanism for the final classification task. This mechanism learns the importance of different image blocks in a pathological region, globally considering the information from each block. In the third stage, all information from the image blocks in a region is aggregated using attention mechanisms, followed by classification to determine the category of the region. Experimental results demonstrate that our proposed method can predict microscopic structures more accurately. After color-coding, the method achieves results on unstained pathology slides that approximate the quality of Hematoxylin and eosin staining, reducing the need for stained pathology slides. Furthermore, by leveraging the concept of indirect measurement and extracting polarized features from structures correlated with lesions, the proposed method can also classify samples where membrane structures cannot be obtained through sampling, providing a potential objective and highly accurate indirect diagnostic technique for thyroid tumors.
Authors: Haopeng Li, Andong Deng, Qiuhong Ke, Jun Liu, Hossein Rahmani, Yulan Guo, Bernt Schiele, Chen Chen
Reasoning over sports videos for question answering is an important task with numerous applications, such as player training and information retrieval. However, this task has not been explored due to the lack of relevant datasets and the challenging nature it presents. Most datasets for video question answering (VideoQA) focus mainly on general and coarse-grained understanding of daily-life videos, which is not applicable to sports scenarios requiring professional action understanding and fine-grained motion analysis. In this paper, we introduce the first dataset, named Sports-QA, specifically designed for the sports VideoQA task. The Sports-QA dataset includes various types of questions, such as descriptions, chronologies, causalities, and counterfactual conditions, covering multiple sports. Furthermore, to address the characteristics of the sports VideoQA task, we propose a new Auto-Focus Transformer (AFT) capable of automatically focusing on particular scales of temporal information for question answering. We conduct extensive experiments on Sports-QA, including baseline studies and the evaluation of different methods. The results demonstrate that our AFT achieves state-of-the-art performance.
Authors: Haopeng Li, Qiuhong Ke, Mingming Gong, Tom Drummond
While significant advancements have been made in video question answering (VideoQA), the potential benefits of enhancing model generalization through tailored difficulty scheduling have been largely overlooked in existing research. This paper seeks to bridge that gap by incorporating VideoQA into a curriculum learning (CL) framework that progressively trains models from simpler to more complex data. Recognizing that conventional self-paced CL methods rely on training loss for difficulty measurement, which might not accurately reflect the intricacies of video-question pairs, we introduce the concept of uncertainty-aware CL. Here, uncertainty serves as the guiding principle for dynamically adjusting the difficulty. Furthermore, we address the challenge posed by uncertainty by presenting a probabilistic modeling approach for VideoQA. Specifically, we conceptualize VideoQA as a stochastic computation graph, where the hidden representations are treated as stochastic variables. This yields two distinct types of uncertainty: one related to the inherent uncertainty in the data and another pertaining to the model's confidence. In practice, we seamlessly integrate the VideoQA model into our framework and conduct comprehensive experiments. The findings affirm that our approach not only achieves enhanced performance but also effectively quantifies uncertainty in the context of VideoQA.
Authors: Yixuan Wang, Shuangyin Li
Diffusion models have emerged as powerful generative tools, rivaling GANs in sample quality and mirroring the likelihood scores of autoregressive models. A subset of these models, exemplified by DDIMs, exhibit an inherent asymmetry: they are trained over $T$ steps but only sample from a subset of $T$ during generation. This selective sampling approach, though optimized for speed, inadvertently misses out on vital information from the unsampled steps, leading to potential compromises in sample quality. To address this issue, we present the S$^{2}$-DMs, which is a new training method by using an innovative $L_{skip}$, meticulously designed to reintegrate the information omitted during the selective sampling phase. The benefits of this approach are manifold: it notably enhances sample quality, is exceptionally simple to implement, requires minimal code modifications, and is flexible enough to be compatible with various sampling algorithms. On the CIFAR10 dataset, models trained using our algorithm showed an improvement of 3.27% to 14.06% over models trained with traditional methods across various sampling algorithms (DDIMs, PNDMs, DEIS) and different numbers of sampling steps (10, 20, ..., 1000). On the CELEBA dataset, the improvement ranged from 8.97% to 27.08%. Access to the code and additional resources is provided in the github.
Authors: Rujiao Long, Hangdi Xing, Zhibo Yang, Qi Zheng, Zhi Yu, Cong Yao, Fei Huang
Table structure recognition (TSR) aims at extracting tables in images into machine-understandable formats. Recent methods solve this problem by predicting the adjacency relations of detected cell boxes or learning to directly generate the corresponding markup sequences from the table images. However, existing approaches either count on additional heuristic rules to recover the table structures, or face challenges in capturing long-range dependencies within tables, resulting in increased complexity. In this paper, we propose an alternative paradigm. We model TSR as a logical location regression problem and propose a new TSR framework called LORE, standing for LOgical location REgression network, which for the first time regresses logical location as well as spatial location of table cells in a unified network. Our proposed LORE is conceptually simpler, easier to train, and more accurate than other paradigms of TSR. Moreover, inspired by the persuasive success of pre-trained models on a number of computer vision and natural language processing tasks, we propose two pre-training tasks to enrich the spatial and logical representations at the feature level of LORE, resulting in an upgraded version called LORE++. The incorporation of pre-training in LORE++ has proven to enjoy significant advantages, leading to a substantial enhancement in terms of accuracy, generalization, and few-shot capability compared to its predecessor. Experiments on standard benchmarks against methods of previous paradigms demonstrate the superiority of LORE++, which highlights the potential and promising prospect of the logical location regression paradigm for TSR.
Authors: Hao Yang, Hong-Yu Zhou, Cheng Li, Weijian Huang, Jiarun Liu, Yong Liang, Shanshan Wang
Multimodal deep learning utilizing imaging and diagnostic reports has made impressive progress in the field of medical imaging diagnostics, demonstrating a particularly strong capability for auxiliary diagnosis in cases where sufficient annotation information is lacking. Nonetheless, localizing diseases accurately without detailed positional annotations remains a challenge. Although existing methods have attempted to utilize local information to achieve fine-grained semantic alignment, their capability in extracting the fine-grained semantics of the comprehensive contextual within reports is limited. To solve this problem, we introduce a new method that takes full sentences from textual reports as the basic units for local semantic alignment. Our approach combines chest X-ray images with their corresponding textual reports, performing contrastive learning at both global and local levels. The leading results obtained by our method on multiple datasets confirm its efficacy in the task of lesion localization.
Authors: Ziyi Bai, Ruiping Wang, Xilin Chen
Video Question Answering (VideoQA) has emerged as a vital tool to evaluate agents' ability to understand human daily behaviors. Despite the recent success of large vision language models in many multi-modal tasks, complex situation reasoning over videos involving multiple human-object interaction events still remains challenging. In contrast, humans can easily tackle it by using a series of episode memories as anchors to quickly locate question-related key moments for reasoning. To mimic this effective reasoning strategy, we propose the Glance-Focus model. One simple way is to apply an action detection model to predict a set of actions as key memories. However, these actions within a closed set vocabulary are hard to generalize to various video domains. Instead of that, we train an Encoder-Decoder to generate a set of dynamic event memories at the glancing stage. Apart from using supervised bipartite matching to obtain the event memories, we further design an unsupervised memory generation method to get rid of dependence on event annotations. Next, at the focusing stage, these event memories act as a bridge to establish the correlation between the questions with high-level event concepts and low-level lengthy video content. Given the question, the model first focuses on the generated key event memory, then focuses on the most relevant moment for reasoning through our designed multi-level cross-attention mechanism. We conduct extensive experiments on four Multi-Event VideoQA benchmarks including STAR, EgoTaskQA, AGQA, and NExT-QA. Our proposed model achieves state-of-the-art results, surpassing current large models in various challenging reasoning tasks. The code and models are available at https://github.com/ByZ0e/Glance-Focus.
Authors: Praveen Mahaulpatha, Thulana Abeywardane, Tomson George
Access to high-quality datasets in the medical industry limits machine learning model performance. To address this issue, we propose a Denoising Diffusion Probabilistic Model (DDPM) combined with a UNet architecture for X-ray image synthesis. Focused on pneumonia medical condition, our methodology employs over 3000 pneumonia X-ray images obtained from Kaggle for training. Results demonstrate the effectiveness of our approach, as the model successfully generated realistic images with low Mean Squared Error (MSE). The synthesized images showed distinct differences from non-pneumonia images, highlighting the model's ability to capture key features of positive cases. Beyond pneumonia, the applications of this synthesizer extend to various medical conditions, provided an ample dataset is available. The capability to produce high-quality images can potentially enhance machine learning models' performance, aiding in more accurate and efficient medical diagnoses. This innovative DDPM-based X-ray photo synthesizer presents a promising avenue for addressing the scarcity of positive medical image datasets, paving the way for improved medical image analysis and diagnosis in the healthcare industry.
Authors: Chen Tang, Yuan Meng, Jiacheng Jiang, Shuzhao Xie, Rongwei Lu, Xinzhu Ma, Zhi Wang, Wenwu Zhu
Quantization is of significance for compressing the over-parameterized deep neural models and deploying them on resource-limited devices. Fixed-precision quantization suffers from performance drop due to the limited numerical representation ability. Conversely, mixed-precision quantization (MPQ) is advocated to compress the model effectively by allocating heterogeneous bit-width for layers. MPQ is typically organized into a searching-retraining two-stage process. Previous works only focus on determining the optimal bit-width configuration in the first stage efficiently, while ignoring the considerable time costs in the second stage. However, retraining always consumes hundreds of GPU-hours on the cutting-edge GPUs, thus hindering deployment efficiency significantly. In this paper, we devise a one-shot training-searching paradigm for mixed-precision model compression. Specifically, in the first stage, all potential bit-width configurations are coupled and thus optimized simultaneously within a set of shared weights. However, our observations reveal a previously unseen and severe bit-width interference phenomenon among highly coupled weights during optimization, leading to considerable performance degradation under a high compression ratio. To tackle this problem, we first design a bit-width scheduler to dynamically freeze the most turbulent bit-width of layers during training, to ensure the rest bit-widths converged properly. Then, taking inspiration from information theory, we present an information distortion mitigation technique to align the behaviour of the bad-performing bit-widths to the well-performing ones.
Authors: Senkang Hu, Zhengru Fang, Yiqin Deng, Xianhao Chen, Yuguang Fang
Autonomous driving has attracted significant attention from both academia and industries, which is expected to offer a safer and more efficient driving system. However, current autonomous driving systems are mostly based on a single vehicle, which has significant limitations which still poses threats to driving safety. Collaborative perception with connected and autonomous vehicles (CAVs) shows a promising solution to overcoming these limitations. In this article, we first identify the challenges of collaborative perception, such as data sharing asynchrony, data volume, and pose errors. Then, we discuss the possible solutions to address these challenges with various technologies, where the research opportunities are also elaborated. Furthermore, we propose a scheme to deal with communication efficiency and latency problems, which is a channel-aware collaborative perception framework to dynamically adjust the communication graph and minimize latency, thereby improving perception performance while increasing communication efficiency. Finally, we conduct experiments to demonstrate the effectiveness of our proposed scheme.
Authors: Mingrui Li, Jiaming He, Guangan Jiang, Hongyu Wang
We propose DDN-SLAM, a real-time dense neural implicit semantic SLAM system designed for dynamic scenes. While existing neural implicit SLAM systems perform well in static scenes, they often encounter challenges in real-world environments with dynamic interferences, leading to ineffective tracking and mapping. DDN-SLAM utilizes the priors provided by the deep semantic system, combined with conditional probability fields, for segmentation.By constructing depth-guided static masks and employing joint multi-resolution hashing encoding, we ensure fast hole filling and high-quality mapping while mitigating the effects of dynamic information interference. To enhance tracking robustness, we utilize sparse feature points validated with optical flow and keyframes, enabling loop closure detection and global bundle optimization. Furthermore, DDN-SLAM supports monocular, stereo, and RGB-D inputs, operating robustly at a frequency of 20-30Hz. Extensive experiments on 6 virtual/real datasets demonstrate that our method outperforms state-of-the-art approaches in both dynamic and static scenes.
Authors: Zipei Yan, Zhengji Liu, Jizhou Li
Implicit Neural Representation (INR) has emerged as an effective method for unsupervised image denoising. However, INR models are typically overparameterized; consequently, these models are prone to overfitting during learning, resulting in suboptimal results, even noisy ones. To tackle this problem, we propose a general recipe for regularizing INR models in image denoising. In detail, we propose to iteratively substitute the supervision signal with the mean value derived from both the prediction and supervision signal during the learning process. We theoretically prove that such a simple iterative substitute can gradually enhance the signal-to-noise ratio of the supervision signal, thereby benefiting INR models during the learning process. Our experimental results demonstrate that INR models can be effectively regularized by the proposed approach, relieving overfitting and boosting image denoising performance.
Authors: Yi Rong, Haoran Zhou, Lixin Yuan, Cheng Mei, Jiahao Wang, Tong Lu
Point cloud completion is an indispensable task for recovering complete point clouds due to incompleteness caused by occlusion, limited sensor resolution, etc. The family of coarse-to-fine generation architectures has recently exhibited great success in point cloud completion and gradually became mainstream. In this work, we unveil one of the key ingredients behind these methods: meticulously devised feature extraction operations with explicit cross-resolution aggregation. We present Cross-Resolution Transformer that efficiently performs cross-resolution aggregation with local attention mechanisms. With the help of our recursive designs, the proposed operation can capture more scales of features than common aggregation operations, which is beneficial for capturing fine geometric characteristics. While prior methodologies have ventured into various manifestations of inter-level cross-resolution aggregation, the effectiveness of intra-level one and their combination has not been analyzed. With unified designs, Cross-Resolution Transformer can perform intra- or inter-level cross-resolution aggregation by switching inputs. We integrate two forms of Cross-Resolution Transformers into one up-sampling block for point generation, and following the coarse-to-fine manner, we construct CRA-PCN to incrementally predict complete shapes with stacked up-sampling blocks. Extensive experiments demonstrate that our method outperforms state-of-the-art methods by a large margin on several widely used benchmarks. Codes are available at https://github.com/EasyRy/CRA-PCN.
Authors: Shichuan Zhang, Sunyi Zheng, Zhongyi Shui, Honglin Li, Lin Yang
Multi-modal Learning has attracted widespread attention in medical image analysis. Using multi-modal data, whole slide images (WSIs) and clinical information, can improve the performance of deep learning models in the diagnosis of axillary lymph node metastasis. However, clinical information is not easy to collect in clinical practice due to privacy concerns, limited resources, lack of interoperability, etc. Although patient selection can ensure the training set to have multi-modal data for model development, missing modality of clinical information can appear during test. This normally leads to performance degradation, which limits the use of multi-modal models in the clinic. To alleviate this problem, we propose a bidirectional distillation framework consisting of a multi-modal branch and a single-modal branch. The single-modal branch acquires the complete multi-modal knowledge from the multi-modal branch, while the multi-modal learns the robust features of WSI from the single-modal. We conduct experiments on a public dataset of Lymph Node Metastasis in Early Breast Cancer to validate the method. Our approach not only achieves state-of-the-art performance with an AUC of 0.861 on the test set without missing data, but also yields an AUC of 0.842 when the rate of missing modality is 80\%. This shows the effectiveness of the approach in dealing with multi-modal data and missing modality. Such a model has the potential to improve treatment decision-making for early breast cancer patients who have axillary lymph node metastatic status.
Authors: Qiyuan Ou, Pei Zhang, Sihang Zhou, En Zhu
Late fusion multi-view clustering (LFMVC) has become a rapidly growing class of methods in the multi-view clustering (MVC) field, owing to its excellent computational speed and clustering performance. One bottleneck faced by existing late fusion methods is that they are usually aligned to the average kernel function, which makes the clustering performance highly dependent on the quality of datasets. Another problem is that they require subsequent k-means clustering after obtaining the consensus partition matrix to get the final discrete labels, and the resulting separation of the label learning and cluster structure optimization processes limits the integrity of these models. To address the above issues, we propose an integrated framework named One-Step Late Fusion Multi-view Clustering with Compressed Subspace (OS-LFMVC-CS). Specifically, we use the consensus subspace to align the partition matrix while optimizing the partition fusion, and utilize the fused partition matrix to guide the learning of discrete labels. A six-step iterative optimization approach with verified convergence is proposed. Sufficient experiments on multiple datasets validate the effectiveness and efficiency of our proposed method.
Authors: Kang Fu, Yicong Peng, Zicheng Zhang, Qihang Xu, Xiaohong Liu, Jia Wang, Guangtao Zhai
Recently, many algorithms have employed image-adaptive lookup tables (LUTs) to achieve real-time image enhancement. Nonetheless, a prevailing trend among existing methods has been the employment of linear combinations of basic LUTs to formulate image-adaptive LUTs, which limits the generalization ability of these methods. To address this limitation, we propose a novel framework named AttentionLut for real-time image enhancement, which utilizes the attention mechanism to generate image-adaptive LUTs. Our proposed framework consists of three lightweight modules. We begin by employing the global image context feature module to extract image-adaptive features. Subsequently, the attention fusion module integrates the image feature with the priori attention feature obtained during training to generate image-adaptive canonical polyadic tensors. Finally, the canonical polyadic reconstruction module is deployed to reconstruct image-adaptive residual 3DLUT, which is subsequently utilized for enhancing input images. Experiments on the benchmark MIT-Adobe FiveK dataset demonstrate that the proposed method achieves better enhancement performance quantitatively and qualitatively than the state-of-the-art methods.
Authors: Cuiwei Liu, Jiahao Liu, Huaijun Qiu, Zhaokui Li, Xiangbin Shi
Unmanned Aerial Vehicle (UAV) visual geo-localization aims to match images of the same geographic target captured from different views, i.e., the UAV view and the satellite view. It is very challenging due to the large appearance differences in UAV-satellite image pairs. Previous works map images captured by UAVs and satellites to a shared feature space and employ a classification framework to learn location-dependent features while neglecting the overall distribution shift between the UAV view and the satellite view. In this paper, we address these limitations by introducing distribution alignment of the two views to shorten their distance in a common space. Specifically, we propose an end-to-end network, called PVDA (Progressive View Distribution Alignment). During training, feature encoder, location classifier, and view discriminator are jointly optimized by a novel progressive adversarial learning strategy. Competition between feature encoder and view discriminator prompts both of them to be stronger. It turns out that the adversarial learning is progressively emphasized until UAV-view images are indistinguishable from satellite-view images. As a result, the proposed PVDA becomes powerful in learning location-dependent yet view-invariant features with good scalability towards unseen images of new locations. Compared to the state-of-the-art methods, the proposed PVDA requires less inference time but has achieved superior performance on the University-1652 dataset.
Authors: Shishen Li, Cuiwei Liu, Huaijun Qiu, Zhaokui Li
This paper addresses the task of Unmanned Aerial Vehicles (UAV) visual geo-localization, which aims to match images of the same geographic target taken by different platforms, i.e., UAVs and satellites. In general, the key to achieving accurate UAV-satellite image matching lies in extracting visual features that are robust against viewpoint changes, scale variations, and rotations. Current works have shown that part matching is crucial for UAV visual geo-localization since part-level representations can capture image details and help to understand the semantic information of scenes. However, the importance of preserving semantic characteristics in part-level representations is not well discussed. In this paper, we introduce a transformer-based adaptive semantic aggregation method that regards parts as the most representative semantics in an image. Correlations of image patches to different parts are learned in terms of the transformer's feature map. Then our method decomposes part-level features into an adaptive sum of all patch features. By doing this, the learned parts are encouraged to focus on patches with typical semantics. Extensive experiments on the University-1652 dataset have shown the superiority of our method over the current works.
Authors: Xuannan Liu, Yaoyao Zhong, Weihong Deng, Hongzhi Shi, Xingchen Cui, Yunfeng Yin, Dongchao Wen
The blooming of social media and face recognition (FR) systems has increased people's concern about privacy and security. A new type of adversarial privacy cloak (class-universal) can be applied to all the images of regular users, to prevent malicious FR systems from acquiring their identity information. In this work, we discover the optimization dilemma in the existing methods -- the local optima problem in large-batch optimization and the gradient information elimination problem in small-batch optimization. To solve these problems, we propose Gradient Accumulation (GA) to aggregate multiple small-batch gradients into a one-step iterative gradient to enhance the gradient stability and reduce the usage of quantization operations. Experiments show that our proposed method achieves high performance on the Privacy-Commons dataset against black-box face recognition models.
Authors: Huan Liu, Julia Qi, Zhenhao Li, Mohammad Hassanpour, Yang Wang, Konstantinos Plataniotis, Yuanhao Yu
Despite the recent remarkable achievement in gaze estimation, efficient and accurate personalization of gaze estimation without labels is a practical problem but rarely touched on in the literature. To achieve efficient personalization, we take inspiration from the recent advances in Natural Language Processing (NLP) by updating a negligible number of parameters, "prompts", at the test time. Specifically, the prompt is additionally attached without perturbing original network and can contain less than 1% of a ResNet-18's parameters. Our experiments show high efficiency of the prompt tuning approach. The proposed one can be 10 times faster in terms of adaptation speed than the methods compared. However, it is non-trivial to update the prompt for personalized gaze estimation without labels. At the test time, it is essential to ensure that the minimizing of particular unsupervised loss leads to the goals of minimizing gaze estimation error. To address this difficulty, we propose to meta-learn the prompt to ensure that its updates align with the goal. Our experiments show that the meta-learned prompt can be effectively adapted even with a simple symmetry loss. In addition, we experiment on four cross-dataset validations to show the remarkable advantages of the proposed method.
Authors: Xin Gu, Heng Fan, Yan Huang, Tiejian Luo, Libo Zhang
Spatio-temporal video grounding (or STVG) task aims at locating a spatio-temporal tube for a specific instance given a text query. Despite advancements, current methods easily suffer the distractors or heavy object appearance variations in videos due to insufficient object information from the text, leading to degradation. Addressing this, we propose a novel framework, context-guided STVG (CG-STVG), which mines discriminative instance context for object in videos and applies it as a supplementary guidance for target localization. The key of CG-STVG lies in two specially designed modules, including instance context generation (ICG), which focuses on discovering visual context information (in both appearance and motion) of the instance, and instance context refinement (ICR), which aims to improve the instance context from ICG by eliminating irrelevant or even harmful information from the context. During grounding, ICG, together with ICR, are deployed at each decoding stage of a Transformer architecture for instance context learning. Particularly, instance context learned from one decoding stage is fed to the next stage, and leveraged as a guidance containing rich and discriminative object feature to enhance the target-awareness in decoding feature, which conversely benefits generating better new instance context for improving localization finally. Compared to existing methods, CG-STVG enjoys object information in text query and guidance from mined instance visual context for more accurate target localization. In our experiments on three benchmarks, including HCSTVG-v1/-v2 and VidSTG, CG-STVG sets new state-of-the-arts in m_tIoU and m_vIoU on all of them, showing its efficacy. The code will be released at https://github.com/HengLan/CGSTVG.
Authors: Weijian Huang, Cheng Li, Hong-Yu Zhou, Jiarun Liu, Hao Yang, Yong Liang, Shanshan Wang
The development of multi-modal medical foundation models has attracted significant attention in the field of medicine and healthcare due to their promising prospects in various clinical applications. One area of focus in this research direction is the extractions of features at different scales. While previous studies have explored feature learning at individual scales, investigation on integrating the diverse scales and modalities of information is lacking, which may hinder the potential for mutual reinforcement among these features. This paper aims to bridge this gap by proposing a method that effectively exploits multi-scale and cross-modality information to enhance the performance of medical foundation models. The proposed method simultaneously exploit features at the local, instance, modality and global aspects, facilitating comprehensive representation learning within the models. We evaluate the effectiveness of the proposed method on six open-source datasets across different clinical tasks, demonstrating its ability to enhance the performance of medical foundation models.
Authors: Ekram Alam, Abu Sufian, Paramartha Dutta, Marco Leo
The elderly population is increasing rapidly around the world. There are no enough caretakers for them. Use of AI-based in-home medical care systems is gaining momentum due to this. Human fall detection is one of the most important tasks of medical care system for the aged people. Human fall is a common problem among elderly people. Detection of a fall and providing medical help as early as possible is very important to reduce any further complexity. The chances of death and other medical complications can be reduced by detecting and providing medical help as early as possible after the fall. There are many state-of-the-art fall detection techniques available these days, but the majority of them need very high computing power. In this paper, we proposed a lightweight and fast human fall detection system using pose estimation. We used `Movenet' for human joins key-points extraction. Our proposed method can work in real-time on any low-computing device with any basic camera. All computation can be processed locally, so there is no problem of privacy of the subject. We used two datasets `GMDCSA' and `URFD' for the experiment. We got the sensitivity value of 0.9375 and 0.9167 for the dataset `GMDCSA' and `URFD' respectively. The source code and the dataset GMDCSA of our work are available online to access.
Authors: Jiarun Liu, Hong-Yu Zhou, Cheng Li, Weijian Huang, Hao Yang, Yong Liang, Shanshan Wang
Existing contrastive language-image pre-training aims to learn a joint representation by matching abundant image-text pairs. However, the number of image-text pairs in medical datasets is usually orders of magnitude smaller than that in natural datasets. Besides, medical image-text pairs often involve numerous complex fine-grained correspondences. This paper aims to enhance the data efficiency by introducing multiple-to-multiple local relationship modeling to capture denser supervisions. More specifically, we propose a Medical Language-Image Pre-training (MLIP) framework, which exploits the limited image-text medical data more efficiently through patch-sentence matching. Furthermore, we introduce a masked contrastive learning strategy with semantic integrity estimation to reduce redundancy in images while preserving the underlying semantics. Our evaluation results show that MLIP outperforms previous work in zero/few-shot classification and few-shot segmentation tasks by a large margin.
Authors: Zitong Huang, Ze Chen, Zhixing Chen, Erjin Zhou, Xinxing Xu, Rick Siow Mong Goh, Yong Liu, Chunmei Feng, Wangmeng Zuo
Few-shot Class-Incremental Learning (FSCIL) aims to continuously learn new classes based on very limited training data without forgetting the old ones encountered. Existing studies solely relied on pure visual networks, while in this paper we solved FSCIL by leveraging the Vision-Language model (e.g., CLIP) and propose a simple yet effective framework, named Learning Prompt with Distribution-based Feature Replay (LP-DiF). We observe that simply using CLIP for zero-shot evaluation can substantially outperform the most influential methods. Then, prompt tuning technique is involved to further improve its adaptation ability, allowing the model to continually capture specific knowledge from each session. To prevent the learnable prompt from forgetting old knowledge in the new session, we propose a pseudo-feature replay approach. Specifically, we preserve the old knowledge of each class by maintaining a feature-level Gaussian distribution with a diagonal covariance matrix, which is estimated by the image features of training images and synthesized features generated from a VAE. When progressing to a new session, pseudo-features are sampled from old-class distributions combined with training images of the current session to optimize the prompt, thus enabling the model to learn new knowledge while retaining old knowledge. Experiments on three prevalent benchmarks, i.e., CIFAR100, mini-ImageNet, CUB-200, and two more challenging benchmarks, i.e., SUN-397 and CUB-200$^*$ proposed in this paper showcase the superiority of LP-DiF, achieving new state-of-the-art (SOTA) in FSCIL. Code is publicly available at https://github.com/1170300714/LP-DiF.
Authors: Boyuan Zheng, Boyu Gou, Jihyung Kil, Huan Sun, Yu Su
The recent development on large multimodal models (LMMs), especially GPT-4V(ision) and Gemini, has been quickly expanding the capability boundaries of multimodal models beyond traditional tasks like image captioning and visual question answering. In this work, we explore the potential of LMMs like GPT-4V as a generalist web agent that can follow natural language instructions to complete tasks on any given website. We propose SEEACT, a generalist web agent that harnesses the power of LMMs for integrated visual understanding and acting on the web. We evaluate on the recent MIND2WEB benchmark. In addition to standard offline evaluation on cached websites, we enable a new online evaluation setting by developing a tool that allows running web agents on live websites. We show that GPT-4V presents a great potential for web agents - it can successfully complete 50% of the tasks on live websites if we manually ground its textual plans into actions on the websites. This substantially outperforms text-only LLMs like GPT-4 or smaller models (FLAN-T5 and BLIP-2) specifically fine-tuned for web agents. However, grounding still remains a major challenge. Existing LMM grounding strategies like set-of-mark prompting turns out not effective for web agents, and the best grounding strategy we develop in this paper leverages both the HTML text and visuals. Yet, there is still a substantial gap with oracle grounding, leaving ample room for further improvement.
Authors: Ying Lv, Zhi Liu, Gongyang Li
RGB-T semantic segmentation is a key technique for autonomous driving scenes understanding. For the existing RGB-T semantic segmentation methods, however, the effective exploration of the complementary relationship between different modalities is not implemented in the information interaction between multiple levels. To address such an issue, the Context-Aware Interaction Network (CAINet) is proposed for RGB-T semantic segmentation, which constructs interaction space to exploit auxiliary tasks and global context for explicitly guided learning. Specifically, we propose a Context-Aware Complementary Reasoning (CACR) module aimed at establishing the complementary relationship between multimodal features with the long-term context in both spatial and channel dimensions. Further, considering the importance of global contextual and detailed information, we propose the Global Context Modeling (GCM) module and Detail Aggregation (DA) module, and we introduce specific auxiliary supervision to explicitly guide the context interaction and refine the segmentation map. Extensive experiments on two benchmark datasets of MFNet and PST900 demonstrate that the proposed CAINet achieves state-of-the-art performance. The code is available at https://github.com/YingLv1106/CAINet.
Authors: Zhaochen Liu, Zhixuan Li, Tingting Jiang
Perceiving the complete shape of occluded objects is essential for human and machine intelligence. While the amodal segmentation task is to predict the complete mask of partially occluded objects, it is time-consuming and labor-intensive to annotate the pixel-level ground truth amodal masks. Box-level supervised amodal segmentation addresses this challenge by relying solely on ground truth bounding boxes and instance classes as supervision, thereby alleviating the need for exhaustive pixel-level annotations. Nevertheless, current box-level methodologies encounter limitations in generating low-resolution masks and imprecise boundaries, failing to meet the demands of practical real-world applications. We present a novel solution to tackle this problem by introducing a directed expansion approach from visible masks to corresponding amodal masks. Our approach involves a hybrid end-to-end network based on the overlapping region - the area where different instances intersect. Diverse segmentation strategies are applied for overlapping regions and non-overlapping regions according to distinct characteristics. To guide the expansion of visible masks, we introduce an elaborately-designed connectivity loss for overlapping regions, which leverages correlations with visible masks and facilitates accurate amodal segmentation. Experiments are conducted on several challenging datasets and the results show that our proposed method can outperform existing state-of-the-art methods with large margins.
Authors: Qingyuan Yang, Guanzhou Chen, Xiaoliang Tan, Tong Wang, Jiaqi Wang, Xiaodong Zhang
Stereo matching and semantic segmentation are significant tasks in binocular satellite 3D reconstruction. However, previous studies primarily view these as independent parallel tasks, lacking an integrated multitask learning framework. This work introduces a solution, the Single-branch Semantic Stereo Network (S3Net), which innovatively combines semantic segmentation and stereo matching using Self-Fuse and Mutual-Fuse modules. Unlike preceding methods that utilize semantic or disparity information independently, our method dentifies and leverages the intrinsic link between these two tasks, leading to a more accurate understanding of semantic information and disparity estimation. Comparative testing on the US3D dataset proves the effectiveness of our S3Net. Our model improves the mIoU in semantic segmentation from 61.38 to 67.39, and reduces the D1-Error and average endpoint error (EPE) in disparity estimation from 10.051 to 9.579 and 1.439 to 1.403 respectively, surpassing existing competitive methods. Our codes are available at:https://github.com/CVEO/S3Net.
Authors: Yilan Zhang, Yingxue Xu, Jianqi Chen, Fengying Xie, Hao Chen
Multimodal learning significantly benefits cancer survival prediction, especially the integration of pathological images and genomic data. Despite advantages of multimodal learning for cancer survival prediction, massive redundancy in multimodal data prevents it from extracting discriminative and compact information: (1) An extensive amount of intra-modal task-unrelated information blurs discriminability, especially for gigapixel whole slide images (WSIs) with many patches in pathology and thousands of pathways in genomic data, leading to an ``intra-modal redundancy" issue. (2) Duplicated information among modalities dominates the representation of multimodal data, which makes modality-specific information prone to being ignored, resulting in an ``inter-modal redundancy" issue. To address these, we propose a new framework, Prototypical Information Bottlenecking and Disentangling (PIBD), consisting of Prototypical Information Bottleneck (PIB) module for intra-modal redundancy and Prototypical Information Disentanglement (PID) module for inter-modal redundancy. Specifically, a variant of information bottleneck, PIB, is proposed to model prototypes approximating a bunch of instances for different risk levels, which can be used for selection of discriminative instances within modality. PID module decouples entangled multimodal data into compact distinct components: modality-common and modality-specific knowledge, under the guidance of the joint prototypical distribution. Extensive experiments on five cancer benchmark datasets demonstrated our superiority over other methods.
Authors: Jan-Niklas Dihlmann, Andreas Engelhardt, Hendrik Lensch
Advances in image diffusion models have recently led to notable improvements in the generation of high-quality images. In combination with Neural Radiance Fields (NeRFs), they enabled new opportunities in 3D generation. However, most generative 3D approaches are object-centric and applying them to editing existing photorealistic scenes is not trivial. We propose SIGNeRF, a novel approach for fast and controllable NeRF scene editing and scene-integrated object generation. A new generative update strategy ensures 3D consistency across the edited images, without requiring iterative optimization. We find that depth-conditioned diffusion models inherently possess the capability to generate 3D consistent views by requesting a grid of images instead of single views. Based on these insights, we introduce a multi-view reference sheet of modified images. Our method updates an image collection consistently based on the reference sheet and refines the original NeRF with the newly generated image set in one go. By exploiting the depth conditioning mechanism of the image diffusion model, we gain fine control over the spatial location of the edit and enforce shape guidance by a selected region or an external mesh.
Authors: Idit Diamant, Idan Achituve, Arnon Netzer
Source-free domain adaptation (SFDA) aims to transfer knowledge learned from a source domain to an unlabeled target domain, where the source data is unavailable during adaptation. Existing approaches for SFDA focus on self-training usually including well-established entropy minimization and pseudo-labeling techniques. Recent work suggested a co-learning strategy to improve the quality of the generated target pseudo-labels using robust pretrained networks such as Swin-B. However, since the generated pseudo-labels depend on the source model, they may be noisy due to domain shift. In this paper, we view SFDA from the perspective of label noise learning and learn to de-confuse the pseudo-labels. More specifically, we learn a noise transition matrix of the pseudo-labels to capture the label corruption of each class and learn the underlying true label distribution. Estimating the noise transition matrix enables a better true class-posterior estimation results with better prediction accuracy. We demonstrate the effectiveness of our approach applied with several SFDA methods: SHOT, SHOT++, and AaD. We obtain state-of-the-art results on three domain adaptation datasets: VisDA, DomainNet, and OfficeHome.
Authors: Fanda Fan, Chunjie Luo, Jianfeng Zhan, Wanling Gao
The burgeoning field of Artificial Intelligence Generated Content (AIGC) is witnessing rapid advancements, particularly in video generation. This paper introduces AIGCBench, a pioneering comprehensive and scalable benchmark designed to evaluate a variety of video generation tasks, with a primary focus on Image-to-Video (I2V) generation. AIGCBench tackles the limitations of existing benchmarks, which suffer from a lack of diverse datasets, by including a varied and open-domain image-text dataset that evaluates different state-of-the-art algorithms under equivalent conditions. We employ a novel text combiner and GPT-4 to create rich text prompts, which are then used to generate images via advanced Text-to-Image models. To establish a unified evaluation framework for video generation tasks, our benchmark includes 11 metrics spanning four dimensions to assess algorithm performance. These dimensions are control-video alignment, motion effects, temporal consistency, and video quality. These metrics are both reference video-dependent and video-free, ensuring a comprehensive evaluation strategy. The evaluation standard proposed correlates well with human judgment, providing insights into the strengths and weaknesses of current I2V algorithms. The findings from our extensive experiments aim to stimulate further research and development in the I2V field. AIGCBench represents a significant step toward creating standardized benchmarks for the broader AIGC landscape, proposing an adaptable and equitable framework for future assessments of video generation tasks.
Authors: Yichen Liu, Huajian Zhang, Daqing Gao
Object detection models represented by YOLO series have been widely used and have achieved great results on the high quality datasets, but not all the working conditions are ideal. To settle down the problem of locating targets on low quality datasets, the existing methods either train a new object detection network, or need a large collection of low-quality datasets to train. However, we propose a framework in this paper and apply it on the YOLO models called DiffYOLO. Specifically, we extract feature maps from the denoising diffusion probabilistic models to enhance the well-trained models, which allows us fine-tune YOLO on high-quality datasets and test on low-quality datasets. The results proved this framework can not only prove the performance on noisy datasets, but also prove the detection results on high-quality test datasets. We will supplement more experiments later (with various datasets and network architectures).
Authors: Jing Yang, Jian Cheng, Cheng Li, Wenxin Fan, Juan Zou, Ruoyou Wu, Shanshan Wang
Diffusion Magnetic Resonance Imaging (dMRI) plays a crucial role in the noninvasive investigation of tissue microstructural properties and structural connectivity in the \textit{in vivo} human brain. However, to effectively capture the intricate characteristics of water diffusion at various directions and scales, it is important to employ comprehensive q-space sampling. Unfortunately, this requirement leads to long scan times, limiting the clinical applicability of dMRI. To address this challenge, we propose SSOR, a Simultaneous q-Space sampling Optimization and Reconstruction framework. We jointly optimize a subset of q-space samples using a continuous representation of spherical harmonic functions and a reconstruction network. Additionally, we integrate the unique properties of diffusion magnetic resonance imaging (dMRI) in both the q-space and image domains by applying $l1$-norm and total-variation regularization. The experiments conducted on HCP data demonstrate that SSOR has promising strengths both quantitatively and qualitatively and exhibits robustness to noise.
Authors: Dengdi Sun, Yajie Pan, Andong Lu, Chenglong Li, Bin Luo
Many RGBT tracking researches primarily focus on modal fusion design, while overlooking the effective handling of target appearance changes. While some approaches have introduced historical frames or fuse and replace initial templates to incorporate temporal information, they have the risk of disrupting the original target appearance and accumulating errors over time. To alleviate these limitations, we propose a novel Transformer RGBT tracking approach, which mixes spatio-temporal multimodal tokens from the static multimodal templates and multimodal search regions in Transformer to handle target appearance changes, for robust RGBT tracking. We introduce independent dynamic template tokens to interact with the search region, embedding temporal information to address appearance changes, while also retaining the involvement of the initial static template tokens in the joint feature extraction process to ensure the preservation of the original reliable target appearance information that prevent deviations from the target appearance caused by traditional temporal updates. We also use attention mechanisms to enhance the target features of multimodal template tokens by incorporating supplementary modal cues, and make the multimodal search region tokens interact with multimodal dynamic template tokens via attention mechanisms, which facilitates the conveyance of multimodal-enhanced target change information. Our module is inserted into the transformer backbone network and inherits joint feature extraction, search-template matching, and cross-modal interaction. Extensive experiments on three RGBT benchmark datasets show that the proposed approach maintains competitive performance compared to other state-of-the-art tracking algorithms while running at 39.1 FPS.
Authors: Necip Enes Gengec, Ergin Tari
The availability of the Global Positioning System (GPS) trajectory data is increasing along with the availability of different GPS receivers and with the increasing use of various mobility services. GPS trajectory is an important data source which is used in traffic density detection, transport mode detection, mapping data inferences with the use of different methods such as image processing and machine learning methods. While the data size increases, efficient representation of this type of data is becoming difficult to be used in these methods. A common approach is the representation of GPS trajectory information such as average speed, bearing, etc. in raster image form and applying analysis methods. In this study, we evaluate GPS trajectory data rasterization using the spatial join functions of QGIS, PostGIS+QGIS, and our iterative spatial structured grid aggregation implementation coded in the Python programming language. Our implementation is also parallelizable, and this parallelization is also included as the fourth method. According to the results of experiment carried out with an example GPS trajectory dataset, QGIS method and PostGIS+QGIS method showed relatively low performance with respect to our method using the metric of total processing time. PostGIS+QGIS method achieved the best results for spatial join though its total performance decreased quickly while test area size increases. On the other hand, both of our methods' performances decrease directly proportional to GPS point. And our methods' performance can be increased proportional to the increase with the number of processor cores and/or with multiple computing clusters.
Authors: Hua Han (1 and 2), Cheng Li (1), Lei Xie (3), Yuanjing Feng (3), Alou Diakite (1 and 2), Shanshan Wang (1 and 4) ((1) Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China, (2) University of Chinese Academy of Sciences, Beijing, China, (3) College of Information Engineering, Zhejiang University of Technology, Hangzhou, China, (4) Peng Cheng Laboratory, Shenzhen, China)
Accurate segmentation of the retinogeniculate visual pathway (RGVP) aids in the diagnosis and treatment of visual disorders by identifying disruptions or abnormalities within the pathway. However, the complex anatomical structure and connectivity of RGVP make it challenging to achieve accurate segmentation. In this study, we propose a novel Modality Exchange Network (ME-Net) that effectively utilizes multi-modal magnetic resonance (MR) imaging information to enhance RGVP segmentation. Our ME-Net has two main contributions. Firstly, we introduce an effective multi-modal soft-exchange technique. Specifically, we design a channel and spatially mixed attention module to exchange modality information between T1-weighted and fractional anisotropy MR images. Secondly, we propose a cross-fusion module that further enhances the fusion of information between the two modalities. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches in terms of RGVP segmentation performance.
Authors: Yaozong Zheng, Bineng Zhong, Qihua Liang, Zhiyi Mo, Shengping Zhang, Xianxian Li
Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers persistently lean on sparse temporal relationships between reference and search frames via an offline mode. Consequently, they can only interact independently within each image-pair and establish limited temporal correlations. To alleviate the above problem, we propose a simple, flexible and effective video-level tracking pipeline, named \textbf{ODTrack}, which densely associates the contextual relationships of video frames in an online token propagation manner. ODTrack receives video frames of arbitrary length to capture the spatio-temporal trajectory relationships of an instance, and compresses the discrimination features (localization information) of a target into a token sequence to achieve frame-to-frame association. This new solution brings the following benefits: 1) the purified token sequences can serve as prompts for the inference in the next video frame, whereby past information is leveraged to guide future inference; 2) the complex online update strategies are effectively avoided by the iterative propagation of token sequences, and thus we can achieve more efficient model representation and computation. ODTrack achieves a new \textit{SOTA} performance on seven benchmarks, while running at real-time speed. Code and models are available at \url{https://github.com/GXNU-ZhongLab/ODTrack}.
Authors: Wenxin Fan, Jian Cheng, Cheng Li, Xinrui Ma, Jing Yang, Juan Zou, Ruoyou Wu, Qiegen Liu, Shanshan Wang
Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI). Nevertheless, existing methods tend to suffer from Rician noise and detail loss in reconstructing the DTI-derived parametric maps especially when sparsely sampled q-space data are used. This paper proposes a novel method, AID-DTI (Accelerating hIgh fiDelity Diffusion Tensor Imaging), to facilitate fast and accurate DTI with only six measurements. AID-DTI is equipped with a newly designed Singular Value Decomposition (SVD)-based regularizer, which can effectively capture fine details while suppressing noise during network training. Experimental results on Human Connectome Project (HCP) data consistently demonstrate that the proposed method estimates DTI parameter maps with fine-grained details and outperforms three state-of-the-art methods both quantitatively and qualitatively.
Authors: Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Jingdong Sun, Wangmeng Xiang, Yusen Hu, Xianhui Lin, Xiaoyang Kang, Zengke Jin, Bin Luo, Yifeng Geng, Xuansong Xie, Jingren Zhou
This paper introduces the WordArt Designer API, a novel framework for user-driven artistic typography synthesis utilizing Large Language Models (LLMs) on ModelScope. We address the challenge of simplifying artistic typography for non-professionals by offering a dynamic, adaptive, and computationally efficient alternative to traditional rigid templates. Our approach leverages the power of LLMs to understand and interpret user input, facilitating a more intuitive design process. We demonstrate through various case studies how users can articulate their aesthetic preferences and functional requirements, which the system then translates into unique and creative typographic designs. Our evaluations indicate significant improvements in user satisfaction, design flexibility, and creative expression over existing systems. The WordArt Designer API not only democratizes the art of typography but also opens up new possibilities for personalized digital communication and design.
Authors: Jiraphon Yenphraphai, Xichen Pan, Sainan Liu, Daniele Panozzo, Saining Xie
We present Image Sculpting, a new framework for editing 2D images by incorporating tools from 3D geometry and graphics. This approach differs markedly from existing methods, which are confined to 2D spaces and typically rely on textual instructions, leading to ambiguity and limited control. Image Sculpting converts 2D objects into 3D, enabling direct interaction with their 3D geometry. Post-editing, these objects are re-rendered into 2D, merging into the original image to produce high-fidelity results through a coarse-to-fine enhancement process. The framework supports precise, quantifiable, and physically-plausible editing options such as pose editing, rotation, translation, 3D composition, carving, and serial addition. It marks an initial step towards combining the creative freedom of generative models with the precision of graphics pipelines.
Authors: Yuzhou Yang, Yangming Zhou, Qichao Ying, Zhenxing Qian, Dan Zeng, Liang Liu
This paper reviews and summarizes the research results on fact-based fake news from the perspectives of tasks and problems, algorithm strategies, and datasets. First, the paper systematically explains the task definition and core problems of fact-based fake news detection. Second, the paper summarizes the existing detection methods based on the algorithm principles. Third, the paper analyzes the classic and newly proposed datasets in the field, and summarizes the experimental results on each dataset. Finally, the paper summarizes the advantages and disadvantages of existing methods, proposes several challenges that methods in this field may face, and looks forward to the next stage of research. It is hoped that this paper will provide reference for subsequent work in the field.
Authors: Zhizhen Wang
Monitoring cameras are extensively utilized in industrial production to monitor equipment running. With advancements in computer vision, device recognition using image features is viable. This paper presents a vision-assisted identification system that implements real-time automatic equipment labeling through image matching in surveillance videos. The system deploys the ORB algorithm to extract image features and the GMS algorithm to remove incorrect matching points. According to the principles of clustering and template locality, a method known as Local Adaptive Clustering (LAC) has been established to enhance label positioning. This method segments matching templates using the cluster center, which improves the efficiency and stability of labels. The experimental results demonstrate that LAC effectively curtails the label drift.
Authors: Long Peng, Yang Cao, Yuejin Sun, Yang Wang
JPEG is a widely used compression scheme to efficiently reduce the volume of transmitted images. The artifacts appear among blocks due to the information loss, which not only affects the quality of images but also harms the subsequent high-level tasks in terms of feature drifting. High-level vision models trained on high-quality images will suffer performance degradation when dealing with compressed images, especially on mobile devices. Numerous learning-based JPEG artifact removal methods have been proposed to handle visual artifacts. However, it is not an ideal choice to use these JPEG artifact removal methods as a pre-processing for compressed image classification for the following reasons: 1. These methods are designed for human vision rather than high-level vision models; 2. These methods are not efficient enough to serve as pre-processing on resource-constrained devices. To address these issues, this paper proposes a novel lightweight AFD module to boost the performance of pre-trained image classification models when facing compressed images. First, a FDE-Net is devised to generate the spatial-wise FDM in the DCT domain. Next, the estimated FDM is transmitted to the FE-Net to generate the mapping relationship between degraded features and corresponding high-quality features. A simple but effective RepConv block equipped with structural re-parameterization is utilized in FE-Net, which enriches feature representation in the training phase while maintaining efficiency in the deployment phase. After training on limited compressed images, the AFD-Module can serve as a "plug-and-play" model for pre-trained classification models to improve their performance on compressed images. Experiments demonstrate that our proposed AFD module can comprehensively improve the accuracy of the pre-trained classification models and significantly outperform the existing methods.
Authors: Wei Yao, Hongwen Zhang, Yunlian Sun, Jinhui Tang
The recovery of 3D human mesh from monocular images has significantly been developed in recent years. However, existing models usually ignore spatial and temporal information, which might lead to mesh and image misalignment and temporal discontinuity. For this reason, we propose a novel Spatio-Temporal Alignment Fusion (STAF) model. As a video-based model, it leverages coherence clues from human motion by an attention-based Temporal Coherence Fusion Module (TCFM). As for spatial mesh-alignment evidence, we extract fine-grained local information through predicted mesh projection on the feature maps. Based on the spatial features, we further introduce a multi-stage adjacent Spatial Alignment Fusion Module (SAFM) to enhance the feature representation of the target frame. In addition to the above, we propose an Average Pooling Module (APM) to allow the model to focus on the entire input sequence rather than just the target frame. This method can remarkably improve the smoothness of recovery results from video. Extensive experiments on 3DPW, MPII3D, and H36M demonstrate the superiority of STAF. We achieve a state-of-the-art trade-off between precision and smoothness. Our code and more video results are on the project page https://yw0208.github.io/staf/
Authors: Thomas Lips, Victor-Louis De Gusseme, Francis wyffels
Assistive robots should be able to wash, fold or iron clothes. However, due to the variety, deformability and self-occlusions of clothes, creating general-purpose robot systems for cloth manipulation is challenging. Synthetic data is a promising direction to improve generalization, though its usability is often limited by the sim-to-real gap. To advance the use of synthetic data for cloth manipulation and to enable tasks such as robotic folding, we present a synthetic data pipeline to train keypoint detectors for almost flattened cloth items. To test its performance, we have also collected a real-world dataset. We train detectors for both T-shirts, towels and shorts and obtain an average precision of 64.3%. Fine-tuning on real-world data improves performance to 74.2%. Additional insight is provided by discussing various failure modes of the keypoint detectors and by comparing different approaches to obtain cloth meshes and materials. We also quantify the remaining sim-to-real gap and argue that further improvements to the fidelity of cloth assets will be required to further reduce this gap. The code, dataset and trained models are available online.
Authors: Fan Liu, Tianshu Zhang, Wenwen Dai, Wenwen Cai Xiaocong Zhou, Delong Chen
Multi-modal (vision-language) models, such as CLIP, are replacing traditional supervised pre-training models (e.g., ImageNet-based pre-training) as the new generation of visual foundation models. These models with robust and aligned semantic representations learned from billions of internet image-text pairs and can be applied to various downstream tasks in a zero-shot manner. However, in some fine-grained domains like medical imaging and remote sensing, the performance of multi-modal foundation models often leaves much to be desired. Consequently, many researchers have begun to explore few-shot adaptation methods for these models, gradually deriving three main technical approaches: 1) prompt-based methods, 2) adapter-based methods, and 3) external knowledge-based methods. Nevertheless, this rapidly developing field has produced numerous results without a comprehensive survey to systematically organize the research progress. Therefore, in this survey, we introduce and analyze the research advancements in few-shot adaptation methods for multi-modal models, summarizing commonly used datasets and experimental setups, and comparing the results of different methods. In addition, due to the lack of reliable theoretical support for existing methods, we derive the few-shot adaptation generalization error bound for multi-modal models. The theorem reveals that the generalization error of multi-modal foundation models is constrained by three factors: domain gap, model capacity, and sample size. Based on this, we propose three possible solutions from the following aspects: 1) adaptive domain generalization, 2) adaptive model selection, and 3) adaptive knowledge utilization.
Authors: Yuexing Han, Liheng Ruan, Bing Wang
Images generated by most of generative models trained with limited data often exhibit deficiencies in either fidelity, diversity, or both. One effective solution to address the limitation is few-shot generative model adaption. However, the type of approaches typically rely on a large-scale pre-trained model, serving as a source domain, to facilitate information transfer to the target domain. In this paper, we propose a method called Information Transfer from the Built Geodesic Surface (ITBGS), which contains two module: Feature Augmentation on Geodesic Surface (FAGS); Interpolation and Regularization (I\&R). With the FAGS module, a pseudo-source domain is created by projecting image features from the training dataset into the Pre-Shape Space, subsequently generating new features on the Geodesic surface. Thus, no pre-trained models is needed for the adaption process during the training of generative models with FAGS. I\&R module are introduced for supervising the interpolated images and regularizing their relative distances, respectively, to further enhance the quality of generated images. Through qualitative and quantitative experiments, we demonstrate that the proposed method consistently achieves optimal or comparable results across a diverse range of semantically distinct datasets, even in extremely few-shot scenarios.
Authors: Zheng Yuan, Jie Zhang, Yude Wang, Shiguang Shan, Xilin Chen
The attention mechanism has been proven effective on various visual tasks in recent years. In the semantic segmentation task, the attention mechanism is applied in various methods, including the case of both Convolution Neural Networks (CNN) and Vision Transformer (ViT) as backbones. However, we observe that the attention mechanism is vulnerable to patch-based adversarial attacks. Through the analysis of the effective receptive field, we attribute it to the fact that the wide receptive field brought by global attention may lead to the spread of the adversarial patch. To address this issue, in this paper, we propose a Robust Attention Mechanism (RAM) to improve the robustness of the semantic segmentation model, which can notably relieve the vulnerability against patch-based attacks. Compared to the vallina attention mechanism, RAM introduces two novel modules called Max Attention Suppression and Random Attention Dropout, both of which aim to refine the attention matrix and limit the influence of a single adversarial patch on the semantic segmentation results of other positions. Extensive experiments demonstrate the effectiveness of our RAM to improve the robustness of semantic segmentation models against various patch-based attack methods under different attack settings.
Authors: Zheng Yuan, Jie Zhang, Shiguang Shan
In recent years, the Vision Transformer (ViT) model has gradually become mainstream in various computer vision tasks, and the robustness of the model has received increasing attention. However, existing large models tend to prioritize performance during training, potentially neglecting the robustness, which may lead to serious security concerns. In this paper, we establish a new challenge: exploring how to use a small number of additional parameters for adversarial finetuning to quickly and effectively enhance the adversarial robustness of a standardly trained model. To address this challenge, we develop the novel LNLoRA module, incorporating a learnable layer normalization before the conventional LoRA module, which helps mitigate magnitude differences in parameters between the adversarial and standard training paradigms.
Furthermore, we propose the FullLoRA-AT framework by integrating the learnable LNLoRA modules into all key components of ViT-based models while keeping the pretrained model frozen, which can significantly improve the model robustness via adversarial finetuning in a parameter-efficient manner.
Extensive experiments on CIFAR-10, CIFAR-100, and Imagenette demonstrate the superiority of our proposed FullLoRA-AT framework. It achieves comparable robustness with full finetuning while only requiring about 5% of the learnable parameters. This also effectively addresses concerns regarding extra model storage space and enormous training time caused by adversarial finetuning.
Authors: Lin Bai, Caiyan Jia, Ziying Song, Chaoqun Cui
With the development of social media, rumors have been spread broadly on social media platforms, causing great harm to society. Beside textual information, many rumors also use manipulated images or conceal textual information within images to deceive people and avoid being detected, making multimodal rumor detection be a critical problem. The majority of multimodal rumor detection methods mainly concentrate on extracting features of source claims and their corresponding images, while ignoring the comments of rumors and their propagation structures. These comments and structures imply the wisdom of crowds and are proved to be crucial to debunk rumors. Moreover, these methods usually only extract visual features in a basic manner, seldom consider tampering or textual information in images. Therefore, in this study, we propose a novel Vision and Graph Fused Attention Network (VGA) for rumor detection to utilize propagation structures among posts so as to obtain the crowd opinions and further explore visual tampering features, as well as the textual information hidden in images. We conduct extensive experiments on three datasets, demonstrating that VGA can effectively detect multimodal rumors and outperform state-of-the-art methods significantly.
Authors: Polina Kirichenko, Mark Ibrahim, Randall Balestriero, Diane Bouchacourt, Ramakrishna Vedantam, Hamed Firooz, Andrew Gordon Wilson
Data augmentation (DA) encodes invariance and provides implicit regularization critical to a model's performance in image classification tasks. However, while DA improves average accuracy, recent studies have shown that its impact can be highly class dependent: achieving optimal average accuracy comes at the cost of significantly hurting individual class accuracy by as much as 20% on ImageNet. There has been little progress in resolving class-level accuracy drops due to a limited understanding of these effects. In this work, we present a framework for understanding how DA interacts with class-level learning dynamics. Using higher-quality multi-label annotations on ImageNet, we systematically categorize the affected classes and find that the majority are inherently ambiguous, co-occur, or involve fine-grained distinctions, while DA controls the model's bias towards one of the closely related classes. While many of the previously reported performance drops are explained by multi-label annotations, our analysis of class confusions reveals other sources of accuracy degradation. We show that simple class-conditional augmentation strategies informed by our framework improve performance on the negatively affected classes.
Authors: Suraj Patil, William Berman, Robin Rombach, Patrick von Platen
We present aMUSEd, an open-source, lightweight masked image model (MIM) for text-to-image generation based on MUSE. With 10 percent of MUSE's parameters, aMUSEd is focused on fast image generation. We believe MIM is under-explored compared to latent diffusion, the prevailing approach for text-to-image generation. Compared to latent diffusion, MIM requires fewer inference steps and is more interpretable. Additionally, MIM can be fine-tuned to learn additional styles with only a single image. We hope to encourage further exploration of MIM by demonstrating its effectiveness on large-scale text-to-image generation and releasing reproducible training code. We also release checkpoints for two models which directly produce images at 256x256 and 512x512 resolutions.
Authors: Ethan Zhu, Haijian Sun
Connected and automated vehicles (CAVs) have become a transformative technology that can change our daily life. Currently, millimeter-wave (mmWave) bands are identified as the promising CAV connectivity solution. While it can provide high data rate, their realization faces many challenges such as high attenuation during mmWave signal propagation and mobility management. Existing solution has to initiate pilot signal to measure channel information, then apply signal processing to calculate the best narrow beam towards the receiver end to guarantee sufficient signal power. This process takes significant overhead and time, hence not suitable for vehicles. In this study, we propose an autonomous and low-cost testbed to collect extensive co-located mmWave signal and other sensors data such as LiDAR (Light Detection and Ranging), cameras, ultrasonic, etc, traditionally for ``automated'', to facilitate mmWave vehicular communications. Intuitively, these sensors can build a 3D map around the vehicle and signal propagation path can be estimated, eliminating iterative the process via pilot signals. This multimodal data fusion, together with AI, is expected to bring significant advances in ``connected'' research.
Authors: Kumar Ashutosh, Zihui Xue, Tushar Nagarajan, Kristen Grauman
We introduce the video detours problem for navigating instructional videos. Given a source video and a natural language query asking to alter the how-to video's current path of execution in a certain way, the goal is to find a related ''detour video'' that satisfies the requested alteration. To address this challenge, we propose VidDetours, a novel video-language approach that learns to retrieve the targeted temporal segments from a large repository of how-to's using video-and-text conditioned queries. Furthermore, we devise a language-based pipeline that exploits how-to video narration text to create weakly supervised training data. We demonstrate our idea applied to the domain of how-to cooking videos, where a user can detour from their current recipe to find steps with alternate ingredients, tools, and techniques. Validating on a ground truth annotated dataset of 16K samples, we show our model's significant improvements over best available methods for video retrieval and question answering, with recall rates exceeding the state of the art by 35%.
Authors: David Junhao Zhang, Dongxu Li, Hung Le, Mike Zheng Shou, Caiming Xiong, Doyen Sahoo
Most existing video diffusion models (VDMs) are limited to mere text conditions. Thereby, they are usually lacking in control over visual appearance and geometry structure of the generated videos. This work presents Moonshot, a new video generation model that conditions simultaneously on multimodal inputs of image and text. The model builts upon a core module, called multimodal video block (MVB), which consists of conventional spatialtemporal layers for representing video features, and a decoupled cross-attention layer to address image and text inputs for appearance conditioning. In addition, we carefully design the model architecture such that it can optionally integrate with pre-trained image ControlNet modules for geometry visual conditions, without needing of extra training overhead as opposed to prior methods. Experiments show that with versatile multimodal conditioning mechanisms, Moonshot demonstrates significant improvement on visual quality and temporal consistency compared to existing models. In addition, the model can be easily repurposed for a variety of generative applications, such as personalized video generation, image animation and video editing, unveiling its potential to serve as a fundamental architecture for controllable video generation. Models will be made public on https://github.com/salesforce/LAVIS.
Authors: Yulin Li, Tianzhu Zhang, Yongdong Zhang
Visible-infrared person re-identification (VI-ReID) is challenging due to the significant cross-modality discrepancies between visible and infrared images. While existing methods have focused on designing complex network architectures or using metric learning constraints to learn modality-invariant features, they often overlook which specific component of the image causes the modality discrepancy problem. In this paper, we first reveal that the difference in the amplitude component of visible and infrared images is the primary factor that causes the modality discrepancy and further propose a novel Frequency Domain modality-invariant feature learning framework (FDMNet) to reduce modality discrepancy from the frequency domain perspective. Our framework introduces two novel modules, namely the Instance-Adaptive Amplitude Filter (IAF) module and the Phrase-Preserving Normalization (PPNorm) module, to enhance the modality-invariant amplitude component and suppress the modality-specific component at both the image- and feature-levels. Extensive experimental results on two standard benchmarks, SYSU-MM01 and RegDB, demonstrate the superior performance of our FDMNet against state-of-the-art methods.
Authors: Carlos Boned, Maxime Talarmain, Nabil Ghanmi, Guillaume Chiron, Sanket Biswas, Ahmad Montaser Awal, Oriol Ramos Terrades
This paper presents a new synthetic dataset of ID and travel documents, called SIDTD. The SIDTD dataset is created to help training and evaluating forged ID documents detection systems. Such a dataset has become a necessity as ID documents contain personal information and a public dataset of real documents can not be released. Moreover, forged documents are scarce, compared to legit ones, and the way they are generated varies from one fraudster to another resulting in a class of high intra-variability. In this paper we trained state-of-the-art models on this dataset and we compare them to the performance achieved in larger, but private, datasets. The creation of this dataset will help to document image analysis community to progress in the task of ID document verification.
Authors: Pratyusha Sharma, Tamar Rott Shaham, Manel Baradad, Stephanie Fu, Adrian Rodriguez-Munoz, Shivam Duggal, Phillip Isola, Antonio Torralba
What does learning to model relationships between strings teach large language models (LLMs) about the visual world? We systematically evaluate LLMs' abilities to generate and recognize an assortment of visual concepts of increasing complexity and then demonstrate how a preliminary visual representation learning system can be trained using models of text. As language models lack the ability to consume or output visual information as pixels, we use code to represent images in our study. Although LLM-generated images do not look like natural images, results on image generation and the ability of models to correct these generated images indicate that precise modeling of strings can teach language models about numerous aspects of the visual world. Furthermore, experiments on self-supervised visual representation learning, utilizing images generated with text models, highlight the potential to train vision models capable of making semantic assessments of natural images using just LLMs.
Authors: Parthipan Siva, Alexander Wong, Patricia Hewston, George Ioannidis, Dr. Jonathan Adachi, Dr. Alexander Rabinovich, Andrea Lee, Alexandra Papaioannou
With an aging population, numerous assistive and monitoring technologies are under development to enable older adults to age in place. To facilitate aging in place predicting risk factors such as falls, and hospitalization and providing early interventions are important. Much of the work on ambient monitoring for risk prediction has centered on gait speed analysis, utilizing privacy-preserving sensors like radar. Despite compelling evidence that monitoring step length, in addition to gait speed, is crucial for predicting risk, radar-based methods have not explored step length measurement in the home. Furthermore, laboratory experiments on step length measurement using radars are limited to proof of concept studies with few healthy subjects. To address this gap, a radar-based step length measurement system for the home is proposed based on detection and tracking using radar point cloud, followed by Doppler speed profiling of the torso to obtain step lengths in the home. The proposed method was evaluated in a clinical environment, involving 35 frail older adults, to establish its validity. Additionally, the method was assessed in people's homes, with 21 frail older adults who had participated in the clinical assessment. The proposed radar-based step length measurement method was compared to the gold standard Zeno Walkway Gait Analysis System, revealing a 4.5cm/8.3% error in a clinical setting. Furthermore, it exhibited excellent reliability (ICC(2,k)=0.91, 95% CI 0.82 to 0.96) in uncontrolled home settings. The method also proved accurate in uncontrolled home settings, as indicated by a strong agreement (ICC(3,k)=0.81 (95% CI 0.53 to 0.92)) between home measurements and in-clinic assessments.
Authors: Evonne Ng, Javier Romero, Timur Bagautdinov, Shaojie Bai, Trevor Darrell, Angjoo Kanazawa, Alexander Richard
We present a framework for generating full-bodied photorealistic avatars that gesture according to the conversational dynamics of a dyadic interaction. Given speech audio, we output multiple possibilities of gestural motion for an individual, including face, body, and hands. The key behind our method is in combining the benefits of sample diversity from vector quantization with the high-frequency details obtained through diffusion to generate more dynamic, expressive motion. We visualize the generated motion using highly photorealistic avatars that can express crucial nuances in gestures (e.g. sneers and smirks). To facilitate this line of research, we introduce a first-of-its-kind multi-view conversational dataset that allows for photorealistic reconstruction. Experiments show our model generates appropriate and diverse gestures, outperforming both diffusion- and VQ-only methods. Furthermore, our perceptual evaluation highlights the importance of photorealism (vs. meshes) in accurately assessing subtle motion details in conversational gestures. Code and dataset available online.
Authors: Weirong Chen, Le Chen, Rui Wang, Marc Pollefeys
Visual odometry estimates the motion of a moving camera based on visual input. Existing methods, mostly focusing on two-view point tracking, often ignore the rich temporal context in the image sequence, thereby overlooking the global motion patterns and providing no assessment of the full trajectory reliability. These shortcomings hinder performance in scenarios with occlusion, dynamic objects, and low-texture areas. To address these challenges, we present the Long-term Effective Any Point Tracking (LEAP) module. LEAP innovatively combines visual, inter-track, and temporal cues with mindfully selected anchors for dynamic track estimation. Moreover, LEAP's temporal probabilistic formulation integrates distribution updates into a learnable iterative refinement module to reason about point-wise uncertainty. Based on these traits, we develop LEAP-VO, a robust visual odometry system adept at handling occlusions and dynamic scenes. Our mindful integration showcases a novel practice by employing long-term point tracking as the front-end. Extensive experiments demonstrate that the proposed pipeline significantly outperforms existing baselines across various visual odometry benchmarks.
Authors: Yunze Liu, Yun Liu, Che Jiang, Kangbo Lyu, Weikang Wan, Hao Shen, Boqiang Liang, Zhoujie Fu, He Wang, Li Yi
We present HOI4D, a large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction. HOI4D consists of 2.4M RGB-D egocentric video frames over 4000 sequences collected by 4 participants interacting with 800 different object instances from 16 categories over 610 different indoor rooms. Frame-wise annotations for panoptic segmentation, motion segmentation, 3D hand pose, category-level object pose and hand action have also been provided, together with reconstructed object meshes and scene point clouds. With HOI4D, we establish three benchmarking tasks to promote category-level HOI from 4D visual signals including semantic segmentation of 4D dynamic point cloud sequences, category-level object pose tracking, and egocentric action segmentation with diverse interaction targets. In-depth analysis shows HOI4D poses great challenges to existing methods and produces great research opportunities.
Authors: Sanghyuk Chun, Wonjae Kim, Song Park, Minsuk Chang, Seong Joon Oh
Image-Text matching (ITM) is a common task for evaluating the quality of Vision and Language (VL) models. However, existing ITM benchmarks have a significant limitation. They have many missing correspondences, originating from the data construction process itself. For example, a caption is only matched with one image although the caption can be matched with other similar images and vice versa. To correct the massive false negatives, we construct the Extended COCO Validation (ECCV) Caption dataset by supplying the missing associations with machine and human annotators. We employ five state-of-the-art ITM models with diverse properties for our annotation process. Our dataset provides x3.6 positive image-to-caption associations and x8.5 caption-to-image associations compared to the original MS-COCO. We also propose to use an informative ranking-based metric mAP@R, rather than the popular Recall@K (R@K). We re-evaluate the existing 25 VL models on existing and proposed benchmarks. Our findings are that the existing benchmarks, such as COCO 1K R@K, COCO 5K R@K, CxC R@1 are highly correlated with each other, while the rankings change when we shift to the ECCV mAP@R. Lastly, we delve into the effect of the bias introduced by the choice of machine annotator. Source code and dataset are available at https://github.com/naver-ai/eccv-caption
Authors: Leonid Mill, Oliver Aust, Jochen A. Ackermann, Philipp Burger, Monica Pascual, Katrin Palumbo-Zerr, Gerhard Krönke, Stefan Uderhardt, Georg Schett, Christoph S. Clemen, Rolf Schröder, Christian Holtzhausen, Samir Jabari, Andreas Maier, Anika Grüneboom
Artificial intelligence (AI), machine learning, and deep learning (DL) methods are becoming increasingly important in the field of biomedical image analysis. However, to exploit the full potential of such methods, a representative number of experimentally acquired images containing a significant number of manually annotated objects is needed as training data. Here we introduce SYNTA (synthetic data) as a novel approach for the generation of synthetic, photo-realistic, and highly complex biomedical images as training data for DL systems. We show the versatility of our approach in the context of muscle fiber and connective tissue analysis in histological sections. We demonstrate that it is possible to perform robust and expert-level segmentation tasks on previously unseen real-world data, without the need for manual annotations using synthetic training data alone. Being a fully parametric technique, our approach poses an interpretable and controllable alternative to Generative Adversarial Networks (GANs) and has the potential to significantly accelerate quantitative image analysis in a variety of biomedical applications in microscopy and beyond.
Authors: Zhaoxin Fan, Yuqing Pan, Hao Xu, Zhenbo Song, Zhicheng Wang, Kejian Wu, Hongyan Liu, Jun He
In the field of full-body reconstruction, the scarcity of annotated data often impedes the efficacy of prevailing methods. To address this issue, we introduce FuRPE, a novel framework that employs part-experts and an ingenious pseudo ground-truth selection scheme to derive high-quality pseudo labels. These labels, central to our approach, equip our network with the capability to efficiently learn from the available data. Integral to FuRPE is a unique exponential moving average training strategy and expert-derived feature distillation strategy. These novel elements of FuRPE not only serve to further refine the model but also to reduce potential biases that may arise from inaccuracies in pseudo labels, thereby optimizing the network's training process and enhancing the robustness of the model. We apply FuRPE to train both two-stage and fully convolutional single-stage full-body reconstruction networks. Our exhaustive experiments on numerous benchmark datasets illustrate a substantial performance boost over existing methods, underscoring FuRPE's potential to reshape the state-of-the-art in full-body reconstruction.
Authors: Oleksandr Balabanov, Bernhard Mehlig, Hampus Linander
We introduce ensembles of stochastic neural networks to approximate the Bayesian posterior, combining stochastic methods such as dropout with deep ensembles. The stochastic ensembles are formulated as families of distributions and trained to approximate the Bayesian posterior with variational inference. We implement stochastic ensembles based on Monte Carlo dropout, DropConnect and a novel non-parametric version of dropout and evaluate them on a toy problem and CIFAR image classification. For both tasks, we test the quality of the posteriors directly against Hamiltonian Monte Carlo simulations. Our results show that stochastic ensembles provide more accurate posterior estimates than other popular baselines for Bayesian inference.
Authors: Patrick Grady, Jeremy A. Collins, Chengcheng Tang, Christopher D. Twigg, Kunal Aneja, James Hays, Charles C. Kemp
Touch plays a fundamental role in manipulation for humans; however, machine perception of contact and pressure typically requires invasive sensors. Recent research has shown that deep models can estimate hand pressure based on a single RGB image. However, evaluations have been limited to controlled settings since collecting diverse data with ground-truth pressure measurements is difficult. We present a novel approach that enables diverse data to be captured with only an RGB camera and a cooperative participant. Our key insight is that people can be prompted to apply pressure in a certain way, and this prompt can serve as a weak label to supervise models to perform well under varied conditions. We collect a novel dataset with 51 participants making fingertip contact with diverse objects. Our network, PressureVision++, outperforms human annotators and prior work. We also demonstrate an application of PressureVision++ to mixed reality where pressure estimation allows everyday surfaces to be used as arbitrary touch-sensitive interfaces. Code, data, and models are available online.
Authors: Rasmus Laurvig Haugaard, Frederik Hagelskjær, Thorbjørn Mosekjær Iversen
Object pose estimation is a core computer vision problem and often an essential component in robotics. Pose estimation is usually approached by seeking the single best estimate of an object's pose, but this approach is ill-suited for tasks involving visual ambiguity. In such cases it is desirable to estimate the uncertainty as a pose distribution to allow downstream tasks to make informed decisions. Pose distributions can have arbitrary complexity which motivates estimating unparameterized distributions, however, until now they have only been used for orientation estimation on SO(3) due to the difficulty in training on and normalizing over SE(3). We propose a novel method for pose distribution estimation on SE(3). We use a hierarchical grid, a pyramid, which enables efficient importance sampling during training and sparse evaluation of the pyramid at inference, allowing real time 6D pose distribution estimation. Our method outperforms state-of-the-art methods on SO(3), and to the best of our knowledge, we provide the first quantitative results on pose distribution estimation on SE(3). Code will be available at spyropose.github.io
Authors: Sourya Sengupta, Mark A. Anastasio
Interpretability is highly desired for deep neural network-based classifiers, especially when addressing high-stake decisions in medical imaging. Commonly used post-hoc interpretability methods have the limitation that they can produce plausible but different interpretations of a given model, leading to ambiguity about which one to choose. To address this problem, a novel decision-theory-inspired approach is investigated to establish a self-interpretable model, given a pre-trained deep binary black-box medical image classifier. This approach involves utilizing a self-interpretable encoder-decoder model in conjunction with a single-layer fully connected network with unity weights. The model is trained to estimate the test statistic of the given trained black-box deep binary classifier to maintain a similar accuracy. The decoder output image, referred to as an equivalency map, is an image that represents a transformed version of the to-be-classified image that, when processed by the fixed fully connected layer, produces the same test statistic value as the original classifier. The equivalency map provides a visualization of the transformed image features that directly contribute to the test statistic value and, moreover, permits quantification of their relative contributions. Unlike the traditional post-hoc interpretability methods, the proposed method is self-interpretable, quantitative. Detailed quantitative and qualitative analyses have been performed with three different medical image binary classification tasks.
Authors: Yue Ma, Yingqing He, Xiaodong Cun, Xintao Wang, Siran Chen, Ying Shan, Xiu Li, Qifeng Chen
Generating text-editable and pose-controllable character videos have an imperious demand in creating various digital human. Nevertheless, this task has been restricted by the absence of a comprehensive dataset featuring paired video-pose captions and the generative prior models for videos. In this work, we design a novel two-stage training scheme that can utilize easily obtained datasets (i.e.,image pose pair and pose-free video) and the pre-trained text-to-image (T2I) model to obtain the pose-controllable character videos. Specifically, in the first stage, only the keypoint-image pairs are used only for a controllable text-to-image generation. We learn a zero-initialized convolutional encoder to encode the pose information. In the second stage, we finetune the motion of the above network via a pose-free video dataset by adding the learnable temporal self-attention and reformed cross-frame self-attention blocks. Powered by our new designs, our method successfully generates continuously pose-controllable character videos while keeps the editing and concept composition ability of the pre-trained T2I model. The code and models will be made publicly available.
Authors: Dhyey Manish Rajani, Surya Pratap Singh, Rahul Kashyap Swayampakula
In this paper, we propose an advanced methodology for the detection of 3D objects and precise estimation of their spatial positions from a single image. Unlike conventional frameworks that rely solely on center-point and dimension predictions, our research leverages a deep convolutional neural network-based 3D object weighted orientation regression paradigm. These estimates are then seamlessly integrated with geometric constraints obtained from a 2D bounding box, resulting in derivation of a comprehensive 3D bounding box. Our novel network design encompasses two key outputs. The first output involves the estimation of 3D object orientation through the utilization of a discrete-continuous loss function. Simultaneously, the second output predicts objectivity-based confidence scores with minimal variance. Additionally, we also introduce enhancements to our methodology through the incorporation of lightweight residual feature extractors. By combining the derived estimates with the geometric constraints inherent in the 2D bounding box, our approach significantly improves the accuracy of 3D object pose determination, surpassing baseline methodologies. Our method is rigorously evaluated on the KITTI 3D object detection benchmark, demonstrating superior performance.
Authors: Candice Schumann, Gbolahan O. Olanubi, Auriel Wright, Ellis Monk Jr., Courtney Heldreth, Susanna Ricco
Understanding different human attributes and how they affect model behavior may become a standard need for all model creation and usage, from traditional computer vision tasks to the newest multimodal generative AI systems. In computer vision specifically, we have relied on datasets augmented with perceived attribute signals (e.g., gender presentation, skin tone, and age) and benchmarks enabled by these datasets. Typically labels for these tasks come from human annotators. However, annotating attribute signals, especially skin tone, is a difficult and subjective task. Perceived skin tone is affected by technical factors, like lighting conditions, and social factors that shape an annotator's lived experience. This paper examines the subjectivity of skin tone annotation through a series of annotation experiments using the Monk Skin Tone (MST) scale, a small pool of professional photographers, and a much larger pool of trained crowdsourced annotators. Along with this study we release the Monk Skin Tone Examples (MST-E) dataset, containing 1515 images and 31 videos spread across the full MST scale. MST-E is designed to help train human annotators to annotate MST effectively. Our study shows that annotators can reliably annotate skin tone in a way that aligns with an expert in the MST scale, even under challenging environmental conditions. We also find evidence that annotators from different geographic regions rely on different mental models of MST categories resulting in annotations that systematically vary across regions. Given this, we advise practitioners to use a diverse set of annotators and a higher replication count for each image when annotating skin tone for fairness research.
Authors: Anahita Fathi Kazerooni, Nastaran Khalili, Xinyang Liu, Debanjan Haldar, Zhifan Jiang, Syed Muhammed Anwar, Jake Albrecht, Maruf Adewole, Udunna Anazodo, Hannah Anderson, Sina Bagheri, Ujjwal Baid, Timothy Bergquist, Austin J. Borja, Evan Calabrese, Verena Chung, Gian-Marco Conte, Farouk Dako, James Eddy, Ivan Ezhov, Ariana Familiar, Keyvan Farahani, Shuvanjan Haldar, Juan Eugenio Iglesias, Anastasia Janas, Elaine Johansen, Blaise V Jones, Florian Kofler, Dominic LaBella, Hollie Anne Lai, Koen Van Leemput, Hongwei Bran Li, Nazanin Maleki, Aaron S McAllister, Zeke Meier, Bjoern Menze, Ahmed W Moawad, Khanak K Nandolia, Julija Pavaine, Marie Piraud, Tina Poussaint, Sanjay P Prabhu, Zachary Reitman, Andres Rodriguez, Jeffrey D Rudie, Ibraheem Salman Shaikh, Lubdha M. Shah, Nakul Sheth, Russel Taki Shinohara, et al. (23 additional authors not shown)
Pediatric tumors of the central nervous system are the most common cause of cancer-related death in children. The five-year survival rate for high-grade gliomas in children is less than 20\%. Due to their rarity, the diagnosis of these entities is often delayed, their treatment is mainly based on historic treatment concepts, and clinical trials require multi-institutional collaborations. The MICCAI Brain Tumor Segmentation (BraTS) Challenge is a landmark community benchmark event with a successful history of 12 years of resource creation for the segmentation and analysis of adult glioma. Here we present the CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge, which represents the first BraTS challenge focused on pediatric brain tumors with data acquired across multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. The BraTS-PEDs 2023 challenge focuses on benchmarking the development of volumentric segmentation algorithms for pediatric brain glioma through standardized quantitative performance evaluation metrics utilized across the BraTS 2023 cluster of challenges. Models gaining knowledge from the BraTS-PEDs multi-parametric structural MRI (mpMRI) training data will be evaluated on separate validation and unseen test mpMRI dataof high-grade pediatric glioma. The CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge brings together clinicians and AI/imaging scientists to lead to faster development of automated segmentation techniques that could benefit clinical trials, and ultimately the care of children with brain tumors.
Authors: Xingqun Qi, Chen Liu, Lincheng Li, Jie Hou, Haoran Xin, Xin Yu
Generating vivid and diverse 3D co-speech gestures is crucial for various applications in animating virtual avatars. While most existing methods can generate gestures from audio directly, they usually overlook that emotion is one of the key factors of authentic co-speech gesture generation. In this work, we propose EmotionGesture, a novel framework for synthesizing vivid and diverse emotional co-speech 3D gestures from audio. Considering emotion is often entangled with the rhythmic beat in speech audio, we first develop an Emotion-Beat Mining module (EBM) to extract the emotion and audio beat features as well as model their correlation via a transcript-based visual-rhythm alignment. Then, we propose an initial pose based Spatial-Temporal Prompter (STP) to generate future gestures from the given initial poses. STP effectively models the spatial-temporal correlations between the initial poses and the future gestures, thus producing the spatial-temporal coherent pose prompt. Once we obtain pose prompts, emotion, and audio beat features, we will generate 3D co-speech gestures through a transformer architecture. However, considering the poses of existing datasets often contain jittering effects, this would lead to generating unstable gestures. To address this issue, we propose an effective objective function, dubbed Motion-Smooth Loss. Specifically, we model motion offset to compensate for jittering ground-truth by forcing gestures to be smooth. Last, we present an emotion-conditioned VAE to sample emotion features, enabling us to generate diverse emotional results. Extensive experiments demonstrate that our framework outperforms the state-of-the-art, achieving vivid and diverse emotional co-speech 3D gestures. Our code and dataset will be released at the project page: https://xingqunqi-lab.github.io/Emotion-Gesture-Web/
Authors: Paul Grimal, Hervé Le Borgne, Olivier Ferret, Julien Tourille
The progress in the generation of synthetic images has made it crucial to assess their quality. While several metrics have been proposed to assess the rendering of images, it is crucial for Text-to-Image (T2I) models, which generate images based on a prompt, to consider additional aspects such as to which extent the generated image matches the important content of the prompt. Moreover, although the generated images usually result from a random starting point, the influence of this one is generally not considered. In this article, we propose a new metric based on prompt templates to study the alignment between the content specified in the prompt and the corresponding generated images. It allows us to better characterize the alignment in terms of the type of the specified objects, their number, and their color. We conducted a study on several recent T2I models about various aspects. An additional interesting result we obtained with our approach is that image quality can vary drastically depending on the noise used as a seed for the images. We also quantify the influence of the number of concepts in the prompt, their order as well as their (color) attributes. Finally, our method allows us to identify some seeds that produce better images than others, opening novel directions of research on this understudied topic.
Authors: Igor Dubinin, Felix Effenberger
Residual connections have been proposed as an architecture-based inductive bias to mitigate the problem of exploding and vanishing gradients and increased task performance in both feed-forward and recurrent networks (RNNs) when trained with the backpropagation algorithm. Yet, little is known about how residual connections in RNNs influence their dynamics and fading memory properties. Here, we introduce weakly coupled residual recurrent networks (WCRNNs) in which residual connections result in well-defined Lyapunov exponents and allow for studying properties of fading memory. We investigate how the residual connections of WCRNNs influence their performance, network dynamics, and memory properties on a set of benchmark tasks. We show that several distinct forms of residual connections yield effective inductive biases that result in increased network expressivity. In particular, those are residual connections that (i) result in network dynamics at the proximity of the edge of chaos, (ii) allow networks to capitalize on characteristic spectral properties of the data, and (iii) result in heterogeneous memory properties. In addition, we demonstrate how our results can be extended to non-linear residuals and introduce a weakly coupled residual initialization scheme that can be used for Elman RNNs.
Authors: Ximing Xing, Chuang Wang, Haitao Zhou, Zhihao Hu, Chongxuan Li, Dong Xu, Qian Yu
Exemplar-based sketch-to-photo synthesis allows users to generate photo-realistic images based on sketches. Recently, diffusion-based methods have achieved impressive performance on image generation tasks, enabling highly-flexible control through text-driven generation or energy functions. However, generating photo-realistic images with color and texture from sketch images remains challenging for diffusion models. Sketches typically consist of only a few strokes, with most regions left blank, making it difficult for diffusion-based methods to produce photo-realistic images. In this work, we propose a two-stage method named ``Inversion-by-Inversion" for exemplar-based sketch-to-photo synthesis. This approach includes shape-enhancing inversion and full-control inversion. During the shape-enhancing inversion process, an uncolored photo is generated with the guidance of a shape-energy function. This step is essential to ensure control over the shape of the generated photo. In the full-control inversion process, we propose an appearance-energy function to control the color and texture of the final generated photo.Importantly, our Inversion-by-Inversion pipeline is training-free and can accept different types of exemplars for color and texture control. We conducted extensive experiments to evaluate our proposed method, and the results demonstrate its effectiveness. The code and project can be found at https://ximinng.github.io/inversion-by-inversion-project/.
Authors: Marek Rychlik, Bekir Tanriover, Yan Han
The scope of our study is all UNOS data of the USA organ donors since 2008. The data is not analyzable in a large scale in the past because it was captured in PDF documents known as "Attachments", whereby every donor is represented by dozens of PDF documents in heterogenous formats. To make the data analyzable, one needs to convert the content inside these PDFs to an analyzable data format, such as a standard SQL database. In this paper we will focus on 2022 UNOS data comprised of $\approx 400,000$ PDF documents spanning millions of pages. The totality of UNOS data covers 15 years (2008--20022) and our results will be quickly extended to the entire data. Our method captures a portion of the data in DCD flowsheets, kidney perfusion data, and data captured during patient hospital stay (e.g. vital signs, ventilator settings, etc.). The current paper assumes that the reader is familiar with the content of the UNOS data. The overview of the types of data and challenges they present is a subject of another paper. Here we focus on demonstrating that the goal of building a comprehensive, analyzable database from UNOS documents is an attainable task, and we provide an overview of our methodology. The project resulted in datasets by far larger than previously available even in this preliminary phase.
Authors: Xiao Feng Zhang, Tian Yi Song, Jia Wei Yao
Segment Anything (SAM), an advanced universal image segmentation model trained on an expansive visual dataset, has set a new benchmark in image segmentation and computer vision. However, it faced challenges when it came to distinguishing between shadows and their backgrounds. To address this, we developed Deshadow-Anything, considering the generalization of large-scale datasets, and we performed Fine-tuning on large-scale datasets to achieve image shadow removal. The diffusion model can diffuse along the edges and textures of an image, helping to remove shadows while preserving the details of the image. Furthermore, we design Multi-Self-Attention Guidance (MSAG) and adaptive input perturbation (DDPM-AIP) to accelerate the iterative training speed of diffusion. Experiments on shadow removal tasks demonstrate that these methods can effectively improve image restoration performance.
Authors: Yaojie Shen, Xin Gu, Kai Xu, Heng Fan, Longyin Wen, Libo Zhang
Existing video captioning approaches typically require to first sample video frames from a decoded video and then conduct a subsequent process (e.g., feature extraction and/or captioning model learning). In this pipeline, manual frame sampling may ignore key information in videos and thus degrade performance. Additionally, redundant information in the sampled frames may result in low efficiency in the inference of video captioning. Addressing this, we study video captioning from a different perspective in compressed domain, which brings multi-fold advantages over the existing pipeline: 1) Compared to raw images from the decoded video, the compressed video, consisting of I-frames, motion vectors and residuals, is highly distinguishable, which allows us to leverage the entire video for learning without manual sampling through a specialized model design; 2) The captioning model is more efficient in inference as smaller and less redundant information is processed. We propose a simple yet effective end-to-end transformer in the compressed domain for video captioning that enables learning from the compressed video for captioning. We show that even with a simple design, our method can achieve state-of-the-art performance on different benchmarks while running almost 2x faster than existing approaches. Code is available at https://github.com/acherstyx/CoCap.
Authors: Yuting Wang, Jinpeng Wang, Bin Chen, Ziyun Zeng, Shu-Tao Xia
Given a text query, partially relevant video retrieval (PRVR) seeks to find untrimmed videos containing pertinent moments in a database. For PRVR, clip modeling is essential to capture the partial relationship between texts and videos. Current PRVR methods adopt scanning-based clip construction to achieve explicit clip modeling, which is information-redundant and requires a large storage overhead. To solve the efficiency problem of PRVR methods, this paper proposes GMMFormer, a Gaussian-Mixture-Model based Transformer which models clip representations implicitly. During frame interactions, we incorporate Gaussian-Mixture-Model constraints to focus each frame on its adjacent frames instead of the whole video. Then generated representations will contain multi-scale clip information, achieving implicit clip modeling. In addition, PRVR methods ignore semantic differences between text queries relevant to the same video, leading to a sparse embedding space. We propose a query diverse loss to distinguish these text queries, making the embedding space more intensive and contain more semantic information. Extensive experiments on three large-scale video datasets (i.e., TVR, ActivityNet Captions, and Charades-STA) demonstrate the superiority and efficiency of GMMFormer. Code is available at \url{https://github.com/huangmozhi9527/GMMFormer}.
Authors: Jiarui Zhang, Mahyar Khayatkhoei, Prateek Chhikara, Filip Ilievski
Multimodal Large Language Models (MLLMs) have recently achieved promising zero-shot accuracy on visual question answering (VQA) -- a fundamental task affecting various downstream applications and domains. Given the great potential for the broad use of these models, it is important to investigate their limitations in dealing with different image and question properties. In this work, we investigate whether MLLMs can perceive details as well as larger components in images. In particular, we show that their zero-shot accuracy in answering visual questions is very sensitive to the size of the visual subject related to the question, declining up to $45.91\%$ with size. Furthermore, we show that this effect is causal by observing that human visual cropping can significantly mitigate their sensitivity to size. To scale up the usefulness of human cropping, we propose ViCrop, a general framework that utilizes automatic visual cropping to enhance zero-shot VQA of MLLMs. We construct five variants of ViCrop leveraging either external localization models or the decision process of the given MLLM itself. Our results show that ViCrop improves MLLMs' zero-shot accuracy across different VQA datasets, for example, enhances BLIP2-T5's performance by $32.23\%$ on the TextVQA test set. To facilitate further investigation of MLLMs' behaviors, our code is publicly released.
Authors: Taehyeon Kim, Eric Lin, Junu Lee, Christian Lau, Vaikkunth Mugunthan
Federated Learning (FL) has emerged as a potent framework for training models across distributed data sources while maintaining data privacy. Nevertheless, it faces challenges with limited high-quality labels and non-IID client data, particularly in applications like autonomous driving. To address these hurdles, we navigate the uncharted waters of Semi-Supervised Federated Object Detection (SSFOD). We present a pioneering SSFOD framework, designed for scenarios where labeled data reside only at the server while clients possess unlabeled data. Notably, our method represents the inaugural implementation of SSFOD for clients with 0% labeled non-IID data, a stark contrast to previous studies that maintain some subset of labels at each client. We propose FedSTO, a two-stage strategy encompassing Selective Training followed by Orthogonally enhanced full-parameter training, to effectively address data shift (e.g. weather conditions) between server and clients. Our contributions include selectively refining the backbone of the detector to avert overfitting, orthogonality regularization to boost representation divergence, and local EMA-driven pseudo label assignment to yield high-quality pseudo labels. Extensive validation on prominent autonomous driving datasets (BDD100K, Cityscapes, and SODA10M) attests to the efficacy of our approach, demonstrating state-of-the-art results. Remarkably, FedSTO, using just 20-30% of labels, performs nearly as well as fully-supervised centralized training methods.
Authors: Feng Zhang, Ming Tian, Zhiqiang Li, Bin Xu, Qingbo Lu, Changxin Gao, Nong Sang
Tone mapping aims to convert high dynamic range (HDR) images to low dynamic range (LDR) representations, a critical task in the camera imaging pipeline. In recent years, 3-Dimensional LookUp Table (3D LUT) based methods have gained attention due to their ability to strike a favorable balance between enhancement performance and computational efficiency. However, these methods often fail to deliver satisfactory results in local areas since the look-up table is a global operator for tone mapping, which works based on pixel values and fails to incorporate crucial local information. To this end, this paper aims to address this issue by exploring a novel strategy that integrates global and local operators by utilizing closed-form Laplacian pyramid decomposition and reconstruction. Specifically, we employ image-adaptive 3D LUTs to manipulate the tone in the low-frequency image by leveraging the specific characteristics of the frequency information. Furthermore, we utilize local Laplacian filters to refine the edge details in the high-frequency components in an adaptive manner. Local Laplacian filters are widely used to preserve edge details in photographs, but their conventional usage involves manual tuning and fixed implementation within camera imaging pipelines or photo editing tools. We propose to learn parameter value maps progressively for local Laplacian filters from annotated data using a lightweight network. Our model achieves simultaneous global tone manipulation and local edge detail preservation in an end-to-end manner. Extensive experimental results on two benchmark datasets demonstrate that the proposed method performs favorably against state-of-the-art methods.
Authors: Hanxiao Chen
Impressed by the coolest skateboarding sports program from 2021 Tokyo Olympic Games, we are the first to curate the original real-world video datasets "SkateboardAI" in the wild, even self-design and implement diverse uni-modal and multi-modal video action recognition approaches to recognize different tricks accurately. For uni-modal methods, we separately apply (1) CNN and LSTM; (2) CNN and BiLSTM; (3) CNN and BiLSTM with effective attention mechanisms; (4) Transformer-based action recognition pipeline. Transferred to the multi-modal conditions, we investigated the two-stream Inflated-3D architecture on "SkateboardAI" datasets to compare its performance with uni-modal cases. In sum, our objective is developing an excellent AI sport referee for the coolest skateboarding competitions.
Authors: Feng Wang, Jieru Mei, Alan Yuille
Recent advances in contrastive language-image pretraining (CLIP) have demonstrated strong capabilities in zero-shot classification by aligning visual representations with target text embeddings in an image level. However, in dense prediction tasks, CLIP often struggles to localize visual features within an image and fails to give accurate pixel-level predictions, which prevents it from functioning as a generalized visual foundation model. In this work, we aim to enhance CLIP's potential for semantic segmentation with minimal modifications to its pretrained models. By rethinking self-attention, we surprisingly find that CLIP can adapt to dense prediction tasks by simply introducing a novel Correlative Self-Attention (CSA) mechanism. Specifically, we replace the traditional self-attention block of CLIP vision encoder's last layer by our CSA module and reuse its pretrained projection matrices of query, key, and value, leading to a training-free adaptation approach for CLIP's zero-shot semantic segmentation. Extensive experiments show the advantage of CSA: we obtain a 38.2% average zero-shot mIoU across eight semantic segmentation benchmarks highlighted in this paper, significantly outperforming the existing SoTA's 33.9% and the vanilla CLIP's 14.1%.
Authors: Mingyue Guo, Li Yuan, Zhaoyi Yan, Binghui Chen, Yaowei Wang, Qixiang Ye
Crowd counting has achieved significant progress by training regressors to predict instance positions. In heavily crowded scenarios, however, regressors are challenged by uncontrollable annotation variance, which causes density map bias and context information inaccuracy. In this study, we propose mutual prompt learning (mPrompt), which leverages a regressor and a segmenter as guidance for each other, solving bias and inaccuracy caused by annotation variance while distinguishing foreground from background. In specific, mPrompt leverages point annotations to tune the segmenter and predict pseudo head masks in a way of point prompt learning. It then uses the predicted segmentation masks, which serve as spatial constraint, to rectify biased point annotations as context prompt learning. mPrompt defines a way of mutual information maximization from prompt learning, mitigating the impact of annotation variance while improving model accuracy. Experiments show that mPrompt significantly reduces the Mean Average Error (MAE), demonstrating the potential to be general framework for down-stream vision tasks.
Authors: Yuxin Zhang, Fan Tang, Nisha Huang, Haibin Huang, Chongyang Ma, Weiming Dong, Changsheng Xu
The essence of a video lies in its dynamic motions, including character actions, object movements, and camera movements. While text-to-video generative diffusion models have recently advanced in creating diverse contents, controlling specific motions through text prompts remains a significant challenge. A primary issue is the coupling of appearance and motion, often leading to overfitting on appearance. To tackle this challenge, we introduce MotionCrafter, a novel one-shot instance-guided motion customization method. MotionCrafter employs a parallel spatial-temporal architecture that injects the reference motion into the temporal component of the base model, while the spatial module is independently adjusted for character or style control. To enhance the disentanglement of motion and appearance, we propose an innovative dual-branch motion disentanglement approach, comprising a motion disentanglement loss and an appearance prior enhancement strategy. During training, a frozen base model provides appearance normalization, effectively separating appearance from motion and thereby preserving diversity. Comprehensive quantitative and qualitative experiments, along with user preference tests, demonstrate that MotionCrafter can successfully integrate dynamic motions while preserving the coherence and quality of the base model with a wide range of appearance generation capabilities. Project page: https://zyxelsa.github.io/homepage-motioncrafter. Codes are available at https://github.com/zyxElsa/MotionCrafter.
Authors: Philipp V. Rouast
This report introduces VitalLens, an app that estimates vital signs such as heart rate and respiration rate from selfie video in real time. VitalLens uses a computer vision model trained on a diverse dataset of video and physiological sensor data. We benchmark performance on several diverse datasets, including VV-Medium, which consists of 289 unique participants. VitalLens outperforms several existing methods including POS and MTTS-CAN on all datasets while maintaining a fast inference speed. On VV-Medium, VitalLens achieves mean absolute errors of 0.71 bpm for heart rate estimation, and 0.76 bpm for respiratory rate estimation.
Authors: Haoyi Wang, Victor Sanchez, Chang-Tsun Li
Cross-age facial images are typically challenging and expensive to collect, making noise-free age-oriented datasets relatively small compared to widely-used large-scale facial datasets. Additionally, in real scenarios, images of the same subject at different ages are usually hard or even impossible to obtain. Both of these factors lead to a lack of supervised data, which limits the versatility of supervised methods for age-invariant face recognition, a critical task in applications such as security and biometrics. To address this issue, we propose a novel semi-supervised learning approach named Cross-Age Contrastive Learning (CACon). Thanks to the identity-preserving power of recent face synthesis models, CACon introduces a new contrastive learning method that leverages an additional synthesized sample from the input image. We also propose a new loss function in association with CACon to perform contrastive learning on a triplet of samples. We demonstrate that our method not only achieves state-of-the-art performance in homogeneous-dataset experiments on several age-invariant face recognition benchmarks but also outperforms other methods by a large margin in cross-dataset experiments.
Authors: Wenhao Li, Xiu Su, Shan You, Tao Huang, Fei Wang, Chen Qian, Chang Xu
Diffusion models have demonstrated remarkable efficacy in various generative tasks with the predictive prowess of denoising model. Currently, these models employ a uniform denoising approach across all timesteps. However, the inherent variations in noisy latents at each timestep lead to conflicts during training, constraining the potential of diffusion models. To address this challenge, we propose a novel two-stage training strategy termed Step-Adaptive Training. In the initial stage, a base denoising model is trained to encompass all timesteps. Subsequently, we partition the timesteps into distinct groups, fine-tuning the model within each group to achieve specialized denoising capabilities. Recognizing that the difficulties of predicting noise at different timesteps vary, we introduce a diverse model size requirement. We dynamically adjust the model size for each timestep by estimating task difficulty based on its signal-to-noise ratio before fine-tuning. This adjustment is facilitated by a proxy-based structural importance assessment mechanism, enabling precise and efficient pruning of the base denoising model. Our experiments validate the effectiveness of the proposed training strategy, demonstrating an improvement in the FID score on CIFAR10 by over 0.3 while utilizing only 80\% of the computational resources. This innovative approach not only enhances model performance but also significantly reduces computational costs, opening new avenues for the development and application of diffusion models.
Authors: Huan Ling, Seung Wook Kim, Antonio Torralba, Sanja Fidler, Karsten Kreis
Text-guided diffusion models have revolutionized image and video generation and have also been successfully used for optimization-based 3D object synthesis. Here, we instead focus on the underexplored text-to-4D setting and synthesize dynamic, animated 3D objects using score distillation methods with an additional temporal dimension. Compared to previous work, we pursue a novel compositional generation-based approach, and combine text-to-image, text-to-video, and 3D-aware multiview diffusion models to provide feedback during 4D object optimization, thereby simultaneously enforcing temporal consistency, high-quality visual appearance and realistic geometry. Our method, called Align Your Gaussians (AYG), leverages dynamic 3D Gaussian Splatting with deformation fields as 4D representation. Crucial to AYG is a novel method to regularize the distribution of the moving 3D Gaussians and thereby stabilize the optimization and induce motion. We also propose a motion amplification mechanism as well as a new autoregressive synthesis scheme to generate and combine multiple 4D sequences for longer generation. These techniques allow us to synthesize vivid dynamic scenes, outperform previous work qualitatively and quantitatively and achieve state-of-the-art text-to-4D performance. Due to the Gaussian 4D representation, different 4D animations can be seamlessly combined, as we demonstrate. AYG opens up promising avenues for animation, simulation and digital content creation as well as synthetic data generation.
Authors: Yifei Chen, Binfeng Zou, Zhaoxin Guo, Yiyu Huang, Yifan Huang, Feiwei Qin, Qinhai Li, Changmiao Wang
Pulmonary embolism (PE) is a prevalent lung disease that can lead to right ventricular hypertrophy and failure in severe cases, ranking second in severity only to myocardial infarction and sudden death. Pulmonary artery CT angiography (CTPA) is a widely used diagnostic method for PE. However, PE detection presents challenges in clinical practice due to limitations in imaging technology. CTPA can produce noises similar to PE, making confirmation of its presence time-consuming and prone to overdiagnosis. Nevertheless, the traditional segmentation method of PE can not fully consider the hierarchical structure of features, local and global spatial features of PE CT images. In this paper, we propose an automatic PE segmentation method called SCUNet++ (Swin Conv UNet++). This method incorporates multiple fusion dense skip connections between the encoder and decoder, utilizing the Swin Transformer as the encoder. And fuses features of different scales in the decoder subnetwork to compensate for spatial information loss caused by the inevitable downsampling in Swin-UNet or other state-of-the-art methods, effectively solving the above problem. We provide a theoretical analysis of this method in detail and validate it on publicly available PE CT image datasets FUMPE and CAD-PE. The experimental results indicate that our proposed method achieved a Dice similarity coefficient (DSC) of 83.47% and a Hausdorff distance 95th percentile (HD95) of 3.83 on the FUMPE dataset, as well as a DSC of 83.42% and an HD95 of 5.10 on the CAD-PE dataset. These findings demonstrate that our method exhibits strong performance in PE segmentation tasks, potentially enhancing the accuracy of automatic segmentation of PE and providing a powerful diagnostic tool for clinical physicians. Our source code and new FUMPE dataset are available at https://github.com/JustlfC03/SCUNet-plusplus.
Authors: Hansong Zhang, Shikun Li, Pengju Wang, Dan Zeng, Shiming Ge
Training state-of-the-art (SOTA) deep models often requires extensive data, resulting in substantial training and storage costs. To address these challenges, dataset condensation has been developed to learn a small synthetic set that preserves essential information from the original large-scale dataset. Nowadays, optimization-oriented methods have been the primary method in the field of dataset condensation for achieving SOTA results. However, the bi-level optimization process hinders the practical application of such methods to realistic and larger datasets. To enhance condensation efficiency, previous works proposed Distribution-Matching (DM) as an alternative, which significantly reduces the condensation cost. Nonetheless, current DM-based methods have yielded less comparable results to optimization-oriented methods due to their focus on aligning only the first moment of the distributions. In this paper, we present a novel DM-based method named M3D for dataset condensation by Minimizing the Maximum Mean Discrepancy between feature representations of the synthetic and real images. By embedding their distributions in a reproducing kernel Hilbert space, we align all orders of moments of the distributions of real and synthetic images, resulting in a more generalized condensed set. Notably, our method even surpasses the SOTA optimization-oriented method IDC on the high-resolution ImageNet dataset. Extensive analysis is conducted to verify the effectiveness of the proposed method.
Authors: Anqi Yi, Nantheera Anantrasirichai
Accurate object tracking in low-light environments is crucial, particularly in surveillance and ethology applications. However, achieving this is significantly challenging due to the poor quality of captured sequences. Factors such as noise, color imbalance, and low contrast contribute to these challenges. This paper presents a comprehensive study examining the impact of these distortions on automatic object trackers. Additionally, we propose a solution to enhance tracking performance by integrating denoising and low-light enhancement methods into the transformer-based object tracking system. Experimental results show that the proposed tracker, trained with low-light synthetic datasets, outperforms both the vanilla MixFormer and Siam R-CNN.
Authors: Ximing Xing, Haitao Zhou, Chuang Wang, Jing Zhang, Dong Xu, Qian Yu
Recently, text-guided scalable vector graphics (SVGs) synthesis has shown promise in domains such as iconography and sketch. However, existing text-to-SVG generation methods lack editability and struggle with visual quality and result diversity. To address these limitations, we propose a novel text-guided vector graphics synthesis method called SVGDreamer. SVGDreamer incorporates a semantic-driven image vectorization (SIVE) process that enables the decomposition of synthesis into foreground objects and background, thereby enhancing editability. Specifically, the SIVE process introduce attention-based primitive control and an attention-mask loss function for effective control and manipulation of individual elements. Additionally, we propose a Vectorized Particle-based Score Distillation (VPSD) approach to tackle the challenges of color over-saturation, vector primitives over-smoothing, and limited result diversity in existing text-to-SVG generation methods. Furthermore, on the basis of VPSD, we introduce Reward Feedback Learning (ReFL) to accelerate VPSD convergence and improve aesthetic appeal. Extensive experiments have been conducted to validate the effectiveness of SVGDreamer, demonstrating its superiority over baseline methods in terms of editability, visual quality, and diversity. The code and demo of SVGDreamer can be found at \href{https://ximinng.github.io/SVGDreamer-project/}{https://ximinng.github.io/SVGDreamer-project/}.
Authors: Senqiao Yang, Tianyuan Qu, Xin Lai, Zhuotao Tian, Bohao Peng, Shu Liu, Jiaya Jia
While LISA effectively bridges the gap between segmentation and large language models to enable reasoning segmentation, it poses certain limitations: unable to distinguish different instances of the target region, and constrained by the pre-defined textual response formats. In this work, we introduce LISA++, an update to the existing LISA model, focusing on improving core functionalities while keeping the base architecture intact. The main enhancements in LISA++ include: \textbf{1) Enhanced Segmentation}: The instance segmentation ability has been added, providing a more detailed scene analysis along with the existing multi-region semantic segmentation. \textbf{2) More Natural Conversation}: Improved capability for multi-turn dialogue, with the ability to incorporate segmentation results directly into text responses, i.e., Segmentation in Dialogue (SiD). These improvements are achieved by curating the existing samples of generic segmentation datasets, aimed specifically at enhancing the segmentation and conversational skills without structural change and additional data sources. Comparative analysis with the original LISA model shows significant advancements in these areas, positioning LISA++ as a notable upgrade in visual understanding and interaction. LISA++'s adaptability and improved features highlight the versatility of the mask-as-embedding paradigm proposed by LISA, and the potential as a foundational model for diverse applications.
Authors: Miao Rang, Zhenni Bi, Chuanjian Liu, Yunhe Wang, Kai Han
The laws of model size, data volume, computation and model performance have been extensively studied in the field of Natural Language Processing (NLP). However, the scaling laws in Optical Character Recognition (OCR) have not yet been investigated. To address this, we conducted comprehensive studies that involved examining the correlation between performance and the scale of models, data volume and computation in the field of text recognition.Conclusively, the study demonstrates smooth power laws between performance and model size, as well as training data volume, when other influencing factors are held constant. Additionally, we have constructed a large-scale dataset called REBU-Syn, which comprises 6 million real samples and 18 million synthetic samples. Based on our scaling law and new dataset, we have successfully trained a scene text recognition model, achieving a new state-ofthe-art on 6 common test benchmarks with a top-1 average accuracy of 97.42%.
Authors: Shanchuan Lin, Xiao Yang
Diffusion models trained with mean squared error loss tend to generate unrealistic samples. Current state-of-the-art models rely on classifier-free guidance to improve sample quality, yet its surprising effectiveness is not fully understood. In this paper, We show that the effectiveness of classifier-free guidance partly originates from it being a form of implicit perceptual guidance. As a result, we can directly incorporate perceptual loss in diffusion training to improve sample quality. Since the score matching objective used in diffusion training strongly resembles the denoising autoencoder objective used in unsupervised training of perceptual networks, the diffusion model itself is a perceptual network and can be used to generate meaningful perceptual loss. We propose a novel self-perceptual objective that results in diffusion models capable of generating more realistic samples. For conditional generation, our method only improves sample quality without entanglement with the conditional input and therefore does not sacrifice sample diversity. Our method can also improve sample quality for unconditional generation, which was not possible with classifier-free guidance before.
Authors: Qianliang Wu, Haobo Jiang, Yaqing Ding, Lei Luo, Jin Xie, Jian Yang
Efficiently finding optimal correspondences between point clouds is crucial for solving both rigid and non-rigid point cloud registration problems. Existing methods often rely on geometric or semantic feature embedding to establish correspondences and estimate transformations or flow fields. Recently, state-of-the-art methods have employed RAFT-like iterative updates to refine the solution. However, these methods have certain limitations. Firstly, their iterative refinement design lacks transparency, and their iterative updates follow a fixed path during the refinement process, which can lead to suboptimal results. Secondly, these methods overlook the importance of refining or optimizing correspondences (or matching matrices) as a precursor to solving transformations or flow fields. They typically compute candidate correspondences based on distances in the point feature space. However, they only project the candidate matching matrix into some matrix space once with Sinkhorn or dual softmax operations to obtain final correspondences. This one-shot projected matching matrix may be far from the globally optimal one, and these approaches do not consider the distribution of the target matching matrix. In this paper, we propose a novel approach that exploits the Denoising Diffusion Model to predict a searching gradient for the optimal matching matrix within the Doubly Stochastic Matrix Space. During the reverse denoising process, our method iteratively searches for better solutions along this denoising gradient, which points towards the maximum likelihood direction of the target matching matrix. Our method offers flexibility by allowing the search to start from any initial matching matrix provided by the online backbone or white noise. Experimental evaluations on the 3DMatch/3DLoMatch and 4DMatch/4DLoMatch datasets demonstrate the effectiveness of our newly designed framework.
Authors: Jingyu Zhuang, Kuo Wang, Liang Lin, Guanbin Li
Semi-Supervised Object Detection (SSOD) has achieved resounding success by leveraging unlabeled data to improve detection performance. However, in Open Scene Semi-Supervised Object Detection (O-SSOD), unlabeled data may contains unknown objects not observed in the labeled data, which will increase uncertainty in the model's predictions for known objects. It is detrimental to the current methods that mainly rely on self-training, as more uncertainty leads to the lower localization and classification precision of pseudo labels. To this end, we propose Credible Teacher, an end-to-end framework. Credible Teacher adopts an interactive teaching mechanism using flexible labels to prevent uncertain pseudo labels from misleading the model and gradually reduces its uncertainty through the guidance of other credible pseudo labels. Empirical results have demonstrated our method effectively restrains the adverse effect caused by O-SSOD and significantly outperforms existing counterparts.
Authors: Jilan Xu, Yifei Huang, Junlin Hou, Guo Chen, Yuejie Zhang, Rui Feng, Weidi Xie
Understanding human actions from videos of first-person view poses significant challenges. Most prior approaches explore representation learning on egocentric videos only, while overlooking the potential benefit of exploiting existing large-scale third-person videos. In this paper, (1) we develop EgoInstructor, a retrieval-augmented multimodal captioning model that automatically retrieves semantically relevant third-person instructional videos to enhance the video captioning of egocentric videos. (2) For training the cross-view retrieval module, we devise an automatic pipeline to discover ego-exo video pairs from distinct large-scale egocentric and exocentric datasets. (3) We train the cross-view retrieval module with a novel EgoExoNCE loss that pulls egocentric and exocentric video features closer by aligning them to shared text features that describe similar actions. (4) Through extensive experiments, our cross-view retrieval module demonstrates superior performance across seven benchmarks. Regarding egocentric video captioning, EgoInstructor exhibits significant improvements by leveraging third-person videos as references.
Authors: Tianyuan Huang, Zejia Wu, Jiajun Wu, Jackelyn Hwang, Ram Rajagopal
Urban transformations have profound societal impact on both individuals and communities at large. Accurately assessing these shifts is essential for understanding their underlying causes and ensuring sustainable urban planning. Traditional measurements often encounter constraints in spatial and temporal granularity, failing to capture real-time physical changes. While street view imagery, capturing the heartbeat of urban spaces from a pedestrian point of view, can add as a high-definition, up-to-date, and on-the-ground visual proxy of urban change. We curate the largest street view time series dataset to date, and propose an end-to-end change detection model to effectively capture physical alterations in the built environment at scale. We demonstrate the effectiveness of our proposed method by benchmark comparisons with previous literature and implementing it at the city-wide level. Our approach has the potential to supplement existing dataset and serve as a fine-grained and accurate assessment of urban change.
Authors: Dimitrios Kollias, Viktoriia Sharmanska, Stefanos Zafeiriou
Multi-Task Learning (MTL) is a framework, where multiple related tasks are learned jointly and benefit from a shared representation space, or parameter transfer. To provide sufficient learning support, modern MTL uses annotated data with full, or sufficiently large overlap across tasks, i.e., each input sample is annotated for all, or most of the tasks. However, collecting such annotations is prohibitive in many real applications, and cannot benefit from datasets available for individual tasks. In this work, we challenge this setup and show that MTL can be successful with classification tasks with little, or non-overlapping annotations, or when there is big discrepancy in the size of labeled data per task. We explore task-relatedness for co-annotation and co-training, and propose a novel approach, where knowledge exchange is enabled between the tasks via distribution matching. To demonstrate the general applicability of our method, we conducted diverse case studies in the domains of affective computing, face recognition, species recognition, and shopping item classification using nine datasets. Our large-scale study of affective tasks for basic expression recognition and facial action unit detection illustrates that our approach is network agnostic and brings large performance improvements compared to the state-of-the-art in both tasks and across all studied databases. In all case studies, we show that co-training via task-relatedness is advantageous and prevents negative transfer (which occurs when MT model's performance is worse than that of at least one single-task model).