Authors: Chung To Kong
Every country must dispose of old banknotes. At the Hong Kong Monetary Authority visitor center, visitors can buy a paperweight souvenir full of shredded banknotes. Even though the shredded banknotes are small, by using computer vision, it is possible to reconstruct the whole banknote like a jigsaw puzzle. Each paperweight souvenir costs $\$100$ HKD, and it is claimed to contain shredded banknotes equivalent to 138 complete $\$1000$ HKD banknotes. In theory, $\$138,000$ HKD can be recovered by using computer vision. This paper discusses the technique of collecting shredded banknote pieces and applying a computer vision program.
Authors: Hartmut Surmann, Niklas Digakis, Jan-Nicklas Kremer, Julien Meine, Max Schulte, Niklas Voigt
In the realm of digital situational awareness during disaster situations, accurate digital representations, like 3D models, play an indispensable role. To ensure the safety of rescue teams, robotic platforms are often deployed to generate these models. In this paper, we introduce an innovative approach that synergizes the capabilities of compact Unmaned Arial Vehicles (UAVs), smaller than 30 cm, equipped with 360 degree cameras and the advances of Neural Radiance Fields (NeRFs). A NeRF, a specialized neural network, can deduce a 3D representation of any scene using 2D images and then synthesize it from various angles upon request. This method is especially tailored for urban environments which have experienced significant destruction, where the structural integrity of buildings is compromised to the point of barring entry-commonly observed post-earthquakes and after severe fires. We have tested our approach through recent post-fire scenario, underlining the efficacy of NeRFs even in challenging outdoor environments characterized by water, snow, varying light conditions, and reflective surfaces.
Authors: Alex Havrilla, Kevin Rojas, Wenjing Liao, Molei Tao
Diffusion generative models have achieved remarkable success in generating images with a fixed resolution. However, existing models have limited ability to generalize to different resolutions when training data at those resolutions are not available. Leveraging techniques from operator learning, we present a novel deep-learning architecture, Dual-FNO UNet (DFU), which approximates the score operator by combining both spatial and spectral information at multiple resolutions. Comparisons of DFU to baselines demonstrate its scalability: 1) simultaneously training on multiple resolutions improves FID over training at any single fixed resolution; 2) DFU generalizes beyond its training resolutions, allowing for coherent, high-fidelity generation at higher-resolutions with the same model, i.e. zero-shot super-resolution image-generation; 3) we propose a fine-tuning strategy to further enhance the zero-shot super-resolution image-generation capability of our model, leading to a FID of 11.3 at 1.66 times the maximum training resolution on FFHQ, which no other method can come close to achieving.
Authors: Jiacheng Yang, Christina Giannoula, Jun Wu, Mostafa Elhoushi, James Gleeson, Gennady Pekhimenko
Sparse Convolution (SC) is widely used for processing 3D point clouds that are inherently sparse. Different from dense convolution, SC preserves the sparsity of the input point cloud by only allowing outputs to specific locations. To efficiently compute SC, prior SC engines first use hash tables to build a kernel map that stores the necessary General Matrix Multiplication (GEMM) operations to be executed (Map step), and then use a Gather-GEMM-Scatter process to execute these GEMM operations (GMaS step). In this work, we analyze the shortcomings of prior state-of-the-art SC engines, and propose Minuet, a novel memory-efficient SC engine tailored for modern GPUs. Minuet proposes to (i) replace the hash tables used in the Map step with a novel segmented sorting double-traversed binary search algorithm that highly utilizes the on-chip memory hierarchy of GPUs, (ii) use a lightweight scheme to autotune the tile size in the Gather and Scatter operations of the GMaS step, such that to adapt the execution to the particular characteristics of each SC layer, dataset, and GPU architecture, and (iii) employ a padding-efficient GEMM grouping approach that reduces both memory padding and kernel launching overheads. Our evaluations show that Minuet significantly outperforms prior SC engines by on average $1.74\times$ (up to $2.22\times$) for end-to-end point cloud network executions. Our novel segmented sorting double-traversed binary search algorithm achieves superior speedups by $15.8\times$ on average (up to $26.8\times$) over prior SC engines in the Map step. The source code of Minuet is publicly available at https://github.com/UofT-EcoSystem/Minuet.
Authors: Tianyu Li, Calvin Qiao, Guanqiao Ren, KangKang Yin, Sehoon Ha
Interactive motion synthesis is essential in creating immersive experiences in entertainment applications, such as video games and virtual reality. However, generating animations that are both high-quality and contextually responsive remains a challenge. Traditional techniques in the game industry can produce high-fidelity animations but suffer from high computational costs and poor scalability. Trained neural network models alleviate the memory and speed issues, yet fall short on generating diverse motions. Diffusion models offer diverse motion synthesis with low memory usage, but require expensive reverse diffusion processes. This paper introduces the Accelerated Auto-regressive Motion Diffusion Model (AAMDM), a novel motion synthesis framework designed to achieve quality, diversity, and efficiency all together. AAMDM integrates Denoising Diffusion GANs as a fast Generation Module, and an Auto-regressive Diffusion Model as a Polishing Module. Furthermore, AAMDM operates in a lower-dimensional embedded space rather than the full-dimensional pose space, which reduces the training complexity as well as further improves the performance. We show that AAMDM outperforms existing methods in motion quality, diversity, and runtime efficiency, through comprehensive quantitative analyses and visual comparisons. We also demonstrate the effectiveness of each algorithmic component through ablation studies.
Authors: Andrew H. Song, Guillaume Jaume, Drew F.K. Williamson, Ming Y. Lu, Anurag Vaidya, Tiffany R. Miller, Faisal Mahmood
Advances in digitizing tissue slides and the fast-paced progress in artificial intelligence, including deep learning, have boosted the field of computational pathology. This field holds tremendous potential to automate clinical diagnosis, predict patient prognosis and response to therapy, and discover new morphological biomarkers from tissue images. Some of these artificial intelligence-based systems are now getting approved to assist clinical diagnosis; however, technical barriers remain for their widespread clinical adoption and integration as a research tool. This Review consolidates recent methodological advances in computational pathology for predicting clinical end points in whole-slide images and highlights how these developments enable the automation of clinical practice and the discovery of new biomarkers. We then provide future perspectives as the field expands into a broader range of clinical and research tasks with increasingly diverse modalities of clinical data.
Authors: Yang Zhong, Weiping Dou, Andrew Cohen, Dia'a Bisharat, Yuandong Tian, Jiang Zhu, Qing Huo Liu
To extend the antenna design on printed circuit boards (PCBs) for more engineers of interest, we propose a simple method that models PCB antennas with a few basic components. By taking two separate steps to decide their geometric dimensions and positions, antenna prototypes can be facilitated with no experience required. Random sampling statistics relate to the quality of dimensions are used in selecting among dimension candidates. A novel image-based classifier using a convolutional neural network (CNN) is introduced to further determine the positions of these fixed-dimension components. Two examples from wearable products have been chosen to examine the entire workflow. Their final designs are realistic and their performance metrics are not inferior to the ones designed by experienced engineers.
Authors: Youssef Mourchid, Rim Slama
This paper tackles the challenge of automatically assessing physical rehabilitation exercises for patients who perform the exercises without clinician supervision. The objective is to provide a quality score to ensure correct performance and achieve desired results. To achieve this goal, a new graph-based model, the Dense Spatio-Temporal Graph Conv-GRU Network with Transformer, is introduced. This model combines a modified version of STGCN and transformer architectures for efficient handling of spatio-temporal data. The key idea is to consider skeleton data respecting its non-linear structure as a graph and detecting joints playing the main role in each rehabilitation exercise. Dense connections and GRU mechanisms are used to rapidly process large 3D skeleton inputs and effectively model temporal dynamics. The transformer encoder's attention mechanism focuses on relevant parts of the input sequence, making it useful for evaluating rehabilitation exercises. The evaluation of our proposed approach on the KIMORE and UI-PRMD datasets highlighted its potential, surpassing state-of-the-art methods in terms of accuracy and computational time. This resulted in faster and more accurate learning and assessment of rehabilitation exercises. Additionally, our model provides valuable feedback through qualitative illustrations, effectively highlighting the significance of joints in specific exercises.
Authors: Jan Peleska, Felix Brüning, Mario Gleirscher, Wen-ling Huang
This technical report presents research results achieved in the field of verification of trained Convolutional Neural Network (CNN) used for image classification in safety-critical applications. As running example, we use the obstacle detection function needed in future autonomous freight trains with Grade of Automation (GoA) 4. It is shown that systems like GoA 4 freight trains are indeed certifiable today with new standards like ANSI/UL 4600 and ISO 21448 used in addition to the long-existing standards EN 50128 and EN 50129. Moreover, we present a quantitative analysis of the system-level hazard rate to be expected from an obstacle detection function. It is shown that using sensor/perceptor fusion, the fused detection system can meet the tolerable hazard rate deemed to be acceptable for the safety integrity level to be applied (SIL-3). A mathematical analysis of CNN models is performed which results in the identification of classification clusters and equivalence classes partitioning the image input space of the CNN. These clusters and classes are used to introduce a novel statistical testing method for determining the residual error probability of a trained CNN and an associated upper confidence limit. We argue that this greybox approach to CNN verification, taking into account the CNN model's internal structure, is essential for justifying that the statistical tests have covered the trained CNN with its neurons and inter-layer mappings in a comprehensive way.
Authors: Dennis Monari, Jack Larkin, Pedro Machado, Jordan J. Bird, Isibor Kennedy Ihianle, Salisu Wada Yahaya, Farhad Fassihi Tash, Md Mahmudul Hasan, Ahmad Lotfi
Invasive signal crayfish have a detrimental impact on ecosystems. They spread the fungal-type crayfish plague disease (Aphanomyces astaci) that is lethal to the native white clawed crayfish, the only native crayfish species in Britain. Invasive signal crayfish extensively burrow, causing habitat destruction, erosion of river banks and adverse changes in water quality, while also competing with native species for resources and leading to declines in native populations. Moreover, pollution exacerbates the vulnerability of White-clawed crayfish, with their populations declining by over 90% in certain English counties, making them highly susceptible to extinction. To safeguard aquatic ecosystems, it is imperative to address the challenges posed by invasive species and discarded plastics in the United Kingdom's river ecosystem's. The UDEEP platform can play a crucial role in environmental monitoring by performing on-the-fly classification of Signal crayfish and plastic debris while leveraging the efficacy of AI, IoT devices and the power of edge computing (i.e., NJN). By providing accurate data on the presence, spread and abundance of these species, the UDEEP platform can contribute to monitoring efforts and aid in mitigating the spread of invasive species.
Authors: Chanho Lee, Jinsu Son, Hyounguk Shon, Yunho Jeon, Junmo Kim
Rotation-equivariance is an essential yet challenging property in oriented object detection. While general object detectors naturally leverage robustness to spatial shifts due to the translation-equivariance of the conventional CNNs, achieving rotation-equivariance remains an elusive goal. Current detectors deploy various alignment techniques to derive rotation-invariant features, but still rely on high capacity models and heavy data augmentation with all possible rotations. In this paper, we introduce a Fully Rotation-Equivariant Oriented Object Detector (FRED), whose entire process from the image to the bounding box prediction is strictly equivariant. Specifically, we decouple the invariant task (object classification) and the equivariant task (object localization) to achieve end-to-end equivariance. We represent the bounding box as a set of rotation-equivariant vectors to implement rotation-equivariant localization. Moreover, we utilized these rotation-equivariant vectors as offsets in the deformable convolution, thereby enhancing the existing advantages of spatial adaptation. Leveraging full rotation-equivariance, our FRED demonstrates higher robustness to image-level rotation compared to existing methods. Furthermore, we show that FRED is one step closer to non-axis aligned learning through our experiments. Compared to state-of-the-art methods, our proposed method delivers comparable performance on DOTA-v1.0 and outperforms by 1.5 mAP on DOTA-v1.5, all while significantly reducing the model parameters to 16%.
Authors: Chang Che, Qunwei Lin, Xinyu Zhao, Jiaxin Huang, Liqiang Yu
The process of transforming input images into corresponding textual explanations stands as a crucial and complex endeavor within the domains of computer vision and natural language processing. In this paper, we propose an innovative ensemble approach that harnesses the capabilities of Contrastive Language-Image Pretraining models.
Authors: Chloé Puget, Jonathan Ganz, Julian Ostermaier, Thomas Konrad, Eda Parlak, Christof Albert Bertram, Matti Kiupel, Katharina Breininger, Marc Aubreville, Robert Klopfleisch
Numerous prognostic factors are currently assessed histopathologically in biopsies of canine mast cell tumors to evaluate clinical behavior. In addition, PCR analysis of the c-Kit exon 11 mutational status is often performed to evaluate the potential success of a tyrosine kinase inhibitor therapy. This project aimed at training deep learning models (DLMs) to identify the c-Kit-11 mutational status of MCTs solely based on morphology without additional molecular analysis. HE slides of 195 mutated and 173 non-mutated tumors were stained consecutively in two different laboratories and scanned with three different slide scanners. This resulted in six different datasets (stain-scanner variations) of whole slide images. DLMs were trained with single and mixed datasets and their performances was assessed under scanner and staining domain shifts. The DLMs correctly classified HE slides according to their c-Kit 11 mutation status in, on average, 87% of cases for the best-suited stain-scanner variant. A relevant performance drop could be observed when the stain-scanner combination of the training and test dataset differed. Multi-variant datasets improved the average accuracy but did not reach the maximum accuracy of algorithms trained and tested on the same stain-scanner variant. In summary, DLM-assisted morphological examination of MCTs can predict c-Kit-exon 11 mutational status of MCTs with high accuracy. However, the recognition performance is impeded by a change of scanner or staining protocol. Larger data sets with higher numbers of scans originating from different laboratories and scanners may lead to more robust DLMs to identify c-Kit mutations in HE slides.
Authors: Baiyang Dai, Jiamin Yang, Hari Shroff, Patrick La Riviere
Determining cell identities in imaging sequences is an important yet challenging task. The conventional method for cell identification is via cell tracking, which is complex and can be time-consuming. In this study, we propose an innovative approach to cell identification during early C. elegans embryogenesis using machine learning. We employed random forest, MLP, and LSTM models, and tested cell classification accuracy on 3D time-lapse confocal datasets spanning the first 4 hours of embryogenesis. By leveraging a small number of spatial-temporal features of individual cells, including cell trajectory and cell fate information, our models achieve an accuracy of over 90%, even with limited data. We also determine the most important feature contributions and can interpret these features in the context of biological knowledge. Our research demonstrates the success of predicting cell identities in 4D imaging sequences directly from simple spatio-temporal features.
Authors: Jing Wu, Mehrtash Harandi
Machine unlearning has become a pivotal task to erase the influence of data from a trained model. It adheres to recent data regulation standards and enhances the privacy and security of machine learning applications. Most existing machine unlearning methods perform well, however, they typically necessitate access to the entirety of the remaining data, which might not be feasible in certain scenarios. In this work, we present a new machine unlearning approach Scissorhands, which operates effectively with only a subset of the training data. Initially, Scissorhands identifies the most pertinent parameters in the given model relative to the forgetting data via connection sensitivity. This process involves reinitializing the most influential top-$k$ percent of these parameters, resulting in a trimmed model for erasing the influence of the forgetting data. Subsequently, Scissorhands retrains the trimmed model through a min-max optimization process, seeking parameters that preserve information on the remaining data while discarding information related to the forgetting data. Our experimental results, conducted across five distinct datasets and utilizing both CNN and ViT, demonstrate that Scissorhands, despite utilizing only a limited portion of the training data, showcases competitive performance when compared to existing methods.
Authors: Rajaei Khatib, Raja Giryes
In recent years, the neural radiance field (NeRF) model has gained popularity due to its ability to recover complex 3D scenes. Following its success, many approaches proposed different NeRF representations in order to further improve both runtime and performance. One such example is Triplane, in which NeRF is represented using three 2D feature planes. This enables easily using existing 2D neural networks in this framework, e.g., to generate the three planes. Despite its advantage, the triplane representation lagged behind in its 3D recovery quality compared to NeRF solutions. In this work, we propose TriNeRFLet, a 2D wavelet-based multiscale triplane representation for NeRF, which closes the 3D recovery performance gap and is competitive with current state-of-the-art methods. Building upon the triplane framework, we also propose a novel super-resolution (SR) technique that combines a diffusion model with TriNeRFLet for improving NeRF resolution.
Authors: Yuwen Xiong, Zhiqi Li, Yuntao Chen, Feng Wang, Xizhou Zhu, Jiapeng Luo, Wenhai Wang, Tong Lu, Hongsheng Li, Yu Qiao, Lewei Lu, Jie Zhou, Jifeng Dai
We introduce Deformable Convolution v4 (DCNv4), a highly efficient and effective operator designed for a broad spectrum of vision applications. DCNv4 addresses the limitations of its predecessor, DCNv3, with two key enhancements: 1. removing softmax normalization in spatial aggregation to enhance its dynamic property and expressive power and 2. optimizing memory access to minimize redundant operations for speedup. These improvements result in a significantly faster convergence compared to DCNv3 and a substantial increase in processing speed, with DCNv4 achieving more than three times the forward speed. DCNv4 demonstrates exceptional performance across various tasks, including image classification, instance and semantic segmentation, and notably, image generation. When integrated into generative models like U-Net in the latent diffusion model, DCNv4 outperforms its baseline, underscoring its possibility to enhance generative models. In practical applications, replacing DCNv3 with DCNv4 in the InternImage model to create FlashInternImage results in up to 80% speed increase and further performance improvement without further modifications. The advancements in speed and efficiency of DCNv4, combined with its robust performance across diverse vision tasks, show its potential as a foundational building block for future vision models.
Authors: Shengbang Tong, Zhuang Liu, Yuexiang Zhai, Yi Ma, Yann LeCun, Saining Xie
Is vision good enough for language? Recent advancements in multimodal models primarily stem from the powerful reasoning abilities of large language models (LLMs). However, the visual component typically depends only on the instance-level contrastive language-image pre-training (CLIP). Our research reveals that the visual capabilities in recent multimodal LLMs (MLLMs) still exhibit systematic shortcomings. To understand the roots of these errors, we explore the gap between the visual embedding space of CLIP and vision-only self-supervised learning. We identify ''CLIP-blind pairs'' - images that CLIP perceives as similar despite their clear visual differences. With these pairs, we construct the Multimodal Visual Patterns (MMVP) benchmark. MMVP exposes areas where state-of-the-art systems, including GPT-4V, struggle with straightforward questions across nine basic visual patterns, often providing incorrect answers and hallucinated explanations. We further evaluate various CLIP-based vision-and-language models and found a notable correlation between visual patterns that challenge CLIP models and those problematic for multimodal LLMs. As an initial effort to address these issues, we propose a Mixture of Features (MoF) approach, demonstrating that integrating vision self-supervised learning features with MLLMs can significantly enhance their visual grounding capabilities. Together, our research suggests visual representation learning remains an open challenge, and accurate visual grounding is crucial for future successful multimodal systems.
Authors: Xinyuan Wang, Chengwei Pan, Hongming Dai, Gangming Zhao, Jinpeng Li, Xiao Zhang, Yizhou Yu
Coronary microvascular disease constitutes a substantial risk to human health. Employing computer-aided analysis and diagnostic systems, medical professionals can intervene early in disease progression, with 3D vessel segmentation serving as a crucial component. Nevertheless, conventional U-Net architectures tend to yield incoherent and imprecise segmentation outcomes, particularly for small vessel structures. While models with attention mechanisms, such as Transformers and large convolutional kernels, demonstrate superior performance, their extensive computational demands during training and inference lead to increased time complexity. In this study, we leverage Fourier domain learning as a substitute for multi-scale convolutional kernels in 3D hierarchical segmentation models, which can reduce computational expenses while preserving global receptive fields within the network. Furthermore, a zero-parameter frequency domain fusion method is designed to improve the skip connections in U-Net architecture. Experimental results on a public dataset and an in-house dataset indicate that our novel Fourier transformation-based network achieves remarkable dice performance (84.37\% on ASACA500 and 80.32\% on ImageCAS) in tubular vessel segmentation tasks and substantially reduces computational requirements without compromising global receptive fields.
Authors: Javad Khoramdel, Ahmad Moori, Yasamin Borhani, Armin Ghanbarzadeh, Esmaeil Najafi
The proposed YOLO-Former method seamlessly integrates the ideas of transformer and YOLOv4 to create a highly accurate and efficient object detection system. The method leverages the fast inference speed of YOLOv4 and incorporates the advantages of the transformer architecture through the integration of convolutional attention and transformer modules. The results demonstrate the effectiveness of the proposed approach, with a mean average precision (mAP) of 85.76\% on the Pascal VOC dataset, while maintaining high prediction speed with a frame rate of 10.85 frames per second. The contribution of this work lies in the demonstration of how the innovative combination of these two state-of-the-art techniques can lead to further improvements in the field of object detection.
Authors: Shaochun Li, Yanjun Wang, Hengfan Cai, Lina Deng, Yunhao Lin
Real-time and accurate information on fine-grained changes in crop cultivation is of great significance for crop growth monitoring, yield prediction and agricultural structure adjustment. Aiming at the problems of serious spectral confusion in visible high-resolution unmanned aerial vehicle (UAV) images of different phases, interference of large complex background and salt-and-pepper noise by existing semantic change detection (SCD) algorithms, in order to effectively extract deep image features of crops and meet the demand of agricultural practical engineering applications, this paper designs and proposes an agricultural geographic scene and parcel-scale constrained SCD framework for crops (AGSPNet). AGSPNet framework contains three parts: agricultural geographic scene (AGS) division module, parcel edge extraction module and crop SCD module. Meanwhile, we produce and introduce an UAV image SCD dataset (CSCD) dedicated to agricultural monitoring, encompassing multiple semantic variation types of crops in complex geographical scene. We conduct comparative experiments and accuracy evaluations in two test areas of this dataset, and the results show that the crop SCD results of AGSPNet consistently outperform other deep learning SCD models in terms of quantity and quality, with the evaluation metrics F1-score, kappa, OA, and mIoU obtaining improvements of 0.038, 0.021, 0.011 and 0.062, respectively, on average over the sub-optimal method. The method proposed in this paper can clearly detect the fine-grained change information of crop types in complex scenes, which can provide scientific and technical support for smart agriculture monitoring and management, food policy formulation and food security assurance.
Authors: Tejas Sudharshan Mathai, Bohan Liu, Ronald M. Summers
Purpose: Lymph nodes (LNs) in the chest have a tendency to enlarge due to various pathologies, such as lung cancer or pneumonia. Clinicians routinely measure nodal size to monitor disease progression, confirm metastatic cancer, and assess treatment response. However, variations in their shapes and appearances make it cumbersome to identify LNs, which reside outside of most organs. Methods: We propose to segment LNs in the mediastinum by leveraging the anatomical priors of 28 different structures (e.g., lung, trachea etc.) generated by the public TotalSegmentator tool. The CT volumes from 89 patients available in the public NIH CT Lymph Node dataset were used to train three 3D nnUNet models to segment LNs. The public St. Olavs dataset containing 15 patients (out-of-training-distribution) was used to evaluate the segmentation performance. Results: For the 15 test patients, the 3D cascade nnUNet model obtained the highest Dice score of 72.2 +- 22.3 for mediastinal LNs with short axis diameter $\geq$ 8mm and 54.8 +- 23.8 for all LNs respectively. These results represent an improvement of 10 points over a current approach that was evaluated on the same test dataset. Conclusion: To our knowledge, we are the first to harness 28 distinct anatomical priors to segment mediastinal LNs, and our work can be extended to other nodal zones in the body. The proposed method has immense potential for improved patient outcomes through the identification of enlarged nodes in initial staging CT scans.
Authors: Edward Sanderson, Bogdan J. Matuszewski
Solutions to vision tasks in gastrointestinal endoscopy (GIE) conventionally use image encoders pretrained in a supervised manner with ImageNet-1k as backbones. However, the use of modern self-supervised pretraining algorithms and a recent dataset of 100k unlabelled GIE images (Hyperkvasir-unlabelled) may allow for improvements. In this work, we study the fine-tuned performance of models with ResNet50 and ViT-B backbones pretrained in self-supervised and supervised manners with ImageNet-1k and Hyperkvasir-unlabelled (self-supervised only) in a range of GIE vision tasks. In addition to identifying the most suitable pretraining pipeline and backbone architecture for each task, out of those considered, our results suggest: that self-supervised pretraining generally produces more suitable backbones for GIE vision tasks than supervised pretraining; that self-supervised pretraining with ImageNet-1k is typically more suitable than pretraining with Hyperkvasir-unlabelled, with the notable exception of monocular depth estimation in colonoscopy; and that ViT-Bs are more suitable in polyp segmentation and monocular depth estimation in colonoscopy, ResNet50s are more suitable in polyp detection, and both architectures perform similarly in anatomical landmark recognition and pathological finding characterisation. We hope this work draws attention to the complexity of pretraining for GIE vision tasks, informs this development of more suitable approaches than the convention, and inspires further research on this topic to help advance this development. Code available: \underline{github.com/ESandML/SSL4GIE}
Authors: Fabio De Sousa Ribeiro, Ben Glocker
Despite the growing popularity of diffusion models, gaining a deep understanding of the model class remains somewhat elusive for the uninitiated in non-equilibrium statistical physics. With that in mind, we present what we believe is a more straightforward introduction to diffusion models using directed graphical modelling and variational Bayesian principles, which imposes relatively fewer prerequisites on the average reader. Our exposition constitutes a comprehensive technical review spanning from foundational concepts like deep latent variable models to recent advances in continuous-time diffusion-based modelling, highlighting theoretical connections between model classes along the way. We provide additional mathematical insights that were omitted in the seminal works whenever possible to aid in understanding, while avoiding the introduction of new notation. We envision this article serving as a useful educational supplement for both researchers and practitioners in the area, and we welcome feedback and contributions from the community at https://github.com/biomedia-mira/demystifying-diffusion.
Authors: Yukun Zuo, Hantao Yao, Liansheng Zhuang, Changsheng Xu
Audio-visual video recognition (AVVR) aims to integrate audio and visual clues to categorize videos accurately. While existing methods train AVVR models using provided datasets and achieve satisfactory results, they struggle to retain historical class knowledge when confronted with new classes in real-world situations. Currently, there are no dedicated methods for addressing this problem, so this paper concentrates on exploring Class Incremental Audio-Visual Video Recognition (CIAVVR). For CIAVVR, since both stored data and learned model of past classes contain historical knowledge, the core challenge is how to capture past data knowledge and past model knowledge to prevent catastrophic forgetting. We introduce Hierarchical Augmentation and Distillation (HAD), which comprises the Hierarchical Augmentation Module (HAM) and Hierarchical Distillation Module (HDM) to efficiently utilize the hierarchical structure of data and models, respectively. Specifically, HAM implements a novel augmentation strategy, segmental feature augmentation, to preserve hierarchical model knowledge. Meanwhile, HDM introduces newly designed hierarchical (video-distribution) logical distillation and hierarchical (snippet-video) correlative distillation to capture and maintain the hierarchical intra-sample knowledge of each data and the hierarchical inter-sample knowledge between data, respectively. Evaluations on four benchmarks (AVE, AVK-100, AVK-200, and AVK-400) demonstrate that the proposed HAD effectively captures hierarchical information in both data and models, resulting in better preservation of historical class knowledge and improved performance. Furthermore, we provide a theoretical analysis to support the necessity of the segmental feature augmentation strategy.
Authors: John Kalkhof, Arlene Kühn, Yannik Frisch, Anirban Mukhopadhyay
Denoising Diffusion Models (DDMs) have become the leading generative technique for synthesizing high-quality images but are often constrained by their UNet-based architectures that impose certain limitations. In particular, the considerable size of often hundreds of millions of parameters makes them impractical when hardware resources are limited. However, even with powerful hardware, processing images in the gigapixel range is difficult. This is especially true in fields such as microscopy or satellite imaging, where such challenges arise from the limitation to a predefined generative size and the inefficient scaling to larger images. We present two variations of Neural Cellular Automata (NCA)-based DDM methods to address these challenges and jumpstart NCA-based DDMs: Diff-NCA and FourierDiff-NCA. Diff-NCA performs diffusion by using only local features of the underlying distribution, making it suitable for applications where local features are critical. To communicate global knowledge in image space, naive NCA setups require timesteps that increase with the image scale. We solve this bottleneck of current NCA architectures by introducing FourierDiff-NCA, which advances Diff-NCA by adding a Fourier-based diffusion process and combines the frequency-organized Fourier space with the image space. By initiating diffusion in the Fourier domain and finalizing it in the image space, FourierDiff-NCA accelerates global communication. We validate our techniques by using Diff-NCA (208k parameters) to generate high-resolution digital pathology scans at 576x576 resolution and FourierDiff-NCA (887k parameters) to synthesize CelebA images at 64x64, outperforming VNCA and five times bigger UNet-based DDMs. In addition, we demonstrate FourierDiff-NCA's capabilities in super-resolution, OOD image synthesis, and inpainting without additional training.
Authors: Akshita Jha, Vinodkumar Prabhakaran, Remi Denton, Sarah Laszlo, Shachi Dave, Rida Qadri, Chandan K. Reddy, Sunipa Dev
Recent studies have highlighted the issue of stereotypical depictions for people of different identity groups in Text-to-Image (T2I) model generations. However, these existing approaches have several key limitations, including a noticeable lack of coverage of global identity groups in their evaluation, and the range of their associated stereotypes. Additionally, they often lack a critical distinction between inherently visual stereotypes, such as `underweight' or `sombrero', and culturally dependent stereotypes like `attractive' or `terrorist'. In this work, we address these limitations with a multifaceted approach that leverages existing textual resources to ground our evaluation of geo-cultural stereotypes in the generated images from T2I models. We employ existing stereotype benchmarks to identify and evaluate visual stereotypes at a global scale, spanning 135 nationality-based identity groups. We demonstrate that stereotypical attributes are thrice as likely to be present in images of these identities as compared to other attributes. We further investigate how disparately offensive the depictions of generated images are for different nationalities. Finally, through a detailed case study, we reveal how the 'default' representations of all identity groups have a stereotypical appearance. Moreover, for the Global South, images across different attributes are visually similar, even when explicitly prompted otherwise. CONTENT WARNING: Some examples may contain offensive stereotypes.
Authors: Xingyu Zhou, Leheng Zhang, Xiaorui Zhao, Keze Wang, Leida Li, Shuhang Gu
Recently, Vision Transformer has achieved great success in recovering missing details in low-resolution sequences, i.e., the video super-resolution (VSR) task.Despite its superiority in VSR accuracy, the heavy computational burden as well as the large memory footprint hinder the deployment of Transformer-based VSR models on constrained devices.In this paper, we address the above issue by proposing a novel feature-level masked processing framework: VSR with Masked Intra and inter frame Attention (MIA-VSR).The core of MIA-VSR is leveraging feature-level temporal continuity between adjacent frames to reduce redundant computations and make more rational use of previously enhanced SR features. Concretely, we propose an intra-frame and inter-frame attention block which takes the respective roles of past features and input features into consideration and only exploits previously enhanced features to provide supplementary information. In addition, an adaptive block-wise mask prediction module is developed to skip unimportant computations according to feature similarity between adjacent frames. We conduct detailed ablation studies to validate our contributions and compare the proposed method with recent state-of-the-art VSR approaches. The experimental results demonstrate that MIA-VSR improves the memory and computation efficiency over state-of-the-art methods, without trading off PSNR accuracy. The code is available at https://github.com/LabShuHangGU/MIA-VSR.
Authors: Banafshe Felfeliyan, Yuyue Zhou, Shrimanti Ghosh, Jessica Kupper, Shaobo Liu, Abhilash Hareendranathan, Jacob L. Jaremko
Osteoarthritis (OA) poses a global health challenge, demanding precise diagnostic methods. Current radiographic assessments are time consuming and prone to variability, prompting the need for automated solutions. The existing deep learning models for OA assessment are unimodal single task systems and they don't incorporate relevant text information such as patient demographics, disease history, or physician reports. This study investigates employing Vision Language Processing (VLP) models to predict OA severity using Xray images and corresponding reports. Our method leverages Xray images of the knee and diverse report templates generated from tabular OA scoring values to train a CLIP (Contrastive Language Image PreTraining) style VLP model. Furthermore, we incorporate additional contrasting captions to enforce the model to discriminate between positive and negative reports. Results demonstrate the efficacy of these models in learning text image representations and their contextual relationships, showcase potential advancement in OA assessment, and establish a foundation for specialized vision language models in medical contexts.
Authors: Shengyi Qian, Weifeng Chen, Min Bai, Xiong Zhou, Zhuowen Tu, Li Erran Li
Affordance grounding refers to the task of finding the area of an object with which one can interact. It is a fundamental but challenging task, as a successful solution requires the comprehensive understanding of a scene in multiple aspects including detection, localization, and recognition of objects with their parts, of geo-spatial configuration/layout of the scene, of 3D shapes and physics, as well as of the functionality and potential interaction of the objects and humans. Much of the knowledge is hidden and beyond the image content with the supervised labels from a limited training set. In this paper, we make an attempt to improve the generalization capability of the current affordance grounding by taking the advantage of the rich world, abstract, and human-object-interaction knowledge from pretrained large-scale vision language models. Under the AGD20K benchmark, our proposed model demonstrates a significant performance gain over the competing methods for in-the-wild object affordance grounding. We further demonstrate it can ground affordance for objects from random Internet images, even if both objects and actions are unseen during training. Project site: https://jasonqsy.github.io/AffordanceLLM/
Authors: Weizheng Wang, Le Mao, Baijian Yang, Guohua Chen, Byung-Cheol Min
Predicting crowded intents and trajectories is crucial in varouls real-world applications, including service robots and autonomous vehicles. Understanding environmental dynamics is challenging, not only due to the complexities of modeling pair-wise spatial and temporal interactions but also the diverse influence of group-wise interactions. To decode the comprehensive pair-wise and group-wise interactions in crowded scenarios, we introduce Hyper-STTN, a Hypergraph-based Spatial-Temporal Transformer Network for crowd trajectory prediction. In Hyper-STTN, crowded group-wise correlations are constructed using a set of multi-scale hypergraphs with varying group sizes, captured through random-walk robability-based hypergraph spectral convolution. Additionally, a spatial-temporal transformer is adapted to capture pedestrians' pair-wise latent interactions in spatial-temporal dimensions. These heterogeneous group-wise and pair-wise are then fused and aligned though a multimodal transformer network. Hyper-STTN outperformes other state-of-the-art baselines and ablation models on 5 real-world pedestrian motion datasets.
Authors: Chang Yu, Junran Peng, Xiangyu Zhu, Zhaoxiang Zhang, Qi Tian, Zhen Lei
The text-to-image synthesis by diffusion models has recently shown remarkable performance in generating high-quality images. Although performs well for simple texts, the models may get confused when faced with complex texts that contain multiple objects or spatial relationships. To get the desired images, a feasible way is to manually adjust the textual descriptions, i.e., narrating the texts or adding some words, which is labor-consuming. In this paper, we propose a framework to learn the proper textual descriptions for diffusion models through prompt learning. By utilizing the quality guidance and the semantic guidance derived from the pre-trained diffusion model, our method can effectively learn the prompts to improve the matches between the input text and the generated images. Extensive experiments and analyses have validated the effectiveness of the proposed method.
Authors: Yifeng Wang, Ke Chen, Yihan Zhang, Haohan Wang
Automated diagnosis of AD in brain images is becoming a clinically important technique to support precision and efficient diagnosis and treatment planning. A few efforts have been made to automatically diagnose AD in magnetic resonance imaging (MRI) using three-dimensional CNNs. However, due to the complexity of 3D models, the performance is still unsatisfactory, both in terms of accuracy and efficiency. To overcome the complexities of 3D images and 3D models, in this study, we aim to attack this problem with 2D vision Transformers. We propose a 2D transformer-based medical image model with various transformer attention encoders to diagnose AD in 3D MRI images, by cutting the 3D images into multiple 2D slices.The model consists of four main components: shared encoders across three dimensions, dimension-specific encoders, attention across images from the same dimension, and attention across three dimensions. It is used to obtain attention relationships among multiple sequences from different dimensions (axial, coronal, and sagittal) and multiple slices. We also propose morphology augmentation, an erosion and dilation based method to increase the structural difference between AD and normal images. In this experiment, we use multiple datasets from ADNI, AIBL, MIRAID, OASIS to show the performance of our model. Our proposed MedTransformer demonstrates a strong ability in diagnosing AD. These results demonstrate the effectiveness of MedTransformer in learning from 3D data using a much smaller model and its capability to generalize among different medical tasks, which provides a possibility to help doctors diagnose AD in a simpler way.
Authors: Xiaoyu Liu, Yueyi Zhang, Zhiwei Xiong, Wei Huang, Bo Hu, Xiaoyan Sun, Feng Wu
Instance-aware embeddings predicted by deep neural networks have revolutionized biomedical instance segmentation, but its resource requirements are substantial. Knowledge distillation offers a solution by transferring distilled knowledge from heavy teacher networks to lightweight yet high-performance student networks. However, existing knowledge distillation methods struggle to extract knowledge for distinguishing instances and overlook global relation information. To address these challenges, we propose a graph relation distillation approach for efficient biomedical instance segmentation, which considers three essential types of knowledge: instance-level features, instance relations, and pixel-level boundaries. We introduce two graph distillation schemes deployed at both the intra-image level and the inter-image level: instance graph distillation (IGD) and affinity graph distillation (AGD). IGD constructs a graph representing instance features and relations, transferring these two types of knowledge by enforcing instance graph consistency. AGD constructs an affinity graph representing pixel relations to capture structured knowledge of instance boundaries, transferring boundary-related knowledge by ensuring pixel affinity consistency. Experimental results on a number of biomedical datasets validate the effectiveness of our approach, enabling student models with less than $ 1\%$ parameters and less than $10\%$ inference time while achieving promising performance compared to teacher models.
Authors: Haoxuan Ding, Junyu Gao, Yuan Yuan, Qi Wang
With the emergence of foundation model, this novel paradigm of deep learning has encouraged many powerful achievements in natural language processing and computer vision. There are many advantages of foundation model, such as excellent feature extraction power, mighty generalization ability, great few-shot and zero-shot learning capacity, etc. which are beneficial to vision tasks. As the unique identity of vehicle, different countries and regions have diverse license plate (LP) styles and appearances, and even different types of vehicles have different LPs. However, recent deep learning based license plate detectors are mainly trained on specific datasets, and these limited datasets constrain the effectiveness and robustness of LP detectors. To alleviate the negative impact of limited data, an attempt to exploit the advantages of foundation model is implement in this paper. We customize a vision foundation model, i.e. Segment Anything Model (SAM), for LP detection task and propose the first LP detector based on vision foundation model, named SamLP. Specifically, we design a Low-Rank Adaptation (LoRA) fine-tuning strategy to inject extra parameters into SAM and transfer SAM into LP detection task. And then, we further propose a promptable fine-tuning step to provide SamLP with prompatable segmentation capacity. The experiments show that our proposed SamLP achieves promising detection performance compared to other LP detectors. Meanwhile, the proposed SamLP has great few-shot and zero-shot learning ability, which shows the potential of transferring vision foundation model. The code is available at https://github.com/Dinghaoxuan/SamLP
Authors: Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang, Zhaoqi Wang
In this paper, we introduce Segmentation-Driven Deformation Multi-View Stereo (SD-MVS), a method that can effectively tackle challenges in 3D reconstruction of textureless areas. We are the first to adopt the Segment Anything Model (SAM) to distinguish semantic instances in scenes and further leverage these constraints for pixelwise patch deformation on both matching cost and propagation. Concurrently, we propose a unique refinement strategy that combines spherical coordinates and gradient descent on normals and pixelwise search interval on depths, significantly improving the completeness of reconstructed 3D model. Furthermore, we adopt the Expectation-Maximization (EM) algorithm to alternately optimize the aggregate matching cost and hyperparameters, effectively mitigating the problem of parameters being excessively dependent on empirical tuning. Evaluations on the ETH3D high-resolution multi-view stereo benchmark and the Tanks and Temples dataset demonstrate that our method can achieve state-of-the-art results with less time consumption.
Authors: Xinyu Wang, Bohan Zhuang, Qi Wu
Humans possess the capability to comprehend diverse modalities and seamlessly transfer information between them. In this work, we introduce ModaVerse, a Multi-modal Large Language Model (MLLM) capable of comprehending and transforming content across various modalities including images, videos, and audio. Predominant MLLM frameworks have largely relied on the alignment of latent spaces of textual and non-textual features. This alignment process, which synchronizes a language model trained on textual data with encoders and decoders trained on multi-modal data, often necessitates extensive training of several projection layers in multiple stages. Inspired by LLM-as-agent methodologies, we propose a novel Input/Output (I/O) alignment mechanism that operates directly at the level of natural language. It aligns the LLM's output with the input of generative models, avoiding the complexities associated with latent feature alignments, and simplifying the multiple training stages of existing MLLMs into a single, efficient process. This conceptual advancement leads to significant reductions in both data and computational costs. By conducting experiments on several benchmarks, we demonstrate that our approach attains comparable performance with the state of the art while achieving considerable efficiencies in data usage and training duration.
Authors: Bowen Shi, Peisen Zhao, Zichen Wang, Yuhang Zhang, Yaoming Wang, Jin Li, Wenrui Dai, Junni Zou, Hongkai Xiong, Qi Tian, Xiaopeng Zhang
Vision-language foundation models, represented by Contrastive language-image pre-training (CLIP), have gained increasing attention for jointly understanding both vision and textual tasks. However, existing approaches primarily focus on training models to match global image representations with textual descriptions, thereby overlooking the critical alignment between local regions and corresponding text tokens. This paper extends CLIP with multi-granularity alignment. Notably, we deliberately construct a new dataset comprising pseudo annotations at various levels of granularities, encompassing image-level, region-level, and pixel-level captions/tags. Accordingly, we develop a unified multi-granularity learning framework, named UMG-CLIP, that simultaneously empowers the model with versatile perception abilities across different levels of detail. Equipped with parameter efficient tuning, UMG-CLIP surpasses current widely used CLIP models and achieves state-of-the-art performance on diverse image understanding benchmarks, including open-world recognition, retrieval, semantic segmentation, and panoptic segmentation tasks. We hope UMG-CLIP can serve as a valuable option for advancing vision-language foundation models.
Authors: Taehee Kim, Yeongjae Cho, Heejun Shin, Yohan Jo, Dongmyung Shin
Visual question answering (VQA) is a task where an image is given, and a series of questions are asked about the image. To build an efficient VQA algorithm, a large amount of QA data is required which is very expensive. Generating synthetic QA pairs based on templates is a practical way to obtain data. However, VQA models trained on those data do not perform well on complex, human-written questions. To address this issue, we propose a new method called {\it chain of QA for human-written questions} (CoQAH). CoQAH utilizes a sequence of QA interactions between a large language model and a VQA model trained on synthetic data to reason and derive logical answers for human-written questions. We tested the effectiveness of CoQAH on two types of human-written VQA datasets for 3D-rendered and chest X-ray images and found that it achieved state-of-the-art accuracy in both types of data. Notably, CoQAH outperformed general vision-language models, VQA models, and medical foundation models with no finetuning.
Authors: Jincheng Zhang, Artur Wolek, Andrew R. Willis
This article presents a comprehensive review of and analysis of state-of-the-art mapping algorithms for UAV (Unmanned Aerial Vehicle) applications, focusing on canopy-level and high-speed scenarios. This article presents a comprehensive exploration of sensor technologies suitable for UAV mapping, assessing their capabilities to provide measurements that meet the requirements of fast UAV mapping. Furthermore, the study conducts extensive experiments in a simulated environment to evaluate the performance of three distinct mapping algorithms: Direct Sparse Odometry (DSO), Stereo DSO (SDSO), and DSO Lite (DSOL). The experiments delve into mapping accuracy and mapping speed, providing valuable insights into the strengths and limitations of each algorithm. The results highlight the versatility and shortcomings of these algorithms in meeting the demands of modern UAV applications. The findings contribute to a nuanced understanding of UAV mapping dynamics, emphasizing their applicability in complex environments and high-speed scenarios. This research not only serves as a benchmark for mapping algorithm comparisons but also offers practical guidance for selecting sensors tailored to specific UAV mapping applications.
Authors: Junuk Cha, Hansol Lee, Jaewon Kim, Nhat Nguyen Bao Truong, Jae Shin Yoon, Seungryul Baek
This paper introduces a novel pipeline to reconstruct the geometry of interacting multi-person in clothing on a globally coherent scene space from a single image. The main challenge arises from the occlusion: a part of a human body is not visible from a single view due to the occlusion by others or the self, which introduces missing geometry and physical implausibility (e.g., penetration). We overcome this challenge by utilizing two human priors for complete 3D geometry and surface contacts. For the geometry prior, an encoder learns to regress the image of a person with missing body parts to the latent vectors; a decoder decodes these vectors to produce 3D features of the associated geometry; and an implicit network combines these features with a surface normal map to reconstruct a complete and detailed 3D humans. For the contact prior, we develop an image-space contact detector that outputs a probability distribution of surface contacts between people in 3D. We use these priors to globally refine the body poses, enabling the penetration-free and accurate reconstruction of interacting multi-person in clothing on the scene space. The results demonstrate that our method is complete, globally coherent, and physically plausible compared to existing methods.
Authors: Ji Liu, Dehua Tang, Yuanxian Huang, Li Zhang, Xiaocheng Zeng, Dong Li, Mingjie Lu, Jinzhang Peng, Yu Wang, Fan Jiang, Lu Tian, Ashish Sirasao
Traditional channel-wise pruning methods by reducing network channels struggle to effectively prune efficient CNN models with depth-wise convolutional layers and certain efficient modules, such as popular inverted residual blocks. Prior depth pruning methods by reducing network depths are not suitable for pruning some efficient models due to the existence of some normalization layers. Moreover, finetuning subnet by directly removing activation layers would corrupt the original model weights, hindering the pruned model from achieving high performance. To address these issues, we propose a novel depth pruning method for efficient models. Our approach proposes a novel block pruning strategy and progressive training method for the subnet. Additionally, we extend our pruning method to vision transformer models. Experimental results demonstrate that our method consistently outperforms existing depth pruning methods across various pruning configurations. We obtained three pruned ConvNeXtV1 models with our method applying on ConvNeXtV1, which surpass most SOTA efficient models with comparable inference performance. Our method also achieves state-of-the-art pruning performance on the vision transformer model.
Authors: Huiyuan Fu, Kuilong Cui, Chuanming Wang, Mengshi Qi, Huadong Ma
With the rapid advancements in deep learning technologies, person re-identification (ReID) has witnessed remarkable performance improvements. However, the majority of prior works have traditionally focused on solving the problem via extracting features solely from a single perspective, such as uniform partitioning, hard attention mechanisms, or semantic masks. While these approaches have demonstrated efficacy within specific contexts, they fall short in diverse situations. In this paper, we propose a novel approach, Mutual Distillation Learning For Person Re-identification (termed as MDPR), which addresses the challenging problem from multiple perspectives within a single unified model, leveraging the power of mutual distillation to enhance the feature representations collectively. Specifically, our approach encompasses two branches: a hard content branch to extract local features via a uniform horizontal partitioning strategy and a Soft Content Branch to dynamically distinguish between foreground and background and facilitate the extraction of multi-granularity features via a carefully designed attention mechanism. To facilitate knowledge exchange between these two branches, a mutual distillation and fusion process is employed, promoting the capability of the outputs of each branch. Extensive experiments are conducted on widely used person ReID datasets to validate the effectiveness and superiority of our approach. Notably, our method achieves an impressive $88.7\%/94.4\%$ in mAP/Rank-1 on the DukeMTMC-reID dataset, surpassing the current state-of-the-art results. Our source code is available at https://github.com/KuilongCui/MDPR.
Authors: Seitaro Ono, Yuka Ogino, Takahiro Toizumi, Atsushi Ito, Masato Tsukada
In recent years, significant progress has been made in image recognition technology based on deep neural networks. However, improving recognition performance under low-light conditions remains a significant challenge. This study addresses the enhancement of recognition model performance in low-light conditions. We propose an image-adaptive learnable module which apply appropriate image processing on input images and a hyperparameter predictor to forecast optimal parameters used in the module. Our proposed approach allows for the enhancement of recognition performance under low-light conditions by easily integrating as a front-end filter without the need to retrain existing recognition models designed for low-light conditions. Through experiments, our proposed method demonstrates its contribution to enhancing image recognition performance under low-light conditions.
Authors: Minxing Luo, Wentao Cheng, Jian Yang
A precise and user-friendly manipulation of image content while preserving image fidelity has always been crucial to the field of image editing. Thanks to the power of generative models, recent point-based image editing methods allow users to interactively change the image content with high generalizability by clicking several control points. But the above mentioned editing process is usually based on the assumption that features stay constant in the motion supervision step from initial to target points. In this work, we conduct a comprehensive investigation in the feature space of diffusion models, and find that features change acutely under in-plane rotation. Based on this, we propose a novel approach named RotationDrag, which significantly improves point-based image editing performance when users intend to in-plane rotate the image content. Our method tracks handle points more precisely by utilizing the feature map of the rotated images, thus ensuring precise optimization and high image fidelity. Furthermore, we build a in-plane rotation focused benchmark called RotateBench, the first benchmark to evaluate the performance of point-based image editing method under in-plane rotation scenario on both real images and generated images. A thorough user study demonstrates the superior capability in accomplishing in-plane rotation that users intend to achieve, comparing the DragDiffusion baseline and other existing diffusion-based methods. See the project page https://github.com/Tony-Lowe/RotationDrag for code and experiment results.
Authors: Xiwei Xuan, Jorge Piazentin Ono, Liang Gou, Kwan-Liu Ma, Liu Ren
Data slice-finding is an emerging technique for evaluating machine learning models. It works by identifying subgroups within a specified dataset that exhibit poor performance, often defined by distinct feature sets or meta-information. However, in the context of unstructured image data, data slice-finding poses two notable challenges: it requires additional metadata -- a laborious and costly requirement, and also demands non-trivial efforts for interpreting the root causes of the underperformance within data slices. To address these challenges, we introduce AttributionScanner, an innovative human-in-the-loop Visual Analytics (VA) system, designed for data-slicing-based machine learning (ML) model validation. Our approach excels in identifying interpretable data slices, employing explainable features extracted through the lens of Explainable AI (XAI) techniques, and removing the necessity for additional metadata of textual annotations or cross-model embeddings. AttributionScanner demonstrates proficiency in pinpointing critical model issues, including spurious correlations and mislabeled data. Our novel VA interface visually summarizes data slices, enabling users to gather insights into model behavior patterns effortlessly. Furthermore, our framework closes the ML Development Cycle by empowering domain experts to address model issues by using a cutting-edge neural network regularization technique. The efficacy of AttributionScanner is underscored through two prototype use cases, elucidating its substantial effectiveness in model validation for vision-centric tasks. Our approach paves the way for ML researchers and practitioners to drive interpretable model validation in a data-efficient way, ultimately leading to more reliable and accurate models.
Authors: Eytan Kats, Jochen G. Hirsch, Mattias P. Heinrich
This paper demonstrates a self-supervised framework for learning voxel-wise coarse-to-fine representations tailored for dense downstream tasks. Our approach stems from the observation that existing methods for hierarchical representation learning tend to prioritize global features over local features due to inherent architectural bias. To address this challenge, we devise a training strategy that balances the contributions of features from multiple scales, ensuring that the learned representations capture both coarse and fine-grained details. Our strategy incorporates 3-fold improvements: (1) local data augmentations, (2) a hierarchically balanced architecture, and (3) a hybrid contrastive-restorative loss function. We evaluate our method on CT and MRI data and demonstrate that our new approach particularly beneficial for fine-tuning with limited annotated data and consistently outperforms the baseline counterpart in linear evaluation settings.
Authors: Sumit Pandey, Satyasaran Changdar, Mathias Perslev, Erik B Dam
Automated segmentation of distinct tumor regions is critical for accurate diagnosis and treatment planning in pediatric brain tumors. This study evaluates the efficacy of the Multi-Planner U-Net (MPUnet) approach in segmenting different tumor subregions across three challenging datasets: Pediatrics Tumor Challenge (PED), Brain Metastasis Challenge (MET), and Sub-Sahara-Africa Adult Glioma (SSA). These datasets represent diverse scenarios and anatomical variations, making them suitable for assessing the robustness and generalization capabilities of the MPUnet model. By utilizing multi-planar information, the MPUnet architecture aims to enhance segmentation accuracy. Our results show varying performance levels across the evaluated challenges, with the tumor core (TC) class demonstrating relatively higher segmentation accuracy. However, variability is observed in the segmentation of other classes, such as the edema and enhancing tumor (ET) regions. These findings emphasize the complexity of brain tumor segmentation and highlight the potential for further refinement of the MPUnet approach and inclusion of MRI more data and preprocessing.
Authors: Chandler Timm C. Doloriel, Rhandley D. Cajote
Small oriented objects that represent tiny pixel-area in large-scale aerial images are difficult to detect due to their size and orientation. Existing oriented aerial detectors have shown promising results but are mainly focused on orientation modeling with less regard to the size of the objects. In this work, we proposed a method to accurately detect small oriented objects in aerial images by enhancing the classification and regression tasks of the oriented object detection model. We designed the Attention-Points Network consisting of two losses: Guided-Attention Loss (GALoss) and Box-Points Loss (BPLoss). GALoss uses an instance segmentation mask as ground-truth to learn the attention features needed to improve the detection of small objects. These attention features are then used to predict box points for BPLoss, which determines the points' position relative to the target oriented bounding box. Experimental results show the effectiveness of our Attention-Points Network on a standard oriented aerial dataset with small object instances (DOTA-v1.5) and on a maritime-related dataset (HRSC2016). The code is publicly available.
Authors: Chandler Timm Doloriel, Ngai-Man Cheung
We study universal deepfake detection. Our goal is to detect synthetic images from a range of generative AI approaches, particularly from emerging ones which are unseen during training of the deepfake detector. Universal deepfake detection requires outstanding generalization capability. Motivated by recently proposed masked image modeling which has demonstrated excellent generalization in self-supervised pre-training, we make the first attempt to explore masked image modeling for universal deepfake detection. We study spatial and frequency domain masking in training deepfake detectors. Based on empirical analysis, we propose a novel deepfake detector via frequency masking. Our focus on frequency domain is different from the majority, which primarily target spatial domain detection. Our comparative analyses reveal substantial performance gains over existing methods. Code and models are publicly available.
Authors: Yu Wang, Junxian Mu, Pengfei Zhu, Qinghua Hu
Open set recognition (OSR) requires the model to classify samples that belong to closed sets while rejecting unknown samples during test. Currently, generative models often perform better than discriminative models in OSR, but recent studies show that generative models may be computationally infeasible or unstable on complex tasks. In this paper, we provide insights into OSR and find that learning supplementary representations can theoretically reduce the open space risk. Based on the analysis, we propose a new model, namely Multi-Expert Diverse Attention Fusion (MEDAF), that learns diverse representations in a discriminative way. MEDAF consists of multiple experts that are learned with an attention diversity regularization term to ensure the attention maps are mutually different. The logits learned by each expert are adaptively fused and used to identify the unknowns through the score function. We show that the differences in attention maps can lead to diverse representations so that the fused representations can well handle the open space. Extensive experiments are conducted on standard and OSR large-scale benchmarks. Results show that the proposed discriminative method can outperform existing generative models by up to 9.5% on AUROC and achieve new state-of-the-art performance with little computational cost. Our method can also seamlessly integrate existing classification models. Code is available at https://github.com/Vanixxz/MEDAF.
Authors: Elias Arbash, Margret Fuchs, Behnood Rasti, Sandra Lorenz, Pedram Ghamisi, Richard Gloaguen
Addressing the critical theme of recycling electronic waste (E-waste), this contribution is dedicated to developing advanced automated data processing pipelines as a basis for decision-making and process control. Aligning with the broader goals of the circular economy and the United Nations (UN) Sustainable Development Goals (SDG), our work leverages non-invasive analysis methods utilizing RGB and hyperspectral imaging data to provide both quantitative and qualitative insights into the E-waste stream composition for optimizing recycling efficiency. In this paper, we introduce 'PCB-Vision'; a pioneering RGB-hyperspectral printed circuit board (PCB) benchmark dataset, comprising 53 RGB images of high spatial resolution paired with their corresponding high spectral resolution hyperspectral data cubes in the visible and near-infrared (VNIR) range. Grounded in open science principles, our dataset provides a comprehensive resource for researchers through high-quality ground truths, focusing on three primary PCB components: integrated circuits (IC), capacitors, and connectors. We provide extensive statistical investigations on the proposed dataset together with the performance of several state-of-the-art (SOTA) models, including U-Net, Attention U-Net, Residual U-Net, LinkNet, and DeepLabv3+. By openly sharing this multi-scene benchmark dataset along with the baseline codes, we hope to foster transparent, traceable, and comparable developments of advanced data processing across various scientific communities, including, but not limited to, computer vision and remote sensing. Emphasizing our commitment to supporting a collaborative and inclusive scientific community, all materials, including code, data, ground truth, and masks, will be accessible at https://github.com/hifexplo/PCBVision.
Authors: Ziying Song, Lin Liu, Feiyang Jia, Yadan Luo, Guoxin Zhang, Lei Yang, Li Wang, Caiyan Jia
In the realm of modern autonomous driving, the perception system is indispensable for accurately assessing the state of the surrounding environment, thereby enabling informed prediction and planning. Key to this system is 3D object detection methods, that utilize vehicle-mounted sensors such as LiDAR and cameras to identify the size, category, and location of nearby objects. Despite the surge in 3D object detection methods aimed at enhancing detection precision and efficiency, there is a gap in the literature that systematically examines their resilience against environmental variations, noise, and weather changes. This study emphasizes the importance of robustness, alongside accuracy and latency, in evaluating perception systems under practical scenarios. Our work presents an extensive survey of camera-based, LiDAR-based, and multimodal 3D object detection algorithms, thoroughly evaluating their trade-off between accuracy, latency, and robustness, particularly on datasets like KITTI-C and nuScenes-C to ensure fair comparisons. Among these,multimodal 3D detection approaches exhibit superior robustness and a novel taxonomy is introduced to reorganize its literature for enhanced clarity. This survey aims to offer a more practical perspective on the current capabilities and constraints of 3D object detection algorithms in real-world applications, thus steering future research towards robustness-centric advancements
Authors: Vandad Imani, Elaheh Moradi, Carlos Sevilla-Salcedo, Vittorio Fortino, Jussi Tohka
Feature selection in noisy label scenarios remains an understudied topic. We propose a novel genetic algorithm-based approach, the Noise-Aware Multi-Objective Feature Selection Genetic Algorithm (NMFS-GA), for selecting optimal feature subsets in binary classification with noisy labels. NMFS-GA offers a unified framework for selecting feature subsets that are both accurate and interpretable. We evaluate NMFS-GA on synthetic datasets with label noise, a Breast Cancer dataset enriched with noisy features, and a real-world ADNI dataset for dementia conversion prediction. Our results indicate that NMFS-GA can effectively select feature subsets that improve the accuracy and interpretability of binary classifiers in scenarios with noisy labels.
Authors: Chenyang Wang, Junjun Jiang, Xingyu Hu, Xianming Liu, Xiangyang Ji
Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks, where old data from experienced tasks is unavailable when learning from a new task. To mitigate the problem, a line of methods propose to replay the data of experienced tasks when learning new tasks. These methods usually adopt an extra memory to store the data for replay. However, it is not expected in practice considering the memory constraint or data privacy issue. As a replacement, data-free data replay methods are proposed by inverting samples from the classification model. Though achieving good results, these methods still suffer from the inconsistency of the inverted and real training data, which is neglected in the inversion stage in recent works. To that effect, we propose to measure the data consistency quantitatively by some simplification and assumptions. Using the measurement, we analyze existing techniques for inverting samples and get some insightful information that inspires a novel loss function to reduce the inconsistency. Specifically, the loss minimizes the KL divergence of the distributions of inverted and real data under the tied multivariate Gaussian assumption, which is easy to implement in continual learning. In addition, we observe that the norms of old class weights turn to decrease continually as learning progresses. We thus analyze the underlying reasons and propose a simple regularization term to balance the class weights so that the samples of old classes are more distinguishable. To conclude, we propose the Consistency enhanced data replay with debiased classifier for Class Incremental Learning (CCIL). Extensive experiments on CIFAR-100, Tiny-ImageNet, and ImageNet100 show consistently improved performance of CCIL compared to previous approaches.
Authors: Chuanji Shi, Yingying Zhang, Jiaotuan Wang, Qiqi Zhu
Urban area-of-interest (AOI) refers to an integrated urban functional zone with defined boundaries. The rapid development of urban commerce has resulted in an increased demand for more precise requirements in defining AOIs. However, existing research primarily concentrates on broad AOI mining for urban planning or regional economic analysis, failing to cater to the precise requirements of mobile Internet online-to-offline businesses. These businesses necessitate accuracy down to a specific community, school, or hospital. In this paper, we propose an end-to-end multimodal deep learning algorithm for detecting AOI fence polygon using remote sensing images and multi-semantics reference information. We then evaluate its timeliness through a cascaded module that incorporates dynamic human mobility and logistics address information. Specifically, we begin by selecting a point-of-interest (POI) of specific category, and use it to recall corresponding remote sensing images, nearby POIs, road nodes, human mobility, and logistics addresses to build a multimodal detection model based on transformer encoder-decoder architecture, titled AOITR. In the model, in addition to the remote sensing images, multi-semantic information including core POI and road nodes is embedded and reorganized as the query content part for the transformer decoder to generate the AOI polygon. Meanwhile, relatively dynamic distribution features of human mobility, nearby POIs, and logistics addresses are used for AOI reliability evaluation through a cascaded feedforward network. The experimental results demonstrate that our algorithm significantly outperforms two existing methods.
Authors: Ali Safa, Wout Mommen, Lars Keuninckx
This work proposes a novel approach for hand gesture recognition using an inexpensive, low-resolution (24 x 32) thermal sensor processed by a Spiking Neural Network (SNN) followed by Sparse Segmentation and feature-based gesture classification via Robust Principal Component Analysis (R-PCA). Compared to the use of standard RGB cameras, the proposed system is insensitive to lighting variations while being significantly less expensive compared to high-frequency radars, time-of-flight cameras and high-resolution thermal sensors previously used in literature. Crucially, this paper shows that the innovative use of the recently proposed Monostable Multivibrator (MMV) neural networks as a new class of SNN achieves more than one order of magnitude smaller memory and compute complexity compared to deep learning approaches, while reaching a top gesture recognition accuracy of 93.9% using a 5-class thermal camera dataset acquired in a car cabin, within an automotive context. Our dataset is released for helping future research.
Authors: Qian Wang, Weiqi Li, Chong Mou, Xinhua Cheng, Jian Zhang
360-degree panoramic videos recently attract more interest in both studies and applications, courtesy of the heightened immersive experiences they engender. Due to the expensive cost of capturing 360-degree panoramic videos, generating desirable panoramic videos by given prompts is urgently required. Recently, the emerging text-to-video (T2V) diffusion methods demonstrate notable effectiveness in standard video generation. However, due to the significant gap in content and motion patterns between panoramic and standard videos, these methods encounter challenges in yielding satisfactory 360-degree panoramic videos. In this paper, we propose a controllable panorama video generation pipeline named 360-Degree Video Diffusion model (360DVD) for generating panoramic videos based on the given prompts and motion conditions. Concretely, we introduce a lightweight module dubbed 360-Adapter and assisted 360 Enhancement Techniques to transform pre-trained T2V models for 360-degree video generation. We further propose a new panorama dataset named WEB360 consisting of 360-degree video-text pairs for training 360DVD, addressing the absence of captioned panoramic video datasets. Extensive experiments demonstrate the superiority and effectiveness of 360DVD for panorama video generation. The code and dataset will be released soon.
Authors: Giampiero Salvi
This paper describes the use of connectionist techniques in phonetic speech recognition with strong latency constraints. The constraints are imposed by the task of deriving the lip movements of a synthetic face in real time from the speech signal, by feeding the phonetic string into an articulatory synthesiser. Particular attention has been paid to analysing the interaction between the time evolution model learnt by the multi-layer perceptrons and the transition model imposed by the Viterbi decoder, in different latency conditions. Two experiments were conducted in which the time dependencies in the language model (LM) were controlled by a parameter. The results show a strong interaction between the three factors involved, namely the neural network topology, the length of time dependencies in the LM and the decoder latency.
Authors: Wei Cao, Chang Luo, Biao Zhang, Matthias Nießner, Jiapeng Tang
We introduce Motion2VecSets, a 4D diffusion model for dynamic surface reconstruction from point cloud sequences. While existing state-of-the-art methods have demonstrated success in reconstructing non-rigid objects using neural field representations, conventional feed-forward networks encounter challenges with ambiguous observations from noisy, partial, or sparse point clouds. To address these challenges, we introduce a diffusion model that explicitly learns the shape and motion distribution of non-rigid objects through an iterative denoising process of compressed latent representations. The diffusion-based prior enables more plausible and probabilistic reconstructions when handling ambiguous inputs. We parameterize 4D dynamics with latent vector sets instead of using a global latent. This novel 4D representation allows us to learn local surface shape and deformation patterns, leading to more accurate non-linear motion capture and significantly improving generalizability to unseen motions and identities. For more temporal-coherent object tracking, we synchronously denoise deformation latent sets and exchange information across multiple frames. To avoid the computational overhead, we design an interleaved space and time attention block to alternately aggregate deformation latents along spatial and temporal domains. Extensive comparisons against the state-of-the-art methods demonstrate the superiority of our Motion2VecSets in 4D reconstruction from various imperfect observations, notably achieving a 19% improvement in Intersection over Union (IoU) compared to CaDex for reconstructing unseen individuals from sparse point clouds on the DeformingThings4D-Animals dataset. More detailed information can be found at https://vveicao.github.io/projects/Motion2VecSets/.
Authors: Peter Lorenz, Ricard Durall, Jansi Keuper
In recent years, diffusion models (DMs) have drawn significant attention for their success in approximating data distributions, yielding state-of-the-art generative results. Nevertheless, the versatility of these models extends beyond their generative capabilities to encompass various vision applications, such as image inpainting, segmentation, adversarial robustness, among others. This study is dedicated to the investigation of adversarial attacks through the lens of diffusion models. However, our objective does not involve enhancing the adversarial robustness of image classifiers. Instead, our focus lies in utilizing the diffusion model to detect and analyze the anomalies introduced by these attacks on images. To that end, we systematically examine the alignment of the distributions of adversarial examples when subjected to the process of transformation using diffusion models. The efficacy of this approach is assessed across CIFAR-10 and ImageNet datasets, including varying image sizes in the latter. The results demonstrate a notable capacity to discriminate effectively between benign and attacked images, providing compelling evidence that adversarial instances do not align with the learned manifold of the DMs.
Authors: Stefan Blücher, Johanna Vielhaben, Nils Strodthoff
Feature removal is a central building block for eXplainable AI (XAI), both for occlusion-based explanations (Shapley values) as well as their evaluation (pixel flipping, PF). However, occlusion strategies can vary significantly from simple mean replacement up to inpainting with state-of-the-art diffusion models. This ambiguity limits the usefulness of occlusion-based approaches. For example, PF benchmarks lead to contradicting rankings. This is amplified by competing PF measures: Features are either removed starting with most influential first (MIF) or least influential first (LIF). This study proposes two complementary perspectives to resolve this disagreement problem. Firstly, we address the common criticism of occlusion-based XAI, that artificial samples lead to unreliable model evaluations. We propose to measure the reliability by the R(eference)-Out-of-Model-Scope (OMS) score. The R-OMS score enables a systematic comparison of occlusion strategies and resolves the disagreement problem by grouping consistent PF rankings. Secondly, we show that the insightfulness of MIF and LIF is conversely dependent on the R-OMS score. To leverage this, we combine the MIF and LIF measures into the symmetric relevance gain (SRG) measure. This breaks the inherent connection to the underlying occlusion strategy and leads to consistent rankings. This resolves the disagreement problem, which we verify for a set of 40 different occlusion strategies.
Authors: M. Erkin Yücel, Serkan Topaloğlu, Cem Ünsalan
The retail sector presents several open and challenging problems that could benefit from advanced pattern recognition and computer vision techniques. One such critical challenge is planogram compliance control. In this study, we propose a complete embedded system to tackle this issue. Our system consists of four key components as image acquisition and transfer via stand-alone embedded camera module, object detection via computer vision and deep learning methods working on single board computers, planogram compliance control method again working on single board computers, and energy harvesting and power management block to accompany the embedded camera modules. The image acquisition and transfer block is implemented on the ESP-EYE camera module. The object detection block is based on YOLOv5 as the deep learning method and local feature extraction. We implement these methods on Raspberry Pi 4, NVIDIA Jetson Orin Nano, and NVIDIA Jetson AGX Orin as single board computers. The planogram compliance control block utilizes sequence alignment through a modified Needleman-Wunsch algorithm. This block is also working along with the object detection block on the same single board computers. The energy harvesting and power management block consists of solar and RF energy harvesting modules with suitable battery pack for operation. We tested the proposed embedded planogram compliance control system on two different datasets to provide valuable insights on its strengths and weaknesses. The results show that our method achieves F1 scores of 0.997 and 1.0 in object detection and planogram compliance control blocks, respectively. Furthermore, we calculated that the complete embedded system can work in stand-alone form up to two years based on battery. This duration can be further extended with the integration of the proposed solar and RF energy harvesting options.
Authors: Damien Robert, Hugo Raguet, Loic Landrieu
We introduce a highly efficient method for panoptic segmentation of large 3D point clouds by redefining this task as a scalable graph clustering problem. This approach can be trained using only local auxiliary tasks, thereby eliminating the resource-intensive instance-matching step during training. Moreover, our formulation can easily be adapted to the superpoint paradigm, further increasing its efficiency. This allows our model to process scenes with millions of points and thousands of objects in a single inference. Our method, called SuperCluster, achieves a new state-of-the-art panoptic segmentation performance for two indoor scanning datasets: $50.1$ PQ ($+7.8$) for S3DIS Area~5, and $58.7$ PQ ($+25.2$) for ScanNetV2. We also set the first state-of-the-art for two large-scale mobile mapping benchmarks: KITTI-360 and DALES. With only $209$k parameters, our model is over $30$ times smaller than the best-competing method and trains up to $15$ times faster. Our code and pretrained models are available at https://github.com/drprojects/superpoint_transformer.
Authors: Muhammad Naveed Riaz, Maciej Wielgosz, Abel Garcia Romera, Antonio M. Lopez
Pedestrian intention prediction is crucial for autonomous driving. In particular, knowing if pedestrians are going to cross in front of the ego-vehicle is core to performing safe and comfortable maneuvers. Creating accurate and fast models that predict such intentions from sequential images is challenging. A factor contributing to this is the lack of datasets with diverse crossing and non-crossing (C/NC) scenarios. We address this scarceness by introducing a framework, named ARCANE, which allows programmatically generating synthetic datasets consisting of C/NC video clip samples. As an example, we use ARCANE to generate a large and diverse dataset named PedSynth. We will show how PedSynth complements widely used real-world datasets such as JAAD and PIE, so enabling more accurate models for C/NC prediction. Considering the onboard deployment of C/NC prediction models, we also propose a deep model named PedGNN, which is fast and has a very low memory footprint. PedGNN is based on a GNN-GRU architecture that takes a sequence of pedestrian skeletons as input to predict crossing intentions.
Authors: Caleb Robinson, Isaac Corley, Anthony Ortiz, Rahul Dodhia, Juan M. Lavista Ferres, Peyman Najafirad
Fully understanding a complex high-resolution satellite or aerial imagery scene often requires spatial reasoning over a broad relevant context. The human object recognition system is able to understand object in a scene over a long-range relevant context. For example, if a human observes an aerial scene that shows sections of road broken up by tree canopy, then they will be unlikely to conclude that the road has actually been broken up into disjoint pieces by trees and instead think that the canopy of nearby trees is occluding the road. However, there is limited research being conducted to understand long-range context understanding of modern machine learning models. In this work we propose a road segmentation benchmark dataset, Chesapeake Roads Spatial Context (RSC), for evaluating the spatial long-range context understanding of geospatial machine learning models and show how commonly used semantic segmentation models can fail at this task. For example, we show that a U-Net trained to segment roads from background in aerial imagery achieves an 84% recall on unoccluded roads, but just 63.5% recall on roads covered by tree canopy despite being trained to model both the same way. We further analyze how the performance of models changes as the relevant context for a decision (unoccluded roads in our case) varies in distance. We release the code to reproduce our experiments and dataset of imagery and masks to encourage future research in this direction -- https://github.com/isaaccorley/ChesapeakeRSC.
Authors: Yun Liu, Yu-Huan Wu, Guolei Sun, Le Zhang, Ajad Chhatkuli, Luc Van Gool
This paper tackles the high computational/space complexity associated with Multi-Head Self-Attention (MHSA) in vanilla vision transformers. To this end, we propose Hierarchical MHSA (H-MHSA), a novel approach that computes self-attention in a hierarchical fashion. Specifically, we first divide the input image into patches as commonly done, and each patch is viewed as a token. Then, the proposed H-MHSA learns token relationships within local patches, serving as local relationship modeling. Then, the small patches are merged into larger ones, and H-MHSA models the global dependencies for the small number of the merged tokens. At last, the local and global attentive features are aggregated to obtain features with powerful representation capacity. Since we only calculate attention for a limited number of tokens at each step, the computational load is reduced dramatically. Hence, H-MHSA can efficiently model global relationships among tokens without sacrificing fine-grained information. With the H-MHSA module incorporated, we build a family of Hierarchical-Attention-based Transformer Networks, namely HAT-Net. To demonstrate the superiority of HAT-Net in scene understanding, we conduct extensive experiments on fundamental vision tasks, including image classification, semantic segmentation, object detection, and instance segmentation. Therefore, HAT-Net provides a new perspective for vision transformers. Code and pretrained models are available at https://github.com/yun-liu/HAT-Net.
Authors: Wele Gedara Chaminda Bandara, Nithin Gopalakrishnan Nair, Vishal M. Patel
Remote sensing change detection is crucial for understanding the dynamics of our planet's surface, facilitating the monitoring of environmental changes, evaluating human impact, predicting future trends, and supporting decision-making. In this work, we introduce a novel approach for change detection that can leverage off-the-shelf, unlabeled remote sensing images in the training process by pre-training a Denoising Diffusion Probabilistic Model (DDPM) - a class of generative models used in image synthesis. DDPMs learn the training data distribution by gradually converting training images into a Gaussian distribution using a Markov chain. During inference (i.e., sampling), they can generate a diverse set of samples closer to the training distribution, starting from Gaussian noise, achieving state-of-the-art image synthesis results. However, in this work, our focus is not on image synthesis but on utilizing it as a pre-trained feature extractor for the downstream application of change detection. Specifically, we fine-tune a lightweight change classifier utilizing the feature representations produced by the pre-trained DDPM alongside change labels. Experiments conducted on the LEVIR-CD, WHU-CD, DSIFN-CD, and CDD datasets demonstrate that the proposed DDPM-CD method significantly outperforms the existing state-of-the-art change detection methods in terms of F1 score, IoU, and overall accuracy, highlighting the pivotal role of pre-trained DDPM as a feature extractor for downstream applications. We have made both the code and pre-trained models available at https://github.com/wgcban/ddpm-cd
Authors: Soojung Hong, Kwanghee Choi
As maintaining road networks is labor-intensive, many automatic road extraction approaches have been introduced to solve this real-world problem, fueled by the abundance of large-scale high-resolution satellite imagery and advances in computer vision. However, their performance is limited for fully automating the road map extraction in real-world services. Hence, many services employ the two-step human-in-the-loop system to post-process the extracted road maps: error localization and automatic mending for faulty road maps. Our paper exclusively focuses on the latter step, introducing a novel image inpainting approach for fixing road maps with complex road geometries without custom-made heuristics, yielding a method that is readily applicable to any road geometry extraction model. We demonstrate the effectiveness of our method on various real-world road geometries, such as straight and curvy roads, T-junctions, and intersections.
Authors: Xingqian Xu, Zhangyang Wang, Eric Zhang, Kai Wang, Humphrey Shi
Recent advances in diffusion models have set an impressive milestone in many generation tasks, and trending works such as DALL-E2, Imagen, and Stable Diffusion have attracted great interest. Despite the rapid landscape changes, recent new approaches focus on extensions and performance rather than capacity, thus requiring separate models for separate tasks. In this work, we expand the existing single-flow diffusion pipeline into a multi-task multimodal network, dubbed Versatile Diffusion (VD), that handles multiple flows of text-to-image, image-to-text, and variations in one unified model. The pipeline design of VD instantiates a unified multi-flow diffusion framework, consisting of sharable and swappable layer modules that enable the crossmodal generality beyond images and text. Through extensive experiments, we demonstrate that VD successfully achieves the following: a) VD outperforms the baseline approaches and handles all its base tasks with competitive quality; b) VD enables novel extensions such as disentanglement of style and semantics, dual- and multi-context blending, etc.; c) The success of our multi-flow multimodal framework over images and text may inspire further diffusion-based universal AI research. Our code and models are open-sourced at https://github.com/SHI-Labs/Versatile-Diffusion.
Authors: Zhenrong Zhang, Pengfei Hu, Jiefeng Ma, Jun Du, Jianshu Zhang, Huihui Zhu, Baocai Yin, Bing Yin, Cong Liu
Table structure recognition is an indispensable element for enabling machines to comprehend tables. Its primary purpose is to identify the internal structure of a table. Nevertheless, due to the complexity and diversity of their structure and style, it is highly challenging to parse the tabular data into a structured format that machines can comprehend. In this work, we adhere to the principle of the split-and-merge based methods and propose an accurate table structure recognizer, termed SEMv2 (SEM: Split, Embed and Merge). Unlike the previous works in the ``split'' stage, we aim to address the table separation line instance-level discrimination problem and introduce a table separation line detection strategy based on conditional convolution. Specifically, we design the ``split'' in a top-down manner that detects the table separation line instance first and then dynamically predicts the table separation line mask for each instance. The final table separation line shape can be accurately obtained by processing the table separation line mask in a row-wise/column-wise manner. To comprehensively evaluate the SEMv2, we also present a more challenging dataset for table structure recognition, dubbed iFLYTAB, which encompasses multiple style tables in various scenarios such as photos, scanned documents, etc. Extensive experiments on publicly available datasets (e.g. SciTSR, PubTabNet and iFLYTAB) demonstrate the efficacy of our proposed approach. The code and iFLYTAB dataset are available at https://github.com/ZZR8066/SEMv2.
Authors: Aristeidis Panos, Yuriko Kobe, Daniel Olmeda Reino, Rahaf Aljundi, Richard E. Turner
In Class-Incremental Learning (CIL) an image classification system is exposed to new classes in each learning session and must be updated incrementally. Methods approaching this problem have updated both the classification head and the feature extractor body at each session of CIL. In this work, we develop a baseline method, First Session Adaptation (FSA), that sheds light on the efficacy of existing CIL approaches and allows us to assess the relative performance contributions from head and body adaption. FSA adapts a pre-trained neural network body only on the first learning session and fixes it thereafter; a head based on linear discriminant analysis (LDA), is then placed on top of the adapted body, allowing exact updates through CIL. FSA is replay-free i.e.~it does not memorize examples from previous sessions of continual learning. To empirically motivate FSA, we first consider a diverse selection of 22 image-classification datasets, evaluating different heads and body adaptation techniques in high/low-shot offline settings. We find that the LDA head performs well and supports CIL out-of-the-box. We also find that Featurewise Layer Modulation (FiLM) adapters are highly effective in the few-shot setting, and full-body adaption in the high-shot setting. Second, we empirically investigate various CIL settings including high-shot CIL and few-shot CIL, including settings that have previously been used in the literature. We show that FSA significantly improves over the state-of-the-art in 15 of the 16 settings considered. FSA with FiLM adapters is especially performant in the few-shot setting. These results indicate that current approaches to continuous body adaptation are not working as expected. Finally, we propose a measure that can be applied to a set of unlabelled inputs which is predictive of the benefits of body adaptation.
Authors: Bohan Li, Yasheng Sun, Zhujin Liang, Dalong Du, Zhuanghui Zhang, Xiaofeng Wang, Yunnan Wang, Xin Jin, Wenjun Zeng
3D semantic scene completion (SSC) is an ill-posed perception task that requires inferring a dense 3D scene from limited observations. Previous camera-based methods struggle to predict accurate semantic scenes due to inherent geometric ambiguity and incomplete observations. In this paper, we resort to stereo matching technique and bird's-eye-view (BEV) representation learning to address such issues in SSC. Complementary to each other, stereo matching mitigates geometric ambiguity with epipolar constraint while BEV representation enhances the hallucination ability for invisible regions with global semantic context. However, due to the inherent representation gap between stereo geometry and BEV features, it is non-trivial to bridge them for dense prediction task of SSC. Therefore, we further develop a unified occupancy-based framework dubbed BRGScene, which effectively bridges these two representations with dense 3D volumes for reliable semantic scene completion. Specifically, we design a novel Mutual Interactive Ensemble (MIE) block for pixel-level reliable aggregation of stereo geometry and BEV features. Within the MIE block, a Bi-directional Reliable Interaction (BRI) module, enhanced with confidence re-weighting, is employed to encourage fine-grained interaction through mutual guidance. Besides, a Dual Volume Ensemble (DVE) module is introduced to facilitate complementary aggregation through channel-wise recalibration and multi-group voting. Our method outperforms all published camera-based methods on SemanticKITTI for semantic scene completion.
Authors: Alessandro Conti, Enrico Fini, Massimiliano Mancini, Paolo Rota, Yiming Wang, Elisa Ricci
Recent advances in large vision-language models have revolutionized the image classification paradigm. Despite showing impressive zero-shot capabilities, a pre-defined set of categories, a.k.a. the vocabulary, is assumed at test time for composing the textual prompts. However, such assumption can be impractical when the semantic context is unknown and evolving. We thus formalize a novel task, termed as Vocabulary-free Image Classification (VIC), where we aim to assign to an input image a class that resides in an unconstrained language-induced semantic space, without the prerequisite of a known vocabulary. VIC is a challenging task as the semantic space is extremely large, containing millions of concepts, with hard-to-discriminate fine-grained categories. In this work, we first empirically verify that representing this semantic space by means of an external vision-language database is the most effective way to obtain semantically relevant content for classifying the image. We then propose Category Search from External Databases (CaSED), a method that exploits a pre-trained vision-language model and an external vision-language database to address VIC in a training-free manner. CaSED first extracts a set of candidate categories from captions retrieved from the database based on their semantic similarity to the image, and then assigns to the image the best matching candidate category according to the same vision-language model. Experiments on benchmark datasets validate that CaSED outperforms other complex vision-language frameworks, while being efficient with much fewer parameters, paving the way for future research in this direction.
Authors: Jifan Zhang, Yifang Chen, Gregory Canal, Stephen Mussmann, Arnav M. Das, Gantavya Bhatt, Yinglun Zhu, Jeffrey Bilmes, Simon Shaolei Du, Kevin Jamieson, Robert D Nowak
Labeled data are critical to modern machine learning applications, but obtaining labels can be expensive. To mitigate this cost, machine learning methods, such as transfer learning, semi-supervised learning and active learning, aim to be label-efficient: achieving high predictive performance from relatively few labeled examples. While obtaining the best label-efficiency in practice often requires combinations of these techniques, existing benchmark and evaluation frameworks do not capture a concerted combination of all such techniques. This paper addresses this deficiency by introducing LabelBench, a new computationally-efficient framework for joint evaluation of multiple label-efficient learning techniques. As an application of LabelBench, we introduce a novel benchmark of state-of-the-art active learning methods in combination with semi-supervised learning for fine-tuning pretrained vision transformers. Our benchmark demonstrates better label-efficiencies than previously reported in active learning. LabelBench's modular codebase is open-sourced for the broader community to contribute label-efficient learning methods and benchmarks. The repository can be found at: https://github.com/EfficientTraining/LabelBench.
Authors: Fangqiang Ding, Zhen Luo, Peijun Zhao, Chris Xiaoxuan Lu
Approaching the era of ubiquitous computing, human motion sensing plays a crucial role in smart systems for decision making, user interaction, and personalized services. Extensive research has been conducted on human tracking, pose estimation, gesture recognition, and activity recognition, which are predominantly based on cameras in traditional methods. However, the intrusive nature of cameras limits their use in smart home applications. To address this, mmWave radars have gained popularity due to their privacy-friendly features. In this work, we propose milliFlow, a novel deep learning method for scene flow estimation as a complementary motion information for mmWave point cloud, serving as an intermediate level of features and directly benefiting downstream human motion sensing tasks. Experimental results demonstrate the superior performance of our method with an average 3D endpoint error of 4.6cm, significantly surpassing the competing approaches. Furthermore, by incorporating scene flow information, we achieve remarkable improvements in human activity recognition, human parsing, and human body part tracking. To foster further research in this area, we will provide our codebase and dataset for open access upon acceptance.
Authors: Anjith George, Christophe Ecabert, Hatef Otroshi Shahreza, Ketan Kotwal, Sebastien Marcel
In this paper, we present EdgeFace, a lightweight and efficient face recognition network inspired by the hybrid architecture of EdgeNeXt. By effectively combining the strengths of both CNN and Transformer models, and a low rank linear layer, EdgeFace achieves excellent face recognition performance optimized for edge devices. The proposed EdgeFace network not only maintains low computational costs and compact storage, but also achieves high face recognition accuracy, making it suitable for deployment on edge devices. Extensive experiments on challenging benchmark face datasets demonstrate the effectiveness and efficiency of EdgeFace in comparison to state-of-the-art lightweight models and deep face recognition models. Our EdgeFace model with 1.77M parameters achieves state of the art results on LFW (99.73%), IJB-B (92.67%), and IJB-C (94.85%), outperforming other efficient models with larger computational complexities. The code to replicate the experiments will be made available publicly.
Authors: Martina Paccini, Giacomo Paschina, Stefano De Beni, Giuseppe Patanè
This paper presents an innovative automatic fusion imaging system that combines 3D CT/MR images with real-time ultrasound (US) acquisition. The system eliminates the need for external physical markers and complex training, making image fusion feasible for physicians with different experience levels. The integrated system involves a portable 3D camera for patient-specific surface acquisition, an electromagnetic tracking system, and US components. The fusion algorithm comprises two main parts: skin segmentation and rigid co-registration, both integrated into the US machine. The co-registration software aligns the surface extracted from CT/MR images with patient-specific coordinates, facilitating rapid and effective fusion. Experimental testing in different settings, including the clinical environment, validates the system's accuracy, computational efficiency, noise robustness, and operator independence. The co-registration error remains under the acceptable range of~$1$ cm.
Authors: Jeong Hun Yeo, Minsu Kim, Jeongsoo Choi, Dae Hoe Kim, Yong Man Ro
Visual Speech Recognition (VSR) is the task of predicting spoken words from silent lip movements. VSR is regarded as a challenging task because of the insufficient information on lip movements. In this paper, we propose an Audio Knowledge empowered Visual Speech Recognition framework (AKVSR) to complement the insufficient speech information of visual modality by using audio modality. Different from the previous methods, the proposed AKVSR 1) utilizes rich audio knowledge encoded by a large-scale pretrained audio model, 2) saves the linguistic information of audio knowledge in compact audio memory by discarding the non-linguistic information from the audio through quantization, and 3) includes Audio Bridging Module which can find the best-matched audio features from the compact audio memory, which makes our training possible without audio inputs, once after the compact audio memory is composed. We validate the effectiveness of the proposed method through extensive experiments, and achieve new state-of-the-art performances on the widely-used LRS3 dataset.
Authors: Minsu Kim, Jeong Hun Yeo, Jeongsoo Choi, Yong Man Ro
This paper proposes a novel lip reading framework, especially for low-resource languages, which has not been well addressed in the previous literature. Since low-resource languages do not have enough video-text paired data to train the model to have sufficient power to model lip movements and language, it is regarded as challenging to develop lip reading models for low-resource languages. In order to mitigate the challenge, we try to learn general speech knowledge, the ability to model lip movements, from a high-resource language through the prediction of speech units. It is known that different languages partially share common phonemes, thus general speech knowledge learned from one language can be extended to other languages. Then, we try to learn language-specific knowledge, the ability to model language, by proposing Language-specific Memory-augmented Decoder (LMDecoder). LMDecoder saves language-specific audio features into memory banks and can be trained on audio-text paired data which is more easily accessible than video-text paired data. Therefore, with LMDecoder, we can transform the input speech units into language-specific audio features and translate them into texts by utilizing the learned rich language knowledge. Finally, by combining general speech knowledge and language-specific knowledge, we can efficiently develop lip reading models even for low-resource languages. Through extensive experiments using five languages, English, Spanish, French, Italian, and Portuguese, the effectiveness of the proposed method is evaluated.
Authors: Haibo Jin, Haoxuan Che, Yi Lin, Hao Chen
Automatic medical report generation (MRG) is of great research value as it has the potential to relieve radiologists from the heavy burden of report writing. Despite recent advancements, accurate MRG remains challenging due to the need for precise clinical understanding and disease identification. Moreover, the imbalanced distribution of diseases makes the challenge even more pronounced, as rare diseases are underrepresented in training data, making their diagnostic performance unreliable. To address these challenges, we propose diagnosis-driven prompts for medical report generation (PromptMRG), a novel framework that aims to improve the diagnostic accuracy of MRG with the guidance of diagnosis-aware prompts. Specifically, PromptMRG is based on encoder-decoder architecture with an extra disease classification branch. When generating reports, the diagnostic results from the classification branch are converted into token prompts to explicitly guide the generation process. To further improve the diagnostic accuracy, we design cross-modal feature enhancement, which retrieves similar reports from the database to assist the diagnosis of a query image by leveraging the knowledge from a pre-trained CLIP. Moreover, the disease imbalanced issue is addressed by applying an adaptive logit-adjusted loss to the classification branch based on the individual learning status of each disease, which overcomes the barrier of text decoder's inability to manipulate disease distributions. Experiments on two MRG benchmarks show the effectiveness of the proposed method, where it obtains state-of-the-art clinical efficacy performance on both datasets. The code is available at https://github.com/jhb86253817/PromptMRG.
Authors: Haoke Xiao, Lv Tang, Bo Li, Zhiming Luo, Shaozi Li
Co-salient Object Detection (CoSOD) endeavors to replicate the human visual system's capacity to recognize common and salient objects within a collection of images. Despite recent advancements in deep learning models, these models still rely on training with well-annotated CoSOD datasets. The exploration of training-free zero-shot CoSOD frameworks has been limited. In this paper, taking inspiration from the zero-shot transfer capabilities of foundational computer vision models, we introduce the first zero-shot CoSOD framework that harnesses these models without any training process. To achieve this, we introduce two novel components in our proposed framework: the group prompt generation (GPG) module and the co-saliency map generation (CMP) module. We evaluate the framework's performance on widely-used datasets and observe impressive results. Our approach surpasses existing unsupervised methods and even outperforms fully supervised methods developed before 2020, while remaining competitive with some fully supervised methods developed before 2022.
Authors: Yu Gao, Lutong Su, Hao Liang, Yufeng Yue, Yi Yang, Mengyin Fu
Neural Radiance Fields (NeRF) employ multi-view images for 3D scene representation and have shown remarkable performance. As one of the primary sources of multi-view images, multi-camera systems encounter challenges such as varying intrinsic parameters and frequent pose changes. Most previous NeRF-based methods often assume a global unique camera and seldom consider scenarios with multiple cameras. Besides, some pose-robust methods still remain susceptible to suboptimal solutions when poses are poor initialized. In this paper, we propose MC-NeRF, a method can jointly optimize both intrinsic and extrinsic parameters for bundle-adjusting Neural Radiance Fields. Firstly, we conduct a theoretical analysis to tackle the degenerate case and coupling issue that arise from the joint optimization between intrinsic and extrinsic parameters. Secondly, based on the proposed solutions, we introduce an efficient calibration image acquisition scheme for multi-camera systems, including the design of calibration object. Lastly, we present a global end-to-end network with training sequence that enables the regression of intrinsic and extrinsic parameters, along with the rendering network. Moreover, most existing datasets are designed for unique camera, we create a new dataset that includes four different styles of multi-camera acquisition systems, allowing readers to generate custom datasets. Experiments confirm the effectiveness of our method when each image corresponds to different camera parameters. Specifically, we adopt up to 110 images with 110 different intrinsic and extrinsic parameters, to achieve 3D scene representation without providing initial poses. The Code and supplementary materials are available at https://in2-viaun.github.io/MC-NeRF.
Authors: Jeong Hun Yeo, Minsu Kim, Shinji Watanabe, Yong Man Ro
This paper proposes a powerful Visual Speech Recognition (VSR) method for multiple languages, especially for low-resource languages that have a limited number of labeled data. Different from previous methods that tried to improve the VSR performance for the target language by using knowledge learned from other languages, we explore whether we can increase the amount of training data itself for the different languages without human intervention. To this end, we employ a Whisper model which can conduct both language identification and audio-based speech recognition. It serves to filter data of the desired languages and transcribe labels from the unannotated, multilingual audio-visual data pool. By comparing the performances of VSR models trained on automatic labels and the human-annotated labels, we show that we can achieve similar VSR performance to that of human-annotated labels even without utilizing human annotations. Through the automated labeling process, we label large-scale unlabeled multilingual databases, VoxCeleb2 and AVSpeech, producing 1,002 hours of data for four low VSR resource languages, French, Italian, Spanish, and Portuguese. With the automatic labels, we achieve new state-of-the-art performance on mTEDx in four languages, significantly surpassing the previous methods. The automatic labels are available online: https://github.com/JeongHun0716/Visual-Speech-Recognition-for-Low-Resource-Languages
Authors: Hao Wang, Omkar Salunkhe, Walter Quadrini, Dan Lämkull, Fredrik Ore, Björn Johansson, Johan Stahre
Wire harnesses are essential hardware for electronic systems in modern automotive vehicles. With a shift in the automotive industry towards electrification and autonomous driving, more and more automotive electronics are responsible for energy transmission and safety-critical functions such as maneuvering, driver assistance, and safety system. This paradigm shift places more demand on automotive wire harnesses from the safety perspective and stresses the greater importance of high-quality wire harness assembly in vehicles. However, most of the current operations of wire harness assembly are still performed manually by skilled workers, and some of the manual processes are problematic in terms of quality control and ergonomics. There is also a persistent demand in the industry to increase competitiveness and gain market share. Hence, assuring assembly quality while improving ergonomics and optimizing labor costs is desired. Robotized assembly, accomplished by robots or in human-robot collaboration, is a key enabler for fulfilling the increasingly demanding quality and safety as it enables more replicable, transparent, and comprehensible processes than completely manual operations. However, robotized assembly of wire harnesses is challenging in practical environments due to the flexibility of the deformable objects, though many preliminary automation solutions have been proposed under simplified industrial configurations. Previous research efforts have proposed the use of computer vision technology to facilitate robotized automation of wire harness assembly, enabling the robots to better perceive and manipulate the flexible wire harness. This article presents an overview of computer vision technology proposed for robotized wire harness assembly and derives research gaps that require further study to facilitate a more practical robotized assembly of wire harnesses.
Authors: Dipam Goswami, Yuyang Liu, Bartłomiej Twardowski, Joost van de Weijer
Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting. Recent approaches to incrementally learning the classifier by freezing the feature extractor after the first task have gained much attention. In this paper, we explore prototypical networks for CIL, which generate new class prototypes using the frozen feature extractor and classify the features based on the Euclidean distance to the prototypes. In an analysis of the feature distributions of classes, we show that classification based on Euclidean metrics is successful for jointly trained features. However, when learning from non-stationary data, we observe that the Euclidean metric is suboptimal and that feature distributions are heterogeneous. To address this challenge, we revisit the anisotropic Mahalanobis distance for CIL. In addition, we empirically show that modeling the feature covariance relations is better than previous attempts at sampling features from normal distributions and training a linear classifier. Unlike existing methods, our approach generalizes to both many- and few-shot CIL settings, as well as to domain-incremental settings. Interestingly, without updating the backbone network, our method obtains state-of-the-art results on several standard continual learning benchmarks. Code is available at https://github.com/dipamgoswami/FeCAM.
Authors: Yunfeng Li, Bo Wang, Xueyi Wu, Zhuoyan Liu, Ye Li
Although single object trackers have achieved advanced performance, their large-scale models hinder their application on limited resources platforms. Moreover, existing lightweight trackers only achieve a balance between 2-3 points in terms of parameters, performance, Flops and FPS. To achieve the optimal balance among these points, this paper proposes a lightweight full-convolutional Siamese tracker called LightFC. LightFC employs a novel efficient cross-correlation module (ECM) and a novel efficient rep-center head (ERH) to improve the feature representation of the convolutional tracking pipeline. The ECM uses an attention-like module design, which conducts spatial and channel linear fusion of fused features and enhances the nonlinearity of the fused features. Additionally, it refers to successful factors of current lightweight trackers and introduces skip-connections and reuse of search area features. The ERH reparameterizes the feature dimensional stage in the standard center-head and introduces channel attention to optimize the bottleneck of key feature flows. Comprehensive experiments show that LightFC achieves the optimal balance between performance, parameters, Flops and FPS. The precision score of LightFC outperforms MixFormerV2-S on LaSOT and TNL2K by 3.7 % and 6.5 %, respectively, while using 5x fewer parameters and 4.6x fewer Flops. Besides, LightFC runs 2x faster than MixFormerV2-S on CPUs. In addition, a higher-performance version named LightFC-vit is proposed by replacing a more powerful backbone network. The code and raw results can be found at https://github.com/LiYunfengLYF/LightFC.
Authors: Tao Liu, Chenpeng Du, Shuai Fan, Feilong Chen, Kai Yu
Generating high-quality and person-generic visual dubbing remains a challenge. Recent innovation has seen the advent of a two-stage paradigm, decoupling the rendering and lip synchronization process facilitated by intermediate representation as a conduit. Still, previous methodologies rely on rough landmarks or are confined to a single speaker, thus limiting their performance. In this paper, we propose DiffDub: Diffusion-based dubbing. We first craft the Diffusion auto-encoder by an inpainting renderer incorporating a mask to delineate editable zones and unaltered regions. This allows for seamless filling of the lower-face region while preserving the remaining parts. Throughout our experiments, we encountered several challenges. Primarily, the semantic encoder lacks robustness, constricting its ability to capture high-level features. Besides, the modeling ignored facial positioning, causing mouth or nose jitters across frames. To tackle these issues, we employ versatile strategies, including data augmentation and supplementary eye guidance. Moreover, we encapsulated a conformer-based reference encoder and motion generator fortified by a cross-attention mechanism. This enables our model to learn person-specific textures with varying references and reduces reliance on paired audio-visual data. Our rigorous experiments comprehensively highlight that our ground-breaking approach outpaces existing methods with considerable margins and delivers seamless, intelligible videos in person-generic and multilingual scenarios.
Authors: Felix Wimbauer, Bichen Wu, Edgar Schoenfeld, Xiaoliang Dai, Ji Hou, Zijian He, Artsiom Sanakoyeu, Peizhao Zhang, Sam Tsai, Jonas Kohler, Christian Rupprecht, Daniel Cremers, Peter Vajda, Jialiang Wang
Diffusion models have recently revolutionized the field of image synthesis due to their ability to generate photorealistic images. However, one of the major drawbacks of diffusion models is that the image generation process is costly. A large image-to-image network has to be applied many times to iteratively refine an image from random noise. While many recent works propose techniques to reduce the number of required steps, they generally treat the underlying denoising network as a black box. In this work, we investigate the behavior of the layers within the network and find that 1) the layers' output changes smoothly over time, 2) the layers show distinct patterns of change, and 3) the change from step to step is often very small. We hypothesize that many layer computations in the denoising network are redundant. Leveraging this, we introduce block caching, in which we reuse outputs from layer blocks of previous steps to speed up inference. Furthermore, we propose a technique to automatically determine caching schedules based on each block's changes over timesteps. In our experiments, we show through FID, human evaluation and qualitative analysis that Block Caching allows to generate images with higher visual quality at the same computational cost. We demonstrate this for different state-of-the-art models (LDM and EMU) and solvers (DDIM and DPM).
Authors: Zheng Zhou, Hongbo Zhao, Ju Liu, Qiaosheng Zhang, Liwei Geng, Shuchang Lyu, Wenquan Feng
Recent investigations demonstrate that adversarial patches can be utilized to manipulate the result of object detection models. However, the conspicuous patterns on these patches may draw more attention and raise suspicions among humans. Moreover, existing works have primarily focused on enhancing the efficacy of attacks in the physical domain, rather than seeking to optimize their stealth attributes and transferability potential. To address these issues, we introduce a dual-perception-based attack framework that generates an adversarial patch known as the More Vivid Patch (MVPatch). The framework consists of a model-perception degradation method and a human-perception improvement method. To derive the MVPatch, we formulate an iterative process that simultaneously constrains the efficacy of multiple object detectors and refines the visual correlation between the generated adversarial patch and a realistic image. Our method employs a model-perception-based approach that reduces the object confidence scores of several object detectors to boost the transferability of adversarial patches. Further, within the human-perception-based framework, we put forward a lightweight technique for visual similarity measurement that facilitates the development of inconspicuous and natural adversarial patches and eliminates the reliance on additional generative models. Additionally, we introduce the naturalness score and transferability score as metrics for an unbiased assessment of various adversarial patches' natural appearance and transferability capacity. Extensive experiments demonstrate that the proposed MVPatch algorithm achieves superior attack transferability compared to similar algorithms in both digital and physical domains while also exhibiting a more natural appearance. These findings emphasize the remarkable stealthiness and transferability of the proposed MVPatch attack algorithm.
Authors: Hao Zhang, Shuaijie Zhang
As an important component of the detector localization branch, bounding box regression loss plays a significant role in object detection tasks. The existing bounding box regression methods usually consider the geometric relationship between the GT box and the predicted box, and calculate the loss by using the relative position and shape of the bounding boxes, while ignoring the influence of inherent properties such as the shape and scale of the bounding boxes on bounding box regression. In order to make up for the shortcomings of existing research, this article proposes a bounding box regression method that focuses on the shape and scale of the bounding box itself. Firstly, we analyzed the regression characteristics of the bounding boxes and found that the shape and scale factors of the bounding boxes themselves will have an impact on the regression results. Based on the above conclusions, we propose the Shape IoU method, which can calculate the loss by focusing on the shape and scale of the bounding box itself, thereby making the bounding box regression more accurate. Finally, we validated our method through a large number of comparative experiments, which showed that our method can effectively improve detection performance and outperform existing methods, achieving state-of-the-art performance in different detection tasks.Code is available at https://github.com/malagoutou/Shape-IoU
Authors: Amirreza Hashemi
This study presents a comprehensive evaluation of tools available on the HuggingFace platform for two pivotal applications in artificial intelligence: image segmentation and voice conversion. The primary objective was to identify the top three tools within each category and subsequently install and configure these tools on Linux systems. We leveraged the power of pre-trained segmentation models such as SAM and DETR Model with ResNet-50 backbone for image segmentation, and the so-vits-svc-fork model for voice conversion. This paper delves into the methodologies and challenges encountered during the implementation process, and showcases the successful combination of video segmentation and voice conversion in a unified project named AutoVisual Fusion Suite.
Authors: Prakash Mallick, Feras Dayoub, Jamie Sherrah
This paper addresses the significant challenge in open-set object detection (OSOD): the tendency of state-of-the-art detectors to erroneously classify unknown objects as known categories with high confidence. We present a novel approach that effectively identifies unknown objects by distinguishing between high and low-density regions in latent space. Our method builds upon the Open-Det (OD) framework, introducing two new elements to the loss function. These elements enhance the known embedding space's clustering and expand the unknown space's low-density regions. The first addition is the Class Wasserstein Anchor (CWA), a new function that refines the classification boundaries. The second is a spectral normalisation step, improving the robustness of the model. Together, these augmentations to the existing Contrastive Feature Learner (CFL) and Unknown Probability Learner (UPL) loss functions significantly improve OSOD performance. Our proposed OpenDet-CWA (OD-CWA) method demonstrates: a) a reduction in open-set errors by approximately 17%-22%, b) an enhancement in novelty detection capability by 1.5%-16%, and c) a decrease in the wilderness index by 2%-20% across various open-set scenarios. These results represent a substantial advancement in the field, showcasing the potential of our approach in managing the complexities of open-set object detection.
Authors: Chunlei Peng, Boyu Wang, Decheng Liu, Nannan Wang, Ruimin Hu, Xinbo Gao
Cloth-changing person re-identification (CC-ReID) aims to match persons who change clothes over long periods. The key challenge in CC-ReID is to extract clothing-independent features, such as face, hairstyle, body shape, and gait. Current research mainly focuses on modeling body shape using multi-modal biological features (such as silhouettes and sketches). However, it does not fully leverage the personal description information hidden in the original RGB image. Considering that there are certain attribute descriptions which remain unchanged after the changing of cloth, we propose a Masked Attribute Description Embedding (MADE) method that unifies personal visual appearance and attribute description for CC-ReID. Specifically, handling variable clothing-sensitive information, such as color and type, is challenging for effective modeling. To address this, we mask the clothing and color information in the personal attribute description extracted through an attribute detection model. The masked attribute description is then connected and embedded into Transformer blocks at various levels, fusing it with the low-level to high-level features of the image. This approach compels the model to discard clothing information. Experiments are conducted on several CC-ReID benchmarks, including PRCC, LTCC, Celeb-reID-light, and LaST. Results demonstrate that MADE effectively utilizes attribute description, enhancing cloth-changing person re-identification performance, and compares favorably with state-of-the-art methods. The code is available at https://github.com/moon-wh/MADE.
Authors: Xiaoyan Yu, Neng Dong, Liehuang Zhu, Hao Peng, Dapeng Tao
Visible-infrared person re-identification (VIReID) primarily deals with matching identities across person images from different modalities. Due to the modality gap between visible and infrared images, cross-modality identity matching poses significant challenges. Recognizing that high-level semantics of pedestrian appearance, such as gender, shape, and clothing style, remain consistent across modalities, this paper intends to bridge the modality gap by infusing visual features with high-level semantics. Given the capability of CLIP to sense high-level semantic information corresponding to visual representations, we explore the application of CLIP within the domain of VIReID. Consequently, we propose a CLIP-Driven Semantic Discovery Network (CSDN) that consists of Modality-specific Prompt Learner, Semantic Information Integration (SII), and High-level Semantic Embedding (HSE). Specifically, considering the diversity stemming from modality discrepancies in language descriptions, we devise bimodal learnable text tokens to capture modality-private semantic information for visible and infrared images, respectively. Additionally, acknowledging the complementary nature of semantic details across different modalities, we integrate text features from the bimodal language descriptions to achieve comprehensive semantics. Finally, we establish a connection between the integrated text features and the visual features across modalities. This process embed rich high-level semantic information into visual representations, thereby promoting the modality invariance of visual representations. The effectiveness and superiority of our proposed CSDN over existing methods have been substantiated through experimental evaluations on multiple widely used benchmarks. The code will be released at \url{https://github.com/nengdong96/CSDN}.
Authors: Beilei Cui, Mobarakol Islam, Long Bai, Hongliang Ren
Purpose: Depth estimation in robotic surgery is vital in 3D reconstruction, surgical navigation and augmented reality visualization. Although the foundation model exhibits outstanding performance in many vision tasks, including depth estimation (e.g., DINOv2), recent works observed its limitations in medical and surgical domain-specific applications. This work presents a low-ranked adaptation (LoRA) of the foundation model for surgical depth estimation. Methods: We design a foundation model-based depth estimation method, referred to as Surgical-DINO, a low-rank adaptation of the DINOv2 for depth estimation in endoscopic surgery. We build LoRA layers and integrate them into DINO to adapt with surgery-specific domain knowledge instead of conventional fine-tuning. During training, we freeze the DINO image encoder, which shows excellent visual representation capacity, and only optimize the LoRA layers and depth decoder to integrate features from the surgical scene. Results: Our model is extensively validated on a MICCAI challenge dataset of SCARED, which is collected from da Vinci Xi endoscope surgery. We empirically show that Surgical-DINO significantly outperforms all the state-of-the-art models in endoscopic depth estimation tasks. The analysis with ablation studies has shown evidence of the remarkable effect of our LoRA layers and adaptation. Conclusion: Surgical-DINO shed some light on the successful adaptation of the foundation models into the surgical domain for depth estimation. There is clear evidence in the results that zero-shot prediction on pre-trained weights in computer vision datasets or naive fine-tuning is not sufficient to use the foundation model in the surgical domain directly. Code is available at https://github.com/BeileiCui/SurgicalDINO.
Authors: Zhaowei Li, Qi Xu, Dong Zhang, Hang Song, Yiqing Cai, Qi Qi, Ran Zhou, Junting Pan, Zefeng Li, Van Tu Vu, Zhida Huang, Tao Wang
Multi-modal large language models have demonstrated impressive performance across various tasks in different modalities. However, existing multi-modal models primarily emphasize capturing global information within each modality while neglecting the importance of perceiving local information across modalities. Consequently, these models lack the ability to effectively understand the fine-grained details of input data, limiting their performance in tasks that require a more nuanced understanding. To address this limitation, there is a compelling need to develop models that enable fine-grained understanding across multiple modalities, thereby enhancing their applicability to a wide range of tasks. In this paper, we propose LEGO, a language enhanced multi-modal grounding model. Beyond capturing global information like other multi-modal models, our proposed model excels at tasks demanding a detailed understanding of local information within the input. It demonstrates precise identification and localization of specific regions in images or moments in videos. To achieve this objective, we design a diversified dataset construction pipeline, resulting in a multi-modal, multi-granularity dataset for model training. The code, dataset, and demo of our model can be found at https: //github.com/lzw-lzw/LEGO.
Authors: Hao Zhang, Cong Xu, Shuaijie Zhang
With the rapid development of detectors, Bounding Box Regression (BBR) loss function has constantly updated and optimized. However, the existing IoU-based BBR still focus on accelerating convergence by adding new loss terms, ignoring the limitations of IoU loss term itself. Although theoretically IoU loss can effectively describe the state of bounding box regression,in practical applications, it cannot adjust itself according to different detectors and detection tasks, and does not have strong generalization. Based on the above, we first analyzed the BBR model and concluded that distinguishing different regression samples and using different scales of auxiliary bounding boxes to calculate losses can effectively accelerate the bounding box regression process. For high IoU samples, using smaller auxiliary bounding boxes to calculate losses can accelerate convergence, while larger auxiliary bounding boxes are suitable for low IoU samples. Then, we propose Inner-IoU loss, which calculates IoU loss through auxiliary bounding boxes. For different datasets and detectors, we introduce a scaling factor ratio to control the scale size of the auxiliary bounding boxes for calculating losses. Finally, integrate Inner-IoU into the existing IoU-based loss functions for simulation and comparative experiments. The experiment result demonstrate a further enhancement in detection performance with the utilization of the method proposed in this paper, verifying the effectiveness and generalization ability of Inner-IoU loss. Code is available at https://github.com/malagoutou/Inner-IoU.