Authors: Tiankai Hang, Shuyang Gu, Dong Chen, Xin Geng, Baining Guo
This paper presents a novel generative model, Collaborative Competitive Agents (CCA), which leverages the capabilities of multiple Large Language Models (LLMs) based agents to execute complex tasks. Drawing inspiration from Generative Adversarial Networks (GANs), the CCA system employs two equal-status generator agents and a discriminator agent. The generators independently process user instructions and generate results, while the discriminator evaluates the outputs, and provides feedback for the generator agents to further reflect and improve the generation results. Unlike the previous generative model, our system can obtain the intermediate steps of generation. This allows each generator agent to learn from other successful executions due to its transparency, enabling a collaborative competition that enhances the quality and robustness of the system's results. The primary focus of this study is image editing, demonstrating the CCA's ability to handle intricate instructions robustly. The paper's main contributions include the introduction of a multi-agent-based generative model with controllable intermediate steps and iterative optimization, a detailed examination of agent relationships, and comprehensive experiments on image editing. Code is available at \href{https://github.com/TiankaiHang/CCA}{https://github.com/TiankaiHang/CCA}.
Authors: Muhammad Imran, Jonathan R Krebs, Veera Rajasekhar Reddy Gopu, Brian Fazzone, Vishal Balaji Sivaraman, Amarjeet Kumar, Chelsea Viscardi, Robert Evans Heithaus, Benjamin Shickel, Yuyin Zhou, Michol A Cooper, Wei Shao
Advancements in medical imaging and endovascular grafting have facilitated minimally invasive treatments for aortic diseases. Accurate 3D segmentation of the aorta and its branches is crucial for interventions, as inaccurate segmentation can lead to erroneous surgical planning and endograft construction. Previous methods simplified aortic segmentation as a binary image segmentation problem, overlooking the necessity of distinguishing between individual aortic branches. In this paper, we introduce Context Infused Swin-UNet (CIS-UNet), a deep learning model designed for multi-class segmentation of the aorta and thirteen aortic branches. Combining the strengths of Convolutional Neural Networks (CNNs) and Swin transformers, CIS-UNet adopts a hierarchical encoder-decoder structure comprising a CNN encoder, symmetric decoder, skip connections, and a novel Context-aware Shifted Window Self-Attention (CSW-SA) as the bottleneck block. Notably, CSW-SA introduces a unique utilization of the patch merging layer, distinct from conventional Swin transformers. It efficiently condenses the feature map, providing a global spatial context and enhancing performance when applied at the bottleneck layer, offering superior computational efficiency and segmentation accuracy compared to the Swin transformers. We trained our model on computed tomography (CT) scans from 44 patients and tested it on 15 patients. CIS-UNet outperformed the state-of-the-art SwinUNetR segmentation model, which is solely based on Swin transformers, by achieving a superior mean Dice coefficient of 0.713 compared to 0.697, and a mean surface distance of 2.78 mm compared to 3.39 mm. CIS-UNet's superior 3D aortic segmentation offers improved precision and optimization for planning endovascular treatments. Our dataset and code will be publicly available.
Authors: Zhaozhi Xie, Bochen Guan, Weihao Jiang, Muyang Yi, Yue Ding, Hongtao Lu, Lei Zhang
The Segment Anything Model (SAM) has exhibited outstanding performance in various image segmentation tasks. Despite being trained with over a billion masks, SAM faces challenges in mask prediction quality in numerous scenarios, especially in real-world contexts. In this paper, we introduce a novel prompt-driven adapter into SAM, namely Prompt Adapter Segment Anything Model (PA-SAM), aiming to enhance the segmentation mask quality of the original SAM. By exclusively training the prompt adapter, PA-SAM extracts detailed information from images and optimizes the mask decoder feature at both sparse and dense prompt levels, improving the segmentation performance of SAM to produce high-quality masks. Experimental results demonstrate that our PA-SAM outperforms other SAM-based methods in high-quality, zero-shot, and open-set segmentation. We're making the source code and models available at https://github.com/xzz2/pa-sam.
Authors: Scout Jarman, Zigfried Hampel-Arias, Adra Carr, Kevin R. Moon
Deep learning identification models have shown promise for identifying gas plumes in Longwave IR hyperspectral images of urban scenes, particularly when a large library of gases are being considered. Because many gases have similar spectral signatures, it is important to properly estimate the signal from a detected plume. Typically, a scene's global mean spectrum and covariance matrix are estimated to whiten the plume's signal, which removes the background's signature from the gas signature. However, urban scenes can have many different background materials that are spatially and spectrally heterogeneous. This can lead to poor identification performance when the global background estimate is not representative of a given local background material. We use image segmentation, along with an iterative background estimation algorithm, to create local estimates for the various background materials that reside underneath a gas plume. Our method outperforms global background estimation on a set of simulated and real gas plumes. This method shows promise in increasing deep learning identification confidence, while being simple and easy to tune when considering diverse plumes.
Authors: Mingyang Li, Yue Ma, Qinru Qiu
Current techniques in Visual Simultaneous Localization and Mapping (VSLAM) estimate camera displacement by comparing image features of consecutive scenes. These algorithms depend on scene continuity, hence requires frequent camera inputs. However, processing images frequently can lead to significant memory usage and computation overhead. In this study, we introduce SemanticSLAM, an end-to-end visual-inertial odometry system that utilizes semantic features extracted from an RGB-D sensor. This approach enables the creation of a semantic map of the environment and ensures reliable camera localization. SemanticSLAM is scene-agnostic, which means it doesn't require retraining for different environments. It operates effectively in indoor settings, even with infrequent camera input, without prior knowledge. The strength of SemanticSLAM lies in its ability to gradually refine the semantic map and improve pose estimation. This is achieved by a convolutional long-short-term-memory (ConvLSTM) network, trained to correct errors during map construction. Compared to existing VSLAM algorithms, SemanticSLAM improves pose estimation by 17%. The resulting semantic map provides interpretable information about the environment and can be easily applied to various downstream tasks, such as path planning, obstacle avoidance, and robot navigation. The code will be publicly available at https://github.com/Leomingyangli/SemanticSLAM
Authors: Abhishek Narayanan, Rushabh Musthyala, Rahul Sankar, Anirudh Prasad Nistala, Pranav Singh, Jacopo Cirrone
Visual Question Answering (VQA) in the medical domain presents a unique, interdisciplinary challenge, combining fields such as Computer Vision, Natural Language Processing, and Knowledge Representation. Despite its importance, research in medical VQA has been scant, only gaining momentum since 2018. Addressing this gap, our research delves into the effective representation of radiology images and the joint learning of multimodal representations, surpassing existing methods. We innovatively augment the SLAKE dataset, enabling our model to respond to a more diverse array of questions, not limited to the immediate content of radiology or pathology images. Our model achieves a top-1 accuracy of 79.55\% with a less complex architecture, demonstrating comparable performance to current state-of-the-art models. This research not only advances medical VQA but also opens avenues for practical applications in diagnostic settings.
Authors: Shyam Sundar Kannan, Byung-Cheol Min
Visual place recognition is a challenging task in the field of computer vision, and autonomous robotics and vehicles, which aims to identify a location or a place from visual inputs. Contemporary methods in visual place recognition employ convolutional neural networks and utilize every region within the image for the place recognition task. However, the presence of dynamic and distracting elements in the image may impact the effectiveness of the place recognition process. Therefore, it is meaningful to focus on task-relevant regions of the image for improved recognition. In this paper, we present PlaceFormer, a novel transformer-based approach for visual place recognition. PlaceFormer employs patch tokens from the transformer to create global image descriptors, which are then used for image retrieval. To re-rank the retrieved images, PlaceFormer merges the patch tokens from the transformer to form multi-scale patches. Utilizing the transformer's self-attention mechanism, it selects patches that correspond to task-relevant areas in an image. These selected patches undergo geometric verification, generating similarity scores across different patch sizes. Subsequently, spatial scores from each patch size are fused to produce a final similarity score. This score is then used to re-rank the images initially retrieved using global image descriptors. Extensive experiments on benchmark datasets demonstrate that PlaceFormer outperforms several state-of-the-art methods in terms of accuracy and computational efficiency, requiring less time and memory.
Authors: Matthew Martell, Nick Terry, Ribhu Sengupta, Chris Salazar, Nicole A. Errett, Scott B. Miles, Joseph Wartman, Youngjun Choe
Street View Images (SVI) are a common source of valuable data for researchers. Researchers have used SVI data for estimating pedestrian volumes, demographic surveillance, and to better understand built and natural environments in cityscapes. However, the most common source of publicly available SVI data is Google Street View. Google Street View images are collected infrequently, making temporal analysis challenging, especially in low population density areas. Our main contribution is the development of an open-source data pipeline for processing 360-degree video recorded from a car-mounted camera. The video data is used to generate SVIs, which then can be used as an input for temporal analysis. We demonstrate the use of the pipeline by collecting a SVI dataset over a 38-month longitudinal survey of Seattle, WA, USA during the COVID-19 pandemic. The output of our pipeline is validated through statistical analyses of pedestrian traffic in the images. We confirm known results in the literature and provide new insights into outdoor pedestrian traffic patterns. This study demonstrates the feasibility and value of collecting and using SVI for research purposes beyond what is possible with currently available SVI data. Limitations and future improvements on the data pipeline and case study are also discussed.
Authors: Michelle R. Greene, Mariam Josyula, Wentao Si, Jennifer A. Hart
Computer-based scene understanding has influenced fields ranging from urban planning to autonomous vehicle performance, yet little is known about how well these technologies work across social differences. We investigate the biases of deep convolutional neural networks (dCNNs) in scene classification, using nearly one million images from global and US sources, including user-submitted home photographs and Airbnb listings. We applied statistical models to quantify the impact of socioeconomic indicators such as family income, Human Development Index (HDI), and demographic factors from public data sources (CIA and US Census) on dCNN performance. Our analyses revealed significant socioeconomic bias, where pretrained dCNNs demonstrated lower classification accuracy, lower classification confidence, and a higher tendency to assign labels that could be offensive when applied to homes (e.g., "ruin", "slum"), especially in images from homes with lower socioeconomic status (SES). This trend is consistent across two datasets of international images and within the diverse economic and racial landscapes of the United States. This research contributes to understanding biases in computer vision, emphasizing the need for more inclusive and representative training datasets. By mitigating the bias in the computer vision pipelines, we can ensure fairer and more equitable outcomes for applied computer vision, including home valuation and smart home security systems. There is urgency in addressing these biases, which can significantly impact critical decisions in urban development and resource allocation. Our findings also motivate the development of AI systems that better understand and serve diverse communities, moving towards technology that equitably benefits all sectors of society.
Authors: Xiongchao Chen, Bo Zhou, Xueqi Guo, Huidong Xie, Qiong Liu, James S. Duncan, Albert J.Sinusas, Chi Liu
Single-Photon Emission Computed Tomography (SPECT) is widely applied for the diagnosis of coronary artery diseases. Low-dose (LD) SPECT aims to minimize radiation exposure but leads to increased image noise. Limited-view (LV) SPECT, such as the latest GE MyoSPECT ES system, enables accelerated scanning and reduces hardware expenses but degrades reconstruction accuracy. Additionally, Computed Tomography (CT) is commonly used to derive attenuation maps ($\mu$-maps) for attenuation correction (AC) of cardiac SPECT, but it will introduce additional radiation exposure and SPECT-CT misalignments. Although various methods have been developed to solely focus on LD denoising, LV reconstruction, or CT-free AC in SPECT, the solution for simultaneously addressing these tasks remains challenging and under-explored. Furthermore, it is essential to explore the potential of fusing cross-domain and cross-modality information across these interrelated tasks to further enhance the accuracy of each task. Thus, we propose a Dual-Domain Coarse-to-Fine Progressive Network (DuDoCFNet), a multi-task learning method for simultaneous LD denoising, LV reconstruction, and CT-free $\mu$-map generation of cardiac SPECT. Paired dual-domain networks in DuDoCFNet are cascaded using a multi-layer fusion mechanism for cross-domain and cross-modality feature fusion. Two-stage progressive learning strategies are applied in both projection and image domains to achieve coarse-to-fine estimations of SPECT projections and CT-derived $\mu$-maps. Our experiments demonstrate DuDoCFNet's superior accuracy in estimating projections, generating $\mu$-maps, and AC reconstructions compared to existing single- or multi-task learning methods, under various iterations and LD levels. The source code of this work is available at https://github.com/XiongchaoChen/DuDoCFNet-MultiTask.
Authors: Mahdi Tabassian, Somayeh Akbari. S, Sandro Queirós, Jan D'hooge
This study presents a deep convolutional auto-encoder network for filtering reverberation artifacts, from transthoracic echocardiographic (TTE) image sequences. Given the spatiotemporal nature of these artifacts, the filtering network was built using 3D convolutional layers to suppress the clutter patterns throughout the cardiac cycle. The network was designed by taking advantage of: i) an attention mechanism to focus primarily on cluttered regions and ii) residual learning to preserve fine structures of the image frames. To train the deep network, a diverse set of artifact patterns was simulated and the simulated patterns were superimposed onto artifact-free ultra-realistic synthetic TTE sequences of six ultrasound vendors to generate input of the filtering network. The artifact-free sequences served as ground-truth. Performance of the filtering network was evaluated using unseen synthetic as well as in-vivo artifactual sequences. Satisfactory results obtained using the latter dataset confirmed the good generalization performance of the proposed network which was trained using the synthetic sequences and simulated artifact patterns. Suitability of the clutter-filtered sequences for further processing was assessed by computing segmental strain curves from them. The results showed that the large discrepancy between the strain profiles computed from the cluttered segments and their corresponding segments in the clutter-free images was significantly reduced after filtering the sequences using the proposed network. The trained deep network could process an artifactual TTE sequence in a fraction of a second and can be used for real-time clutter filtering. Moreover, it can improve the precision of the clinical indexes that are computed from the TTE sequences. The source code of the proposed method is available at: https://github.com/MahdiTabassian/Deep-Clutter-Filtering/tree/main.
Authors: Luciano Carvalho Ayres, Ricardo Augusto Borsoi, José Carlos Moreira Bermudez, Sérgio José Melo de Almeida
In hyperspectral sparse unmixing, a successful approach employs spectral bundles to address the variability of the endmembers in the spatial domain. However, the regularization penalties usually employed aggregate substantial computational complexity, and the solutions are very noise-sensitive. We generalize a multiscale spatial regularization approach to solve the unmixing problem by incorporating group sparsity-inducing mixed norms. Then, we propose a noise-robust method that can take advantage of the bundle structure to deal with endmember variability while ensuring inter- and intra-class sparsity in abundance estimation with reasonable computational cost. We also present a general heuristic to select the \emph{most representative} abundance estimation over multiple runs of the unmixing process, yielding a solution that is robust and highly reproducible. Experiments illustrate the robustness and consistency of the results when compared to related methods.
Authors: Haotian Hu, Fanyi Wang, Yaonong Wang, Laifeng Hu, Jingwei Xu, Zhiwang Zhang
In the field of autonomous driving, online high-definition (HD) map reconstruction is crucial for planning tasks. Recent research has developed several high-performance HD map reconstruction models to meet this necessity. However, the point sequences within the instance vectors may be jittery or jagged due to prediction bias, which can impact subsequent tasks. Therefore, this paper proposes the Anti-disturbance Map reconstruction framework (ADMap). To mitigate point-order jitter, the framework consists of three modules: Multi-Scale Perception Neck, Instance Interactive Attention (IIA), and Vector Direction Difference Loss (VDDL). By exploring the point-order relationships between and within instances in a cascading manner, the model can monitor the point-order prediction process more effectively. ADMap achieves state-of-the-art performance on the nuScenes and Argoverse2 datasets. Extensive results demonstrate its ability to produce stable and reliable map elements in complex and changing driving scenarios. Code and more demos are available at https://github.com/hht1996ok/ADMap.
Authors: Dong Zhang, Pingcheng Dong, Xinting Hu, Long Chen, Kwang-Ting Cheng
Recently, it has been revealed that small semantic segmentation (SS) models exhibit a tendency to make errors in maintaining boundary region completeness and preserving target region connectivity, despite their effective segmentation of the main object regions. To address these errors, we propose a targeted boundary and relation distillation (BRD) strategy using knowledge distillation from large teacher models to small student models. Specifically, the boundary distillation extracts explicit object boundaries from the hierarchical feature maps of the backbone network, subsequently enhancing the student model's mask quality in boundary regions. Concurrently, the relation distillation transfers implicit relations from the teacher model to the student model using pixel-level self-relation as a bridge, ensuring that the student's mask has strong target region connectivity. The proposed BRD is designed concretely for SS and is characterized by simplicity and efficiency. Through experimental evaluations on multiple SS datasets, including Pascal VOC 2012, Cityscapes, ADE20K, and COCO-Stuff 10K, we demonstrated that BRD significantly surpasses the current methods without increasing the inference costs, generating crisp region boundaries and smooth connecting regions that are challenging for small models.
Authors: Yuanming Li, Gwantae Kim, Jeong-gi Kwak, Bon-hwa Ku, Hanseok Ko
Recently, deep learning-based facial landmark detection for in-the-wild faces has achieved significant improvement. However, there are still challenges in face landmark detection in other domains (e.g. cartoon, caricature, etc). This is due to the scarcity of extensively annotated training data. To tackle this concern, we design a two-stage training approach that effectively leverages limited datasets and the pre-trained diffusion model to obtain aligned pairs of landmarks and face in multiple domains. In the first stage, we train a landmark-conditioned face generation model on a large dataset of real faces. In the second stage, we fine-tune the above model on a small dataset of image-landmark pairs with text prompts for controlling the domain. Our new designs enable our method to generate high-quality synthetic paired datasets from multiple domains while preserving the alignment between landmarks and facial features. Finally, we fine-tuned a pre-trained face landmark detection model on the synthetic dataset to achieve multi-domain face landmark detection. Our qualitative and quantitative results demonstrate that our method outperforms existing methods on multi-domain face landmark detection.
Authors: Minsoo Kang, Minkoo Kang, Suhyun Kim
Deep learning has made significant advances in computer vision, particularly in image classification tasks. Despite their high accuracy on training data, deep learning models often face challenges related to complexity and overfitting. One notable concern is that the model often relies heavily on a limited subset of filters for making predictions. This dependency can result in compromised generalization and an increased vulnerability to minor variations. While regularization techniques like weight decay, dropout, and data augmentation are commonly used to address this issue, they may not directly tackle the reliance on specific filters. Our observations reveal that the heavy reliance problem gets severe when slow-learning filters are deprived of learning opportunities due to fast-learning filters. Drawing inspiration from image augmentation research that combats over-reliance on specific image regions by removing and replacing parts of images, our idea is to mitigate the problem of over-reliance on strong filters by substituting highly activated features. To this end, we present a novel method called Catch-up Mix, which provides learning opportunities to a wide range of filters during training, focusing on filters that may lag behind. By mixing activation maps with relatively lower norms, Catch-up Mix promotes the development of more diverse representations and reduces reliance on a small subset of filters. Experimental results demonstrate the superiority of our method in various vision classification datasets, providing enhanced robustness.
Authors: Tejas Vyas, Mohsena Chowdhury, Xiaojiao Xiao, Mathias Claeys, Géraldine Ong, Guanghui Wang
Mitral Transcatheter Edge-to-Edge Repair (mTEER) is a medical procedure utilized for the treatment of mitral valve disorders. However, predicting the outcome of the procedure poses a significant challenge. This paper makes the first attempt to harness classical machine learning (ML) and deep learning (DL) techniques for predicting mitral valve mTEER surgery outcomes. To achieve this, we compiled a dataset from 467 patients, encompassing labeled echocardiogram videos and patient reports containing Transesophageal Echocardiography (TEE) measurements detailing Mitral Valve Repair (MVR) treatment outcomes. Leveraging this dataset, we conducted a benchmark evaluation of six ML algorithms and two DL models. The results underscore the potential of ML and DL in predicting mTEER surgery outcomes, providing insight for future investigation and advancements in this domain.
Authors: Shan Yang, Yongfei Zhang
Multimodal large language models (MLLM) have achieved satisfactory results in many tasks. However, their performance in the task of person re-identification (ReID) has not been explored to date. This paper will investigate how to adapt them for the task of ReID. An intuitive idea is to fine-tune MLLM with ReID image-text datasets, and then use their visual encoder as a backbone for ReID. However, there still exist two apparent issues: (1) Designing instructions for ReID, MLLMs may overfit specific instructions, and designing a variety of instructions will lead to higher costs. (2) Latent image feature vectors from LLMs are not involved in loss computation. Instructional learning, aligning image-text features, results in indirect optimization and a learning objective that inadequately utilizes features, limiting effectiveness in person feature learning. To address these problems, this paper proposes MLLMReID: Multimodal Large Language Model-based ReID. Firstly, we proposed Common Instruction, a simple approach that leverages the essence ability of LLMs to continue writing, avoiding complex and diverse instruction design. Secondly, we proposed DirectReID, which effectively employs the latent image feature vectors of images outputted by LLMs in ReID tasks. The experimental results demonstrate the superiority of our method. We will open-source the code on GitHub.
Authors: Yunfan Zhang, Hong Huang, Zhiwei Xiong, Zhiqi Shen, Guosheng Lin, Hao Wang, Nicholas Vun
Controllable 3D indoor scene synthesis stands at the forefront of technological progress, offering various applications like gaming, film, and augmented/virtual reality. The capability to stylize and de-couple objects within these scenarios is a crucial factor, providing an advanced level of control throughout the editing process. This control extends not just to manipulating geometric attributes like translation and scaling but also includes managing appearances, such as stylization. Current methods for scene stylization are limited to applying styles to the entire scene, without the ability to separate and customize individual objects. Addressing the intricacies of this challenge, we introduce a unique pipeline designed for synthesis 3D indoor scenes. Our approach involves strategically placing objects within the scene, utilizing information from professionally designed bounding boxes. Significantly, our pipeline prioritizes maintaining style consistency across multiple objects within the scene, ensuring a cohesive and visually appealing result aligned with the desired aesthetic. The core strength of our pipeline lies in its ability to generate 3D scenes that are not only visually impressive but also exhibit features like photorealism, multi-view consistency, and diversity. These scenes are crafted in response to various natural language prompts, demonstrating the versatility and adaptability of our model.
Authors: Junlin Liu, Xinchen Lyu
Adversarial examples are one critical security threat to various visual applications, where injected human-imperceptible perturbations can confuse the output.Generating transferable adversarial examples in the black-box setting is crucial but challenging in practice. Existing input-diversity-based methods adopt different image transformations, but may be inefficient due to insufficient input diversity and an identical perturbation step size. Motivated by the fact that different image regions have distinctive weights in classification, this paper proposes a black-box adversarial generative framework by jointly designing enhanced input diversity and adaptive step sizes. We design local mixup to randomly mix a group of transformed adversarial images, strengthening the input diversity. For precise adversarial generation, we project the perturbation into the $tanh$ space to relax the boundary constraint. Moreover, the step sizes of different regions can be dynamically adjusted by integrating a second-order momentum.Extensive experiments on ImageNet validate that our framework can achieve superior transferability compared to state-of-the-art baselines.
Authors: Lulan Shen, Ali Edalati, Brett Meyer, Warren Gross, James J. Clark
This paper describes a simple yet effective technique for refining a pretrained classifier network. The proposed AdCorDA method is based on modification of the training set and making use of the duality between network weights and layer inputs. We call this input space training. The method consists of two stages - adversarial correction followed by domain adaptation. Adversarial correction uses adversarial attacks to correct incorrect training-set classifications. The incorrectly classified samples of the training set are removed and replaced with the adversarially corrected samples to form a new training set, and then, in the second stage, domain adaptation is performed back to the original training set. Extensive experimental validations show significant accuracy boosts of over 5% on the CIFAR-100 dataset. The technique can be straightforwardly applied to refinement of weight-quantized neural networks, where experiments show substantial enhancement in performance over the baseline. The adversarial correction technique also results in enhanced robustness to adversarial attacks.
Authors: Miao Zhang, Zee fryer, Ben Colman, Ali Shahriyari, Gaurav Bharaj
Machine learning model bias can arise from dataset composition: sensitive features correlated to the learning target disturb the model decision rule and lead to performance differences along the features. Existing de-biasing work captures prominent and delicate image features which are traceable in model latent space, like colors of digits or background of animals. However, using the latent space is not sufficient to understand all dataset feature correlations. In this work, we propose a framework to extract feature clusters in a dataset based on image descriptions, allowing us to capture both subtle and coarse features of the images. The feature co-occurrence pattern is formulated and correlation is measured, utilizing a human-in-the-loop for examination. The analyzed features and correlations are human-interpretable, so we name the method Common-Sense Bias Discovery (CSBD). Having exposed sensitive correlations in a dataset, we demonstrate that downstream model bias can be mitigated by adjusting image sampling weights, without requiring a sensitive group label supervision. Experiments show that our method discovers novel biases on multiple classification tasks for two benchmark image datasets, and the intervention outperforms state-of-the-art unsupervised bias mitigation methods.
Authors: Xiaolin Ma, Junkai Cheng, Aihua Li, Yuhua Zhang, Zhilong Lin
Recently, methods based on deep learning have been successfully applied to ship detection for synthetic aperture radar (SAR) images. Despite the development of numerous ship detection methodologies, detecting small and coastal ships remains a significant challenge due to the limited features and clutter in coastal environments. For that, a novel adaptive multi-hierarchical attention module (AMAM) is proposed to learn multi-scale features and adaptively aggregate salient features from various feature layers, even in complex environments. Specifically, we first fuse information from adjacent feature layers to enhance the detection of smaller targets, thereby achieving multi-scale feature enhancement. Then, to filter out the adverse effects of complex backgrounds, we dissect the previously fused multi-level features on the channel, individually excavate the salient regions, and adaptively amalgamate features originating from different channels. Thirdly, we present a novel adaptive multi-hierarchical attention network (AMANet) by embedding the AMAM between the backbone network and the feature pyramid network (FPN). Besides, the AMAM can be readily inserted between different frameworks to improve object detection. Lastly, extensive experiments on two large-scale SAR ship detection datasets demonstrate that our AMANet method is superior to state-of-the-art methods.
Authors: Saiyang Na, Yuzhi Guo, Feng Jiang, Hehuan Ma, Junzhou Huang
In the rapidly evolving field of AI research, foundational models like BERT and GPT have significantly advanced language and vision tasks. The advent of pretrain-prompting models such as ChatGPT and Segmentation Anything Model (SAM) has further revolutionized image segmentation. However, their applications in specialized areas, particularly in nuclei segmentation within medical imaging, reveal a key challenge: the generation of high-quality, informative prompts is as crucial as applying state-of-the-art (SOTA) fine-tuning techniques on foundation models. To address this, we introduce Segment Any Cell (SAC), an innovative framework that enhances SAM specifically for nuclei segmentation. SAC integrates a Low-Rank Adaptation (LoRA) within the attention layer of the Transformer to improve the fine-tuning process, outperforming existing SOTA methods. It also introduces an innovative auto-prompt generator that produces effective prompts to guide segmentation, a critical factor in handling the complexities of nuclei segmentation in biomedical imaging. Our extensive experiments demonstrate the superiority of SAC in nuclei segmentation tasks, proving its effectiveness as a tool for pathologists and researchers. Our contributions include a novel prompt generation strategy, automated adaptability for diverse segmentation tasks, the innovative application of Low-Rank Attention Adaptation in SAM, and a versatile framework for semantic segmentation challenges.
Authors: Yimin Xu, Nanxi Gao, Zhongyun Shan, Fei Chao, Rongrong Ji
In contrast to traditional image restoration methods, all-in-one image restoration techniques are gaining increased attention for their ability to restore images affected by diverse and unknown corruption types and levels. However, contemporary all-in-one image restoration methods omit task-wise difficulties and employ the same networks to reconstruct images afflicted by diverse degradations. This practice leads to an underestimation of the task correlations and suboptimal allocation of computational resources. To elucidate task-wise complexities, we introduce a novel concept positing that intricate image degradation can be represented in terms of elementary degradation. Building upon this foundation, we propose an innovative approach, termed the Unified-Width Adaptive Dynamic Network (U-WADN), consisting of two pivotal components: a Width Adaptive Backbone (WAB) and a Width Selector (WS). The WAB incorporates several nested sub-networks with varying widths, which facilitates the selection of the most apt computations tailored to each task, thereby striking a balance between accuracy and computational efficiency during runtime. For different inputs, the WS automatically selects the most appropriate sub-network width, taking into account both task-specific and sample-specific complexities. Extensive experiments across a variety of image restoration tasks demonstrate that the proposed U-WADN achieves better performance while simultaneously reducing up to 32.3\% of FLOPs and providing approximately 15.7\% real-time acceleration. The code has been made available at \url{https://github.com/xuyimin0926/U-WADN}.
Authors: Ziru Zeng, Yue Ding, Hongtao Lu
Recently,the detection transformer has gained substantial attention for its inherent minimal post-processing requirement.However,this paradigm relies on abundant training data,yet in the context of the cross-domain adaptation,insufficient labels in the target domain exacerbate issues of class imbalance and model performance degradation.To address these challenges, we propose a novel class-aware cross domain detection transformer based on the adversarial learning and mean-teacher framework.First,considering the inconsistencies between the classification and regression tasks,we introduce an IoU-aware prediction branch and exploit the consistency of classification and location scores to filter and reweight pseudo labels.Second, we devise a dynamic category threshold refinement to adaptively manage model confidence.Third,to alleviate the class imbalance,an instance-level class-aware contrastive learning module is presented to encourage the generation of discriminative features for each class,particularly benefiting minority classes.Experimental results across diverse domain-adaptive scenarios validate our method's effectiveness in improving performance and alleviating class imbalance issues,which outperforms the state-of-the-art transformer based methods.
Authors: Shuchang Ye, Mingyuan Meng, Mingjian Li, Dagan Feng, Jinman Kim
With increasing reliance on medical imaging in clinical practices, automated report generation from medical images is in great demand. Existing report generation methods typically adopt an encoder-decoder deep learning framework to build a uni-directional image-to-report mapping. However, such a framework ignores the bi-directional mutual associations between images and reports, thus incurring difficulties in associating the intrinsic medical meanings between them. Recent generative representation learning methods have demonstrated the benefits of dual-modal learning from both image and text modalities. However, these methods exhibit two major drawbacks for medical report generation: 1) they tend to capture morphological information and have difficulties in capturing subtle pathological semantic information, and 2) they predict masked text rely on both unmasked images and text, inevitably degrading performance when inference is based solely on images. In this study, we propose a new report generation framework with dual-modal dynamic traceback learning (DTrace) to overcome the two identified drawbacks and enable dual-modal learning for medical report generation. To achieve this, our DTrace introduces a traceback mechanism to control the semantic validity of generated content via self-assessment. Further, our DTrace introduces a dynamic learning strategy to adapt to various proportions of image and text input, enabling report generation without reliance on textual input during inference. Extensive experiments on two well-benchmarked datasets (IU-Xray and MIMIC-CXR) show that our DTrace outperforms state-of-the-art medical report generation methods.
Authors: Pengcheng Zhao, Yanxiang Chen, Yang Zhao, Wei Jia, Zhao Zhang, Ronggang Wang, Richang Hong
Automatic image colorization is inherently an ill-posed problem with uncertainty, which requires an accurate semantic understanding of scenes to estimate reasonable colors for grayscale images. Although recent interaction-based methods have achieved impressive performance, it is still a very difficult task to infer realistic and accurate colors for automatic colorization. To reduce the difficulty of semantic understanding of grayscale scenes, this paper tries to utilize corresponding audio, which naturally contains extra semantic information about the same scene. Specifically, a novel audio-infused automatic image colorization (AIAIC) network is proposed, which consists of three stages. First, we take color image semantics as a bridge and pretrain a colorization network guided by color image semantics. Second, the natural co-occurrence of audio and video is utilized to learn the color semantic correlations between audio and visual scenes. Third, the implicit audio semantic representation is fed into the pretrained network to finally realize the audio-guided colorization. The whole process is trained in a self-supervised manner without human annotation. In addition, an audiovisual colorization dataset is established for training and testing. Experiments demonstrate that audio guidance can effectively improve the performance of automatic colorization, especially for some scenes that are difficult to understand only from visual modality.
Authors: Ming-Chang Chiu, Yingfei Wang, Yen-Ju Kuo, Pin-Yu Chen
Skin tone as a demographic bias and inconsistent human labeling poses challenges in dermatology AI. We take another angle to investigate color contrast's impact, beyond skin tones, on malignancy detection in skin disease datasets: We hypothesize that in addition to skin tones, the color difference between the lesion area and skin also plays a role in malignancy detection performance of dermatology AI models. To study this, we first propose a robust labeling method to quantify color contrast scores of each image and validate our method by showing small labeling variations. More importantly, applying our method to \textit{the only} diverse-skin tone and pathologically-confirmed skin disease dataset DDI, yields \textbf{DDI-CoCo Dataset}, and we observe a performance gap between the high and low color difference groups. This disparity remains consistent across various state-of-the-art (SoTA) image classification models, which supports our hypothesis. Furthermore, we study the interaction between skin tone and color difference effects and suggest that color difference can be an additional reason behind model performance bias between skin tones. Our work provides a complementary angle to dermatology AI for improving skin disease detection.
Authors: Shengjing Tian, Yinan Han, Xiuping Liu, Xiantong Zhao
Single Object Tracking in LiDAR point cloud is one of the most essential parts of environmental perception, in which small objects are inevitable in real-world scenarios and will bring a significant barrier to the accurate location. However, the existing methods concentrate more on exploring universal architectures for common categories and overlook the challenges that small objects have long been thorny due to the relative deficiency of foreground points and a low tolerance for disturbances. To this end, we propose a Siamese network-based method for small object tracking in the LiDAR point cloud, which is composed of the target-awareness prototype mining (TAPM) module and the regional grid subdivision (RGS) module. The TAPM module adopts the reconstruction mechanism of the masked decoder to learn the prototype in the feature space, aiming to highlight the presence of foreground points that will facilitate the subsequent location of small objects. Through the above prototype is capable of accentuating the small object of interest, the positioning deviation in feature maps still leads to high tracking errors. To alleviate this issue, the RGS module is proposed to recover the fine-grained features of the search region based on ViT and pixel shuffle layers. In addition, apart from the normal settings, we elaborately design a scaling experiment to evaluate the robustness of the different trackers on small objects. Extensive experiments on KITTI and nuScenes demonstrate that our method can effectively improve the tracking performance of small targets without affecting normal-sized objects.
Authors: Julie Tores, Lucile Sassatelli, Hui-Yin Wu, Clement Bergman, Lea Andolfi, Victor Ecrement, Frederic Precioso, Thierry Devars, Magali Guaresi, Virginie Julliard, Sarah Lecossais
In film gender studies, the concept of 'male gaze' refers to the way the characters are portrayed on-screen as objects of desire rather than subjects. In this article, we introduce a novel video-interpretation task, to detect character objectification in films. The purpose is to reveal and quantify the usage of complex temporal patterns operated in cinema to produce the cognitive perception of objectification. We introduce the ObyGaze12 dataset, made of 1914 movie clips densely annotated by experts for objectification concepts identified in film studies and psychology. We evaluate recent vision models, show the feasibility of the task and where the challenges remain with concept bottleneck models. Our new dataset and code are made available to the community.
Authors: Yunjie Tian, Tianren Ma, Lingxi Xie, Jihao Qiu, Xi Tang, Yuan Zhang, Jianbin Jiao, Qi Tian, Qixiang Ye
In this study, we establish a baseline for a new task named multimodal multi-round referring and grounding (MRG), opening up a promising direction for instance-level multimodal dialogues. We present a new benchmark and an efficient vision-language model for this purpose. The new benchmark, named CB-300K, spans challenges including multi-round dialogue, complex spatial relationships among multiple instances, and consistent reasoning, which are beyond those shown in existing benchmarks. The proposed model, named ChatterBox, utilizes a two-branch architecture to collaboratively handle vision and language tasks. By tokenizing instance regions, the language branch acquires the ability to perceive referential information. Meanwhile, ChatterBox feeds a query embedding in the vision branch to a token receiver for visual grounding. A two-stage optimization strategy is devised, making use of both CB-300K and auxiliary external data to improve the model's stability and capacity for instance-level understanding. Experiments show that ChatterBox outperforms existing models in MRG both quantitatively and qualitatively, paving a new path towards multimodal dialogue scenarios with complicated and precise interactions. Code, data, and model are available at: https://github.com/sunsmarterjie/ChatterBox.
Authors: Rohan Wadhawan, Hritik Bansal, Kai-Wei Chang, Nanyun Peng
Recent advancements in AI have led to the development of large multimodal models (LMMs) capable of processing complex tasks involving joint reasoning over text and visual content in the image (e.g., navigating maps in public places). This paper introduces ConTextual, a novel benchmark comprising instructions designed explicitly to evaluate LMMs' ability to perform context-sensitive text-rich visual reasoning. ConTextual emphasizes diverse real-world scenarios (e.g., time-reading, navigation, shopping and more) demanding a deeper understanding of the interactions between textual and visual elements. Our findings reveal a significant performance gap of 30.8% between the best-performing LMM, GPT-4V(ision), and human capabilities using human evaluation indicating substantial room for improvement in context-sensitive text-rich visual reasoning. Notably, while GPT-4V excelled in abstract categories like meme and quote interpretation, its overall performance still lagged behind humans. In addition to human evaluations, we also employed automatic evaluation metrics using GPT-4, uncovering similar trends in performance disparities. We also perform a fine-grained evaluation across diverse visual contexts and provide qualitative analysis which provides a robust framework for future advancements in the LMM design. https://con-textual.github.io/
Authors: Ryota Tanaka, Taichi Iki, Kyosuke Nishida, Kuniko Saito, Jun Suzuki
We study the problem of completing various visual document understanding (VDU) tasks, e.g., question answering and information extraction, on real-world documents through human-written instructions. To this end, we propose InstructDoc, the first large-scale collection of 30 publicly available VDU datasets, each with diverse instructions in a unified format, which covers a wide range of 12 tasks and includes open document types/formats. Furthermore, to enhance the generalization performance on VDU tasks, we design a new instruction-based document reading and understanding model, InstructDr, that connects document images, image encoders, and large language models (LLMs) through a trainable bridging module. Experiments demonstrate that InstructDr can effectively adapt to new VDU datasets, tasks, and domains via given instructions and outperforms existing multimodal LLMs and ChatGPT without specific training.
Authors: Mathias Ramm Haugland, Hemin Ali Qadir, Ilangko Balasingham
To cope with the growing prevalence of colorectal cancer (CRC), screening programs for polyp detection and removal have proven their usefulness. Colonoscopy is considered the best-performing procedure for CRC screening. To ease the examination, deep learning based methods for automatic polyp detection have been developed for conventional white-light imaging (WLI). Compared with WLI, narrow-band imaging (NBI) can improve polyp classification during colonoscopy but requires special equipment. We propose a CycleGAN-based framework to convert images captured with regular WLI to synthetic NBI (SNBI) as a pre-processing method for improving object detection on WLI when NBI is unavailable. This paper first shows that better results for polyp detection can be achieved on NBI compared to a relatively similar dataset of WLI. Secondly, experimental results demonstrate that our proposed modality translation can achieve improved polyp detection on SNBI images generated from WLI compared to the original WLI. This is because our WLI-to-SNBI translation model can enhance the observation of polyp surface patterns in the generated SNBI images.
Authors: Yuanpeng Tu, Zhun Zhong, Yuxi Li, Hengshuang Zhao
Generalized category discovery (GCD) aims at addressing a more realistic and challenging setting of semi-supervised learning, where only part of the category labels are assigned to certain training samples. Previous methods generally employ naive contrastive learning or unsupervised clustering scheme for all the samples. Nevertheless, they usually ignore the inherent critical information within the historical predictions of the model being trained. Specifically, we empirically reveal that a significant number of salient unlabeled samples yield consistent historical predictions corresponding to their ground truth category. From this observation, we propose a Memory Consistency guided Divide-and-conquer Learning framework (MCDL). In this framework, we introduce two memory banks to record historical prediction of unlabeled data, which are exploited to measure the credibility of each sample in terms of its prediction consistency. With the guidance of credibility, we can design a divide-and-conquer learning strategy to fully utilize the discriminative information of unlabeled data while alleviating the negative influence of noisy labels. Extensive experimental results on multiple benchmarks demonstrate the generality and superiority of our method, where our method outperforms state-of-the-art models by a large margin on both seen and unseen classes of the generic image recognition and challenging semantic shift settings (i.e.,with +8.4% gain on CUB and +8.1% on Standford Cars).
Authors: Dezhao Luo, Jiabo Huang, Shaogang Gong, Hailin Jin, Yang Liu
Video Moment Retrieval (VMR) requires precise modelling of fine-grained moment-text associations to capture intricate visual-language relationships. Due to the lack of a diverse and generalisable VMR dataset to facilitate learning scalable moment-text associations, existing methods resort to joint training on both source and target domain videos for cross-domain applications. Meanwhile, recent developments in vision-language multimodal models pre-trained on large-scale image-text and/or video-text pairs are only based on coarse associations (weakly labelled). They are inadequate to provide fine-grained moment-text correlations required for cross-domain VMR. In this work, we solve the problem of unseen cross-domain VMR, where certain visual and textual concepts do not overlap across domains, by only utilising target domain sentences (text prompts) without accessing their videos. To that end, we explore generative video diffusion for fine-grained editing of source videos controlled by the target sentences, enabling us to simulate target domain videos. We address two problems in video editing for optimising unseen domain VMR: (1) generation of high-quality simulation videos of different moments with subtle distinctions, (2) selection of simulation videos that complement existing source training videos without introducing harmful noise or unnecessary repetitions. On the first problem, we formulate a two-stage video diffusion generation controlled simultaneously by (1) the original video structure of a source video, (2) subject specifics, and (3) a target sentence prompt. This ensures fine-grained variations between video moments. On the second problem, we introduce a hybrid selection mechanism that combines two quantitative metrics for noise filtering and one qualitative metric for leveraging VMR prediction on simulation video selection.
Authors: Matteo Gambella, Jary Pomponi, Simone Scardapane, Manuel Roveri
Early Exit Neural Networks (EENNs) endow astandard Deep Neural Network (DNN) with Early Exit Classifiers (EECs), to provide predictions at intermediate points of the processing when enough confidence in classification is achieved. This leads to many benefits in terms of effectiveness and efficiency. Currently, the design of EENNs is carried out manually by experts, a complex and time-consuming task that requires accounting for many aspects, including the correct placement, the thresholding, and the computational overhead of the EECs. For this reason, the research is exploring the use of Neural Architecture Search (NAS) to automatize the design of EENNs. Currently, few comprehensive NAS solutions for EENNs have been proposed in the literature, and a fully automated, joint design strategy taking into consideration both the backbone and the EECs remains an open problem. To this end, this work presents Neural Architecture Search for Hardware Constrained Early Exit Neural Networks (NACHOS), the first NAS framework for the design of optimal EENNs satisfying constraints on the accuracy and the number of Multiply and Accumulate (MAC) operations performed by the EENNs at inference time. In particular, this provides the joint design of backbone and EECs to select a set of admissible (i.e., respecting the constraints) Pareto Optimal Solutions in terms of best tradeoff between the accuracy and number of MACs. The results show that the models designed by NACHOS are competitive with the state-of-the-art EENNs. Additionally, this work investigates the effectiveness of two novel regularization terms designed for the optimization of the auxiliary classifiers of the EENN
Authors: Yangsen Chen, Hao Wang
The accurate 3D reconstruction of deformable soft body tissues from endoscopic videos is a pivotal challenge in medical applications such as VR surgery and medical image analysis. Existing methods often struggle with accuracy and the ambiguity of hallucinated tissue parts, limiting their practical utility. In this work, we introduce EndoGaussians, a novel approach that employs Gaussian Splatting for dynamic endoscopic 3D reconstruction. This method marks the first use of Gaussian Splatting in this context, overcoming the limitations of previous NeRF-based techniques. Our method sets new state-of-the-art standards, as demonstrated by quantitative assessments on various endoscope datasets. These advancements make our method a promising tool for medical professionals, offering more reliable and efficient 3D reconstructions for practical applications in the medical field.
Authors: Qi Cai, Xinrui Li, Yuanxin Wu
How to efficiently and accurately handle image matching outliers is a critical issue in two-view relative estimation. The prevailing RANSAC method necessitates that the minimal point pairs be inliers. This paper introduces a linear relative pose estimation algorithm for n $( n \geq 6$) point pairs, which is founded on the recent pose-only imaging geometry to filter out outliers by proper reweighting. The proposed algorithm is able to handle planar degenerate scenes, and enhance robustness and accuracy in the presence of a substantial ratio of outliers. Specifically, we embed the linear global translation (LiGT) constraint into the strategies of iteratively reweighted least-squares (IRLS) and RANSAC so as to realize robust outlier removal. Simulations and real tests of the Strecha dataset show that the proposed algorithm achieves relative rotation accuracy improvement of 2 $\sim$ 10 times in face of as large as 80% outliers.
Authors: Zhe Xu, Kun Wei, Xu Yang, Cheng Deng
Human dance generation (HDG) aims to synthesize realistic videos from images and sequences of driving poses. Despite great success, existing methods are limited to generating videos of a single person with specific backgrounds, while the generalizability for real-world scenarios with multiple persons and complex backgrounds remains unclear. To systematically measure the generalizability of HDG models, we introduce a new task, dataset, and evaluation protocol of compositional human dance generation (cHDG). Evaluating the state-of-the-art methods on cHDG, we empirically find that they fail to generalize to real-world scenarios. To tackle the issue, we propose a novel zero-shot framework, dubbed MultiDance-Zero, that can synthesize videos consistent with arbitrary multiple persons and background while precisely following the driving poses. Specifically, in contrast to straightforward DDIM or null-text inversion, we first present a pose-aware inversion method to obtain the noisy latent code and initialization text embeddings, which can accurately reconstruct the composed reference image. Since directly generating videos from them will lead to severe appearance inconsistency, we propose a compositional augmentation strategy to generate augmented images and utilize them to optimize a set of generalizable text embeddings. In addition, consistency-guided sampling is elaborated to encourage the background and keypoints of the estimated clean image at each reverse step to be close to those of the reference image, further improving the temporal consistency of generated videos. Extensive qualitative and quantitative results demonstrate the effectiveness and superiority of our approach.
Authors: Dong Han, Yong Li, Joachim Denzler
Face recognition technology has been deployed in various real-life applications. The most sophisticated deep learning-based face recognition systems rely on training millions of face images through complex deep neural networks to achieve high accuracy. It is quite common for clients to upload face images to the service provider in order to access the model inference. However, the face image is a type of sensitive biometric attribute tied to the identity information of each user. Directly exposing the raw face image to the service provider poses a threat to the user's privacy. Current privacy-preserving approaches to face recognition focus on either concealing visual information on model input or protecting model output face embedding. The noticeable drop in recognition accuracy is a pitfall for most methods. This paper proposes a hybrid frequency-color fusion approach to reduce the input dimensionality of face recognition in the frequency domain. Moreover, sparse color information is also introduced to alleviate significant accuracy degradation after adding differential privacy noise. Besides, an identity-specific embedding mapping scheme is applied to protect original face embedding by enlarging the distance among identities. Lastly, secure multiparty computation is implemented for safely computing the embedding distance during model inference. The proposed method performs well on multiple widely used verification datasets. Moreover, it has around 2.6% to 4.2% higher accuracy than the state-of-the-art in the 1:N verification scenario.
Authors: Wei Li, Xue Xu, Jiachen Liu, Xinyan Xiao
Existing text-to-image diffusion models primarily generate images from text prompts. However, the inherent conciseness of textual descriptions poses challenges in faithfully synthesizing images with intricate details, such as specific entities or scenes. This paper presents \textbf{UNIMO-G}, a simple multimodal conditional diffusion framework that operates on multimodal prompts with interleaved textual and visual inputs, which demonstrates a unified ability for both text-driven and subject-driven image generation. UNIMO-G comprises two core components: a Multimodal Large Language Model (MLLM) for encoding multimodal prompts, and a conditional denoising diffusion network for generating images based on the encoded multimodal input. We leverage a two-stage training strategy to effectively train the framework: firstly pre-training on large-scale text-image pairs to develop conditional image generation capabilities, and then instruction tuning with multimodal prompts to achieve unified image generation proficiency. A well-designed data processing pipeline involving language grounding and image segmentation is employed to construct multi-modal prompts. UNIMO-G excels in both text-to-image generation and zero-shot subject-driven synthesis, and is notably effective in generating high-fidelity images from complex multimodal prompts involving multiple image entities.
Authors: Chollette C. Olisah
Despite the advancement in computational modeling towards brain tumor segmentation, of which several models have been developed, it is evident from the computational complexity of existing models which are still at an all-time high, that performance and efficiency under clinical application scenarios are limited. Therefore, this paper proposes a shallow encoder and decoder network named SEDNet for brain tumor segmentation. The proposed network is adapted from the U-Net structure. Though brain tumors do not assume complex structures like the task the traditional U-Net was designed for, their variance in appearance, shape, and ambiguity of boundaries makes it a compelling complex task to solve. SEDNet architecture design is inspired by the localized nature of brain tumors in brain images, thus consists of sufficient hierarchical convolutional blocks in the encoding pathway capable of learning the intrinsic features of brain tumors in brain slices, and a decoding pathway with selective skip path sufficient for capturing miniature local-level spatial features alongside the global-level features of brain tumor. SEDNet with the integration of the proposed preprocessing algorithm and optimization function on the BraTS2020 set reserved for testing achieves impressive dice and Hausdorff scores of 0.9308, 0.9451, 0.9026, and 0.7040, 1.2866, 0.7762 for non-enhancing tumor core (NTC), peritumoral edema (ED), and enhancing tumor (ET), respectively. Furthermore, through transfer learning with initialized SEDNet pre-trained weights, termed SEDNetX, a performance increase is observed. The dice and Hausdorff scores recorded are 0.9336, 0.9478, 0.9061, 0.6983, 1.2691, and 0.7711 for NTC, ED, and ET, respectively. With about 1.3 million parameters and impressive performance in comparison to the state-of-the-art, SEDNet(X) is shown to be computationally efficient for real-time clinical diagnosis.
Authors: Dongmyoung Lee, Wei Chen, Nicolas Rojas
Object recognition and object pose estimation in robotic grasping continue to be significant challenges, since building a labelled dataset can be time consuming and financially costly in terms of data collection and annotation. In this work, we propose a synthetic data generation method that minimizes human intervention and makes downstream image segmentation algorithms more robust by combining a generated synthetic dataset with a smaller real-world dataset (hybrid dataset). Annotation experiments show that the proposed synthetic scene generation can diminish labelling time dramatically. RGB image segmentation is trained with hybrid dataset and combined with depth information to produce pixel-to-point correspondence of individual segmented objects. The object to grasp is then determined by the confidence score of the segmentation algorithm. Pick-and-place experiments demonstrate that segmentation trained on our hybrid dataset (98.9%, 70%) outperforms the real dataset and a publicly available dataset by (6.7%, 18.8%) and (2.8%, 10%) in terms of labelling and grasping success rate, respectively. Supplementary material is available at https://sites.google.com/view/synthetic-dataset-generation.
Authors: Xingyu Song, Zhan Li, Shi Chen, Kazuyuki Demachi
Current datasets for action recognition tasks face limitations stemming from traditional collection and generation methods, including the constrained range of action classes, absence of multi-viewpoint recordings, limited diversity, poor video quality, and labor-intensive manually collection. To address these challenges, we introduce GTAutoAct, a innovative dataset generation framework leveraging game engine technology to facilitate advancements in action recognition. GTAutoAct excels in automatically creating large-scale, well-annotated datasets with extensive action classes and superior video quality. Our framework's distinctive contributions encompass: (1) it innovatively transforms readily available coordinate-based 3D human motion into rotation-orientated representation with enhanced suitability in multiple viewpoints; (2) it employs dynamic segmentation and interpolation of rotation sequences to create smooth and realistic animations of action; (3) it offers extensively customizable animation scenes; (4) it implements an autonomous video capture and processing pipeline, featuring a randomly navigating camera, with auto-trimming and labeling functionalities. Experimental results underscore the framework's robustness and highlights its potential to significantly improve action recognition model training.
Authors: Gian Luca Marcialis, Paolo Mastinu, Fabio Roli
Serial, or sequential, fusion of multiple biometric matchers has been not thoroughly investigated so far. However, this approach exhibits some advantages with respect to the widely adopted parallel approaches. In this paper, we propose a novel theoretical framework for the assessment of performance of such systems, based on a previous work of the authors. Benefits in terms of performance are theoretically evaluated, as well as estimation errors in the model parameters computation. Model is analyzed from the viewpoint of its pros and cons, by mean of preliminary experiments performed on NIST Biometric Score Set 1.
Authors: Lang Nie, Chunyu Lin, Kang Liao, Shuaicheng Liu, Yao Zhao
Thin-plate spline (TPS) is a principal warp that allows for representing elastic, nonlinear transformation with control point motions. With the increase of control points, the warp becomes increasingly flexible but usually encounters a bottleneck caused by undesired issues, e.g., content distortion. In this paper, we explore generic applications of TPS in single-image-based warping tasks, such as rotation correction, rectangling, and portrait correction. To break this bottleneck, we propose the coupled thin-plate spline model (CoupledTPS), which iteratively couples multiple TPS with limited control points into a more flexible and powerful transformation. Concretely, we first design an iterative search to predict new control points according to the current latent condition. Then, we present the warping flow as a bridge for the coupling of different TPS transformations, effectively eliminating interpolation errors caused by multiple warps. Besides, in light of the laborious annotation cost, we develop a semi-supervised learning scheme to improve warping quality by exploiting unlabeled data. It is formulated through dual transformation between the searched control points of unlabeled data and its graphic augmentation, yielding an implicit correction consistency constraint. Finally, we collect massive unlabeled data to exhibit the benefit of our semi-supervised scheme in rotation correction. Extensive experiments demonstrate the superiority and universality of CoupledTPS over the existing state-of-the-art (SoTA) solutions for rotation correction and beyond. The code and data will be available at https://github.com/nie-lang/CoupledTPS.
Authors: Mihaela Croitor Ibrahim, Nishant Ravikumar, Alistair Curd, Joanna Leng, Oliver Umney, Michelle Peckham
Z-disks are complex structures that delineate repeating sarcomeres in striated muscle. They play significant roles in cardiomyocytes such as providing mechanical stability for the contracting sarcomere, cell signalling and autophagy. Changes in Z-disk architecture have been associated with impaired cardiac function. Hence, there is a strong need to create tools to segment Z-disks from microscopy images, that overcome traditional limitations such as variability in image brightness and staining technique. In this study, we apply deep learning based segmentation models to extract Z-disks in images of striated muscle tissue. We leverage a novel Airyscan confocal dataset, which comprises high resolution images of Z-disks of healthy heart tissue, stained with Affimers for specific Z-disk proteins. We employed an interactive labelling tool, Ilastik to obtain ground truth segmentation masks and use the resulting data set to train and evaluate the performance of several state-of-the-art segmentation networks. On the test set, UNet++ achieves best segmentation performance for Z-disks in cardiomyocytes, with an average Dice score of 0.91 and outperforms other established segmentation methods including UNet, FPN, DeepLabv3+ and pix2pix. However, pix2pix demonstrates improved generalisation, when tested on an additional dataset of cardiomyocytes with a titin mutation. This is the first study to demonstrate that automated machine learning-based segmentation approaches may be used effectively to segment Z-disks in confocal microscopy images. Automated segmentation approaches and predicted segmentation masks could be used to derive morphological features of Z-disks (e.g. width and orientation), and subsequently, to quantify disease-related changes to cardiac microstructure.
Authors: Siwei Wu, Yizhi Li, Kang Zhu, Ge Zhang, Yiming Liang, Kaijing Ma, Chenghao Xiao, Haoran Zhang, Bohao Yang, Wenhu Chen, Wenhao Huang, Noura Al Moubayed, Jie Fu, Chenghua Lin
Multi-modal information retrieval (MMIR) is a rapidly evolving field, where significant progress, particularly in image-text pairing, has been made through advanced representation learning and cross-modality alignment research. However, current benchmarks for evaluating MMIR performance in image-text pairing within the scientific domain show a notable gap, where chart and table images described in scholarly language usually do not play a significant role. To bridge this gap, we develop a specialised scientific MMIR (SciMMIR) benchmark by leveraging open-access paper collections to extract data relevant to the scientific domain. This benchmark comprises 530K meticulously curated image-text pairs, extracted from figures and tables with detailed captions in scientific documents. We further annotate the image-text pairs with two-level subset-subcategory hierarchy annotations to facilitate a more comprehensive evaluation of the baselines. We conducted zero-shot and fine-tuning evaluations on prominent multi-modal image-captioning and visual language models, such as CLIP and BLIP. Our analysis offers critical insights for MMIR in the scientific domain, including the impact of pre-training and fine-tuning settings and the influence of the visual and textual encoders. All our data and checkpoints are publicly available at https://github.com/Wusiwei0410/SciMMIR.
Authors: Maofa Wang, Bingchen Yan
Few-shot image classification has emerged as a key challenge in the field of computer vision, highlighting the capability to rapidly adapt to new tasks with minimal labeled data. Existing methods predominantly rely on image-level features or local descriptors, often overlooking the holistic context surrounding these descriptors. In this work, we introduce a novel approach termed "Local Descriptor with Contextual Augmentation (LDCA)". Specifically, this method bridges the gap between local and global understanding uniquely by leveraging an adaptive global contextual enhancement module. This module incorporates a visual transformer, endowing local descriptors with contextual awareness capabilities, ranging from broad global perspectives to intricate surrounding nuances. By doing so, LDCA transcends traditional descriptor-based approaches, ensuring each local feature is interpreted within its larger visual narrative. Extensive experiments underscore the efficacy of our method, showing a maximal absolute improvement of 20\% over the next-best on fine-grained classification datasets, thus demonstrating significant advancements in few-shot classification tasks.
Authors: Hai-Xin Zhang, Dong Huang, Hua-Bao Ling, Guang-Yu Zhang, Wei-jun Sun, Zi-hao Wen
In this paper, we present a novel deep image clustering approach termed PICI, which enforces the partial information discrimination and the cross-level interaction in a joint learning framework. In particular, we leverage a Transformer encoder as the backbone, through which the masked image modeling with two paralleled augmented views is formulated. After deriving the class tokens from the masked images by the Transformer encoder, three partial information learning modules are further incorporated, including the PISD module for training the auto-encoder via masked image reconstruction, the PICD module for employing two levels of contrastive learning, and the CLI module for mutual interaction between the instance-level and cluster-level subspaces. Extensive experiments have been conducted on six real-world image datasets, which demononstrate the superior clustering performance of the proposed PICI approach over the state-of-the-art deep clustering approaches. The source code is available at https://github.com/Regan-Zhang/PICI.
Authors: Xinyu Yang, Jizhe Zhou
In recent years, particularly since the early 2020s, Large Language Models (LLMs) have emerged as the most powerful AI tools in addressing a diverse range of challenges, from natural language processing to complex problem-solving in various domains. In the field of tamper detection, LLMs are capable of identifying basic tampering activities.To assess the capabilities of LLMs in more specialized domains, we have collected five different LLMs developed by various companies: GPT-4, LLaMA, Bard, ERNIE Bot 4.0, and Tongyi Qianwen. This diverse range of models allows for a comprehensive evaluation of their performance in detecting sophisticated tampering instances.We devised two domains of detection: AI-Generated Content (AIGC) detection and manipulation detection. AIGC detection aims to test the ability to distinguish whether an image is real or AI-generated. Manipulation detection, on the other hand, focuses on identifying tampered images. According to our experiments, most LLMs can identify composite pictures that are inconsistent with logic, and only more powerful LLMs can distinguish logical, but visible signs of tampering to the human eye. All of the LLMs can't identify carefully forged images and very realistic images generated by AI. In the area of tamper detection, LLMs still have a long way to go, particularly in reliably identifying highly sophisticated forgeries and AI-generated images that closely mimic reality.
Authors: Chuan Guo, Yuxuan Mu, Xinxin Zuo, Peng Dai, Youliang Yan, Juwei Lu, Li Cheng
Human motion stylization aims to revise the style of an input motion while keeping its content unaltered. Unlike existing works that operate directly in pose space, we leverage the latent space of pretrained autoencoders as a more expressive and robust representation for motion extraction and infusion. Building upon this, we present a novel generative model that produces diverse stylization results of a single motion (latent) code. During training, a motion code is decomposed into two coding components: a deterministic content code, and a probabilistic style code adhering to a prior distribution; then a generator massages the random combination of content and style codes to reconstruct the corresponding motion codes. Our approach is versatile, allowing the learning of probabilistic style space from either style labeled or unlabeled motions, providing notable flexibility in stylization as well. In inference, users can opt to stylize a motion using style cues from a reference motion or a label. Even in the absence of explicit style input, our model facilitates novel re-stylization by sampling from the unconditional style prior distribution. Experimental results show that our proposed stylization models, despite their lightweight design, outperform the state-of-the-arts in style reeanactment, content preservation, and generalization across various applications and settings. Project Page: https://yxmu.foo/GenMoStyle
Authors: Ruben T. Lucassen, Willeke A. M. Blokx, Mitko Veta
Tissue segmentation is a routine preprocessing step to reduce the computational cost of whole slide image (WSI) analysis by excluding background regions. Traditional image processing techniques are commonly used for tissue segmentation, but often require manual adjustments to parameter values for atypical cases, fail to exclude all slide and scanning artifacts from the background, and are unable to segment adipose tissue. Pen marking artifacts in particular can be a potential source of bias for subsequent analyses if not removed. In addition, several applications require the separation of individual cross-sections, which can be challenging due to tissue fragmentation and adjacent positioning. To address these problems, we develop a convolutional neural network for tissue and pen marking segmentation using a dataset of 200 H&E stained WSIs. For separating tissue cross-sections, we propose a novel post-processing method based on clustering predicted centroid locations of the cross-sections in a 2D histogram. On an independent test set, the model achieved a mean Dice score of 0.981$\pm$0.033 for tissue segmentation and a mean Dice score of 0.912$\pm$0.090 for pen marking segmentation. The mean absolute difference between the number of annotated and separated cross-sections was 0.075$\pm$0.350. Our results demonstrate that the proposed model can accurately segment H&E stained tissue cross-sections and pen markings in WSIs while being robust to many common slide and scanning artifacts. The model with trained model parameters and post-processing method are made publicly available as a Python package called SlideSegmenter.
Authors: Juan Hu, Xin Liao, Difei Gao, Satoshi Tsutsui, Qian Wang, Zheng Qin, Mike Zheng Shou
Deepfake videos are becoming increasingly realistic, showing subtle tampering traces on facial areasthat vary between frames. Consequently, many existing Deepfake detection methods struggle to detect unknown domain Deepfake videos while accurately locating the tampered region. To address thislimitation, we propose Delocate, a novel Deepfake detection model that can both recognize andlocalize unknown domain Deepfake videos. Ourmethod consists of two stages named recoveringand localization. In the recovering stage, the modelrandomly masks regions of interest (ROIs) and reconstructs real faces without tampering traces, resulting in a relatively good recovery effect for realfaces and a poor recovery effect for fake faces. Inthe localization stage, the output of the recoveryphase and the forgery ground truth mask serve assupervision to guide the forgery localization process. This process strategically emphasizes the recovery phase of fake faces with poor recovery, facilitating the localization of tampered regions. Ourextensive experiments on four widely used benchmark datasets demonstrate that Delocate not onlyexcels in localizing tampered areas but also enhances cross-domain detection performance.
Authors: Zengbin Wang, Saihui Hou, Man Zhang, Xu Liu, Chunshui Cao, Yongzhen Huang, Peipei Li, Shibiao Xu
Gait recognition is a promising biometric method that aims to identify pedestrians from their unique walking patterns. Silhouette modality, renowned for its easy acquisition, simple structure, sparse representation, and convenient modeling, has been widely employed in controlled in-the-lab research. However, as gait recognition rapidly advances from in-the-lab to in-the-wild scenarios, various conditions raise significant challenges for silhouette modality, including 1) unidentifiable low-quality silhouettes (abnormal segmentation, severe occlusion, or even non-human shape), and 2) identifiable but challenging silhouettes (background noise, non-standard posture, slight occlusion). To address these challenges, we revisit gait recognition pipeline and approach gait recognition from a quality perspective, namely QAGait. Specifically, we propose a series of cost-effective quality assessment strategies, including Maxmial Connect Area and Template Match to eliminate background noises and unidentifiable silhouettes, Alignment strategy to handle non-standard postures. We also propose two quality-aware loss functions to integrate silhouette quality into optimization within the embedding space. Extensive experiments demonstrate our QAGait can guarantee both gait reliability and performance enhancement. Furthermore, our quality assessment strategies can seamlessly integrate with existing gait datasets, showcasing our superiority. Code is available at https://github.com/wzb-bupt/QAGait.
Authors: Yongwei Nie, Hao Huang, Chengjiang Long, Qing Zhang, Pradipta Maji, Hongmin Cai
Without human annotations, a typical Unsupervised Video Anomaly Detection (UVAD) method needs to train two models that generate pseudo labels for each other. In previous work, the two models are closely entangled with each other, and it is not known how to upgrade their method without modifying their training framework significantly. Second, previous work usually adopts fixed thresholding to obtain pseudo labels, however the user-specified threshold is not reliable which inevitably introduces errors into the training process. To alleviate these two problems, we propose a novel interleaved framework that alternately trains a One-Class Classification (OCC) model and a Weakly-Supervised (WS) model for UVAD. The OCC or WS models in our method can be easily replaced with other OCC or WS models, which facilitates our method to upgrade with the most recent developments in both fields. For handling the fixed thresholding problem, we break through the conventional cognitive boundary and propose a weighted OCC model that can be trained on both normal and abnormal data. We also propose an adaptive mechanism for automatically finding the optimal threshold for the WS model in a loose to strict manner. Experiments demonstrate that the proposed UVAD method outperforms previous approaches.
Authors: Otto Brookes, Majid Mirmehdi, Colleen Stephens, Samuel Angedakin, Katherine Corogenes, Dervla Dowd, Paula Dieguez, Thurston C. Hicks, Sorrel Jones, Kevin Lee, Vera Leinert, Juan Lapuente, Maureen S. McCarthy, Amelia Meier, Mizuki Murai, Emmanuelle Normand, Virginie Vergnes, Erin G. Wessling, Roman M. Wittig, Kevin Langergraber, Nuria Maldonado, Xinyu Yang, Klaus Zuberbuhler, Christophe Boesch, Mimi Arandjelovic, Hjalmar Kuhl, Tilo Burghardt
We present the PanAf20K dataset, the largest and most diverse open-access annotated video dataset of great apes in their natural environment. It comprises more than 7 million frames across ~20,000 camera trap videos of chimpanzees and gorillas collected at 18 field sites in tropical Africa as part of the Pan African Programme: The Cultured Chimpanzee. The footage is accompanied by a rich set of annotations and benchmarks making it suitable for training and testing a variety of challenging and ecologically important computer vision tasks including ape detection and behaviour recognition. Furthering AI analysis of camera trap information is critical given the International Union for Conservation of Nature now lists all species in the great ape family as either Endangered or Critically Endangered. We hope the dataset can form a solid basis for engagement of the AI community to improve performance, efficiency, and result interpretation in order to support assessments of great ape presence, abundance, distribution, and behaviour and thereby aid conservation efforts.
Authors: Mike Laszkiewicz, Imant Daunhawer, Julia E. Vogt, Asja Fischer, Johannes Lederer
Recent years have witnessed a rapid development of deep generative models for creating synthetic media, such as images and videos. While the practical applications of these models in everyday tasks are enticing, it is crucial to assess the inherent risks regarding their fairness. In this work, we introduce a comprehensive framework for benchmarking the performance and fairness of conditional generative models. We develop a set of metrics$\unicode{x2013}$inspired by their supervised fairness counterparts$\unicode{x2013}$to evaluate the models on their fairness and diversity. Focusing on the specific application of image upsampling, we create a benchmark covering a wide variety of modern upsampling methods. As part of the benchmark, we introduce UnfairFace, a subset of FairFace that replicates the racial distribution of common large-scale face datasets. Our empirical study highlights the importance of using an unbiased training set and reveals variations in how the algorithms respond to dataset imbalances. Alarmingly, we find that none of the considered methods produces statistically fair and diverse results.
Authors: Zhaohu Xing, Tian Ye, Yijun Yang, Guang Liu, Lei Zhu
The Transformer architecture has shown a remarkable ability in modeling global relationships. However, it poses a significant computational challenge when processing high-dimensional medical images. This hinders its development and widespread adoption in this task. Mamba, as a State Space Model (SSM), recently emerged as a notable manner for long-range dependencies in sequential modeling, excelling in natural language processing filed with its remarkable memory efficiency and computational speed. Inspired by its success, we introduce SegMamba, a novel 3D medical image \textbf{Seg}mentation \textbf{Mamba} model, designed to effectively capture long-range dependencies within whole volume features at every scale. Our SegMamba, in contrast to Transformer-based methods, excels in whole volume feature modeling from a state space model standpoint, maintaining superior processing speed, even with volume features at a resolution of {$64\times 64\times 64$}. Comprehensive experiments on the BraTS2023 dataset demonstrate the effectiveness and efficiency of our SegMamba. The code for SegMamba is available at: https://github.com/ge-xing/SegMamba
Authors: Haixin Zhang, Dong Huang
Previous contrastive deep clustering methods mostly focus on instance-level information while overlooking the member relationship within groups/clusters, which may significantly undermine their representation learning and clustering capability. Recently, some group-contrastive methods have been developed, which, however, typically rely on the samples of the entire dataset to obtain pseudo labels and lack the ability to efficiently update the group assignments in a batch-wise manner. To tackle these critical issues, we present a novel end-to-end deep clustering framework with dynamic grouping and prototype aggregation, termed as DigPro. Specifically, the proposed dynamic grouping extends contrastive learning from instance-level to group-level, which is effective and efficient for timely updating groups. Meanwhile, we perform contrastive learning on prototypes in a spherical feature space, termed as prototype aggregation, which aims to maximize the inter-cluster distance. Notably, with an expectation-maximization framework, DigPro simultaneously takes advantage of compact intra-cluster connections, well-separated clusters, and efficient group updating during the self-supervised training. Extensive experiments on six image benchmarks demonstrate the superior performance of our approach over the state-of-the-art. Code is available at https://github.com/Regan-Zhang/DigPro.
Authors: Rodrigo Aldana-López, Rosario Aragüés, Carlos Sagüés
Target tracking is a popular problem with many potential applications. There has been a lot of effort on improving the quality of the detection of targets using cameras through different techniques. In general, with higher computational effort applied, i.e., a longer perception-latency, a better detection accuracy is obtained. However, it is not always useful to apply the longest perception-latency allowed, particularly when the environment doesn't require to and when the computational resources are shared between other tasks. In this work, we propose a new Perception-LATency aware Estimator (PLATE), which uses different perception configurations in different moments of time in order to optimize a certain performance measure. This measure takes into account a perception-latency and accuracy trade-off aiming for a good compromise between quality and resource usage. Compared to other heuristic frame-skipping techniques, PLATE comes with a formal complexity and optimality analysis. The advantages of PLATE are verified by several experiments including an evaluation over a standard benchmark with real data and using state of the art deep learning object detection methods for the perception stage.
Authors: Naresh Kumar Lahajal, Harini S
Photo search, the task of retrieving images based on textual queries, has witnessed significant advancements with the introduction of CLIP (Contrastive Language-Image Pretraining) model. CLIP leverages a vision-language pre training approach, wherein it learns a shared representation space for images and text, enabling cross-modal understanding. This model demonstrates the capability to understand the semantic relationships between diverse image and text pairs, allowing for efficient and accurate retrieval of images based on natural language queries. By training on a large-scale dataset containing images and their associated textual descriptions, CLIP achieves remarkable generalization, providing a powerful tool for tasks such as zero-shot learning and few-shot classification. This abstract summarizes the foundational principles of CLIP and highlights its potential impact on advancing the field of photo search, fostering a seamless integration of natural language understanding and computer vision for improved information retrieval in multimedia applications
Authors: Xi Zhang, Xiaolin Wu
Recently, DNN models for lossless image coding have surpassed their traditional counterparts in compression performance, reducing the bit rate by about ten percent for natural color images. But even with these advances, mathematically lossless image compression (MLLIC) ratios for natural images still fall short of the bandwidth and cost-effectiveness requirements of most practical imaging and vision systems at present and beyond. To break the bottleneck of MLLIC in compression performance, we question the necessity of MLLIC, as almost all digital sensors inherently introduce acquisition noises, making mathematically lossless compression counterproductive. Therefore, in contrast to MLLIC, we propose a new paradigm of joint denoising and compression called functionally lossless image compression (FLLIC), which performs lossless compression of optimally denoised images (the optimality may be task-specific). Although not literally lossless with respect to the noisy input, FLLIC aims to achieve the best possible reconstruction of the latent noise-free original image. Extensive experiments show that FLLIC achieves state-of-the-art performance in joint denoising and compression of noisy images and does so at a lower computational cost.
Authors: Fanghua Yu, Jinjin Gu, Zheyuan Li, Jinfan Hu, Xiangtao Kong, Xintao Wang, Jingwen He, Yu Qiao, Chao Dong
We introduce SUPIR (Scaling-UP Image Restoration), a groundbreaking image restoration method that harnesses generative prior and the power of model scaling up. Leveraging multi-modal techniques and advanced generative prior, SUPIR marks a significant advance in intelligent and realistic image restoration. As a pivotal catalyst within SUPIR, model scaling dramatically enhances its capabilities and demonstrates new potential for image restoration. We collect a dataset comprising 20 million high-resolution, high-quality images for model training, each enriched with descriptive text annotations. SUPIR provides the capability to restore images guided by textual prompts, broadening its application scope and potential. Moreover, we introduce negative-quality prompts to further improve perceptual quality. We also develop a restoration-guided sampling method to suppress the fidelity issue encountered in generative-based restoration. Experiments demonstrate SUPIR's exceptional restoration effects and its novel capacity to manipulate restoration through textual prompts.
Authors: Ivan DeAndres-Tame, Ruben Tolosana, Ruben Vera-Rodriguez, Aythami Morales, Julian Fierrez, Javier Ortega-Garcia
Large Language Models (LLMs) such as GPT developed by OpenAI, have already shown astonishing results, introducing quick changes in our society. This has been intensified by the release of ChatGPT which allows anyone to interact in a simple conversational way with LLMs, without any experience in the field needed. As a result, ChatGPT has been rapidly applied to many different tasks such as code- and song-writer, education, virtual assistants, etc., showing impressive results for tasks for which it was not trained (zero-shot learning).
The present study aims to explore the ability of ChatGPT, based on the recent GPT-4 multimodal LLM, for the task of face biometrics. In particular, we analyze the ability of ChatGPT to perform tasks such as face verification, soft-biometrics estimation, and explainability of the results. ChatGPT could be very valuable to further increase the explainability and transparency of the automatic decisions in human scenarios. Experiments are carried out in order to evaluate the performance and robustness of ChatGPT, using popular public benchmarks and comparing the results with state-of-the-art methods in the field. The results achieved in this study show the potential of LLMs such as ChatGPT for face biometrics, especially to enhance explainability. For reproducibility reasons, we release all the code in GitHub.
Authors: Jing Yu Koh, Robert Lo, Lawrence Jang, Vikram Duvvur, Ming Chong Lim, Po-Yu Huang, Graham Neubig, Shuyan Zhou, Ruslan Salakhutdinov, Daniel Fried
Autonomous agents capable of planning, reasoning, and executing actions on the web offer a promising avenue for automating computer tasks. However, the majority of existing benchmarks primarily focus on text-based agents, neglecting many natural tasks that require visual information to effectively solve. Given that most computer interfaces cater to human perception, visual information often augments textual data in ways that text-only models struggle to harness effectively. To bridge this gap, we introduce VisualWebArena, a benchmark designed to assess the performance of multimodal web agents on realistic \textit{visually grounded tasks}. VisualWebArena comprises of a set of diverse and complex web-based tasks that evaluate various capabilities of autonomous multimodal agents. To perform on this benchmark, agents need to accurately process image-text inputs, interpret natural language instructions, and execute actions on websites to accomplish user-defined objectives. We conduct an extensive evaluation of state-of-the-art LLM-based autonomous agents, including several multimodal models. Through extensive quantitative and qualitative analysis, we identify several limitations of text-only LLM agents, and reveal gaps in the capabilities of state-of-the-art multimodal language agents. VisualWebArena provides a framework for evaluating multimodal autonomous language agents, and offers insights towards building stronger autonomous agents for the web. Our code, baseline models, and data is publicly available at https://jykoh.com/vwa.
Authors: Marianne Rakic, Hallee E. Wong, Jose Javier Gonzalez Ortiz, Beth Cimini, John Guttag, Adrian V. Dalca
Existing learning-based solutions to medical image segmentation have two important shortcomings. First, for most new segmentation task, a new model has to be trained or fine-tuned. This requires extensive resources and machine learning expertise, and is therefore often infeasible for medical researchers and clinicians. Second, most existing segmentation methods produce a single deterministic segmentation mask for a given image. In practice however, there is often considerable uncertainty about what constitutes the correct segmentation, and different expert annotators will often segment the same image differently. We tackle both of these problems with Tyche, a model that uses a context set to generate stochastic predictions for previously unseen tasks without the need to retrain. Tyche differs from other in-context segmentation methods in two important ways. (1) We introduce a novel convolution block architecture that enables interactions among predictions. (2) We introduce in-context test-time augmentation, a new mechanism to provide prediction stochasticity. When combined with appropriate model design and loss functions, Tyche can predict a set of plausible diverse segmentation candidates for new or unseen medical images and segmentation tasks without the need to retrain.
Authors: Anvar Kabulov, Alimdzhan Babadzhanov, Islambek Saymanov
In this paper, we propose to consider various models of pattern recognition. At the same time, it is proposed to consider models in the form of two operators: a recognizing operator and a decision rule. Algebraic operations are introduced on recognizing operators, and based on the application of these operators, a family of recognizing algorithms is created. An upper estimate is constructed for the model, which guarantees the completeness of the extension.
Authors: Weilin Cong, William Wang, Wang-Chien Lee
Despite the great success object detection and segmentation models have achieved in recognizing individual objects in images, performance on cognitive tasks such as image caption, semantic image retrieval, and visual QA is far from satisfactory. To achieve better performance on these cognitive tasks, merely recognizing individual object instances is insufficient. Instead, the interactions between object instances need to be captured in order to facilitate reasoning and understanding of the visual scenes in an image. Scene graph, a graph representation of images that captures object instances and their relationships, offers a comprehensive understanding of an image. However, existing techniques on scene graph generation fail to distinguish subjects and objects in the visual scenes of images and thus do not perform well with real-world datasets where exist ambiguous object instances. In this work, we propose a novel scene graph generation model for predicting object instances and its corresponding relationships in an image. Our model, SG-CRF, learns the sequential order of subject and object in a relationship triplet, and the semantic compatibility of object instance nodes and relationship nodes in a scene graph efficiently. Experiments empirically show that SG-CRF outperforms the state-of-the-art methods, on three different datasets, i.e., CLEVR, VRD, and Visual Genome, raising the Recall@100 from 24.99% to 49.95%, from 41.92% to 50.47%, and from 54.69% to 54.77%, respectively.
Authors: Yassir Zardoua, Boulaala Mohammed, Mhamed El Mrabet, Astito Abdelali
Accurate and fast sea horizon detection is vital for tasks in autonomous navigation and maritime security, such as video stabilization, target region reduction, precise tracking, and obstacle avoidance. This paper introduces a novel sea horizon detector from RGB videos, focusing on rapid and effective sea noise suppression while preserving weak horizon edges. Line fitting methods are subsequently employed on filtered edges for horizon detection. We address the filtering problem by extracting line segments with a very low edge threshold, ensuring the detection of line segments even in low-contrast horizon conditions. We show that horizon line segments have simple and relevant properties in RGB images, which we exploit to suppress noisy segments. Then we use the surviving segments to construct a filtered edge map and infer the horizon from the filtered edges. We propose a careful incorporation of temporal information for horizon inference and experimentally show its effectiveness. We address the computational constraint by providing a vectorized implementation for efficient CPU execution, and leveraging image downsizing with minimal loss of accuracy on the original size. Moreover, we contribute a public horizon line dataset to enrich existing data resources. Our algorithm's performance is rigorously evaluated against state-of-the-art methods, and its components are validated through ablation experiments. Source code and dataset files are available at:
Authors: Sara Abdali, Sina shaham, Bhaskar Krishnamachari
As social media platforms are evolving from text-based forums into multi-modal environments, the nature of misinformation in social media is also transforming accordingly. Taking advantage of the fact that visual modalities such as images and videos are more favorable and attractive to the users and textual contents are sometimes skimmed carelessly, misinformation spreaders have recently targeted contextual connections between the modalities e.g., text and image. Hence many researchers have developed automatic techniques for detecting possible cross-modal discordance in web-based content. We analyze, categorize and identify existing approaches in addition to challenges and shortcomings they face in order to unearth new research opportunities in the field of multi-modal misinformation detection.
Authors: S.H.Shabbeer Basha, Debapriya Tula, Sravan Kumar Vinakota, Shiv Ram Dubey
Transfer Learning enables Convolutional Neural Networks (CNN) to acquire knowledge from a source domain and transfer it to a target domain, where collecting large-scale annotated examples is time-consuming and expensive. Conventionally, while transferring the knowledge learned from one task to another task, the deeper layers of a pre-trained CNN are finetuned over the target dataset. However, these layers are originally designed for the source task which may be over-parameterized for the target task. Thus, finetuning these layers over the target dataset may affect the generalization ability of the CNN due to high network complexity. To tackle this problem, we propose a two-stage framework called TASCNet which enables efficient knowledge transfer. In the first stage, the configuration of the deeper layers is learned automatically and finetuned over the target dataset. Later, in the second stage, the redundant filters are pruned from the fine-tuned CNN to decrease the network's complexity for the target task while preserving the performance. This two-stage mechanism finds a compact version of the pre-trained CNN with optimal structure (number of filters in a convolutional layer, number of neurons in a dense layer, and so on) from the hypothesis space. The efficacy of the proposed method is evaluated using VGG-16, ResNet-50, and DenseNet-121 on CalTech-101, CalTech-256, and Stanford Dogs datasets. Similar to computer vision tasks, we have also conducted experiments on Movie Review Sentiment Analysis task. The proposed TASCNet reduces the computational complexity of pre-trained CNNs over the target task by reducing both trainable parameters and FLOPs which enables resource-efficient knowledge transfer. The source code is available at: https://github.com/Debapriya-Tula/TASCNet.
Authors: Yang Liu, Shen Yan, Laura Leal-Taixé, James Hays, Deva Ramanan
Modern neural networks are over-parameterized and thus rely on strong regularization such as data augmentation and weight decay to reduce overfitting and improve generalization. The dominant form of data augmentation applies invariant transforms, where the learning target of a sample is invariant to the transform applied to that sample. We draw inspiration from human visual classification studies and propose generalizing augmentation with invariant transforms to soft augmentation where the learning target softens non-linearly as a function of the degree of the transform applied to the sample: e.g., more aggressive image crop augmentations produce less confident learning targets. We demonstrate that soft targets allow for more aggressive data augmentation, offer more robust performance boosts, work with other augmentation policies, and interestingly, produce better calibrated models (since they are trained to be less confident on aggressively cropped/occluded examples). Combined with existing aggressive augmentation strategies, soft target 1) doubles the top-1 accuracy boost across Cifar-10, Cifar-100, ImageNet-1K, and ImageNet-V2, 2) improves model occlusion performance by up to $4\times$, and 3) halves the expected calibration error (ECE). Finally, we show that soft augmentation generalizes to self-supervised classification tasks. Code available at https://github.com/youngleox/soft_augmentation
Authors: T. Windeatt
A new method of detecting adversarial attacks is proposed for an ensemble of Deep Neural Networks (DNNs) solving two-class pattern recognition problems. The ensemble is combined using Walsh coefficients which are capable of approximating Boolean functions and thereby controlling the complexity of the ensemble decision boundary. The hypothesis in this paper is that decision boundaries with high curvature allow adversarial perturbations to be found, but change the curvature of the decision boundary, which is then approximated in a different way by Walsh coefficients compared to the clean images. By observing the difference in Walsh coefficient approximation between clean and adversarial images, it is shown experimentally that transferability of attack may be used for detection. Furthermore, approximating the decision boundary may aid in understanding the learning and transferability properties of DNNs. While the experiments here use images, the proposed approach of modelling two-class ensemble decision boundaries could in principle be applied to any application area. Code for approximating Boolean functions using Walsh coefficients: https://doi.org/10.24433/CO.3695905.v1
Authors: Xiangming Meng, Yoshiyuki Kabashima
We consider the ubiquitous linear inverse problems with additive Gaussian noise and propose an unsupervised sampling approach called diffusion model based posterior sampling (DMPS) to reconstruct the unknown signal from noisy linear measurements. Specifically, using one diffusion model (DM) as an implicit prior, the fundamental difficulty in performing posterior sampling is that the noise-perturbed likelihood score, i.e., gradient of an annealed likelihood function, is intractable. To circumvent this problem, we introduce a simple yet effective closed-form approximation using an uninformative prior assumption. Extensive experiments are conducted on a variety of noisy linear inverse problems such as noisy super-resolution, denoising, deblurring, and colorization. In all tasks, the proposed DMPS demonstrates highly competitive or even better performances on various tasks while being 3 times faster than the state-of-the-art competitor diffusion posterior sampling (DPS).
Authors: Claudio Turchetti, Laura Falaschetti
The aim of this paper is to present a mathematical framework for tensor PCA. The proposed approach is able to overcome the limitations of previous methods that extract a low dimensional subspace by iteratively solving an optimization problem. The core of the proposed approach is the derivation of a basis in tensor space from a real self-adjoint tensor operator, thus reducing the problem of deriving a basis to an eigenvalue problem. Three different cases have been studied to derive: i) a basis from a self-adjoint tensor operator; ii) a rank-1 basis; iii) a basis in a subspace. In particular, the equivalence between eigenvalue equation for a real self-adjoint tensor operator and standard matrix eigenvalue equation has been proven. For all the three cases considered, a subspace approach has been adopted to derive a tensor PCA. Experiments on image datasets validate the proposed mathematical framework.
Authors: Shanchuan Lin, Bingchen Liu, Jiashi Li, Xiao Yang
We discover that common diffusion noise schedules do not enforce the last timestep to have zero signal-to-noise ratio (SNR), and some implementations of diffusion samplers do not start from the last timestep. Such designs are flawed and do not reflect the fact that the model is given pure Gaussian noise at inference, creating a discrepancy between training and inference. We show that the flawed design causes real problems in existing implementations. In Stable Diffusion, it severely limits the model to only generate images with medium brightness and prevents it from generating very bright and dark samples. We propose a few simple fixes: (1) rescale the noise schedule to enforce zero terminal SNR; (2) train the model with v prediction; (3) change the sampler to always start from the last timestep; (4) rescale classifier-free guidance to prevent over-exposure. These simple changes ensure the diffusion process is congruent between training and inference and allow the model to generate samples more faithful to the original data distribution.
Authors: Rui Cao, Jing Jiang
Large-scale pre-trained models (PTMs) show great zero-shot capabilities. In this paper, we study how to leverage them for zero-shot visual question answering (VQA). Our approach is motivated by a few observations. First, VQA questions often require multiple steps of reasoning, which is still a capability that most PTMs lack. Second, different steps in VQA reasoning chains require different skills such as object detection and relational reasoning, but a single PTM may not possess all these skills. Third, recent work on zero-shot VQA does not explicitly consider multi-step reasoning chains, which makes them less interpretable compared with a decomposition-based approach. We propose a modularized zero-shot network that explicitly decomposes questions into sub reasoning steps and is highly interpretable. We convert sub reasoning tasks to acceptable objectives of PTMs and assign tasks to proper PTMs without any adaptation. Our experiments on two VQA benchmarks under the zero-shot setting demonstrate the effectiveness of our method and better interpretability compared with several baselines.
Authors: Pum Jun Kim, Yoojin Jang, Jisu Kim, Jaejun Yoo
We propose a robust and reliable evaluation metric for generative models by introducing topological and statistical treatments for rigorous support estimation. Existing metrics, such as Inception Score (IS), Frechet Inception Distance (FID), and the variants of Precision and Recall (P&R), heavily rely on supports that are estimated from sample features. However, the reliability of their estimation has not been seriously discussed (and overlooked) even though the quality of the evaluation entirely depends on it. In this paper, we propose Topological Precision and Recall (TopP&R, pronounced 'topper'), which provides a systematic approach to estimating supports, retaining only topologically and statistically important features with a certain level of confidence. This not only makes TopP&R strong for noisy features, but also provides statistical consistency. Our theoretical and experimental results show that TopP&R is robust to outliers and non-independent and identically distributed (Non-IID) perturbations, while accurately capturing the true trend of change in samples. To the best of our knowledge, this is the first evaluation metric focused on the robust estimation of the support and provides its statistical consistency under noise.
Authors: Royi Rassin, Eran Hirsch, Daniel Glickman, Shauli Ravfogel, Yoav Goldberg, Gal Chechik
Text-conditioned image generation models often generate incorrect associations between entities and their visual attributes. This reflects an impaired mapping between linguistic binding of entities and modifiers in the prompt and visual binding of the corresponding elements in the generated image. As one notable example, a query like "a pink sunflower and a yellow flamingo" may incorrectly produce an image of a yellow sunflower and a pink flamingo. To remedy this issue, we propose SynGen, an approach which first syntactically analyses the prompt to identify entities and their modifiers, and then uses a novel loss function that encourages the cross-attention maps to agree with the linguistic binding reflected by the syntax. Specifically, we encourage large overlap between attention maps of entities and their modifiers, and small overlap with other entities and modifier words. The loss is optimized during inference, without retraining or fine-tuning the model. Human evaluation on three datasets, including one new and challenging set, demonstrate significant improvements of SynGen compared with current state of the art methods. This work highlights how making use of sentence structure during inference can efficiently and substantially improve the faithfulness of text-to-image generation.
Authors: Yuchen Su, Zhineng Chen, Zhiwen Shao, Yuning Du, Zhilong Ji, Jinfeng Bai, Yong Zhou, Yu-Gang Jiang
Recently, regression-based methods, which predict parameterized text shapes for text localization, have gained popularity in scene text detection. However, the existing parameterized text shape methods still have limitations in modeling arbitrary-shaped texts due to ignoring the utilization of text-specific shape information. Moreover, the time consumption of the entire pipeline has been largely overlooked, leading to a suboptimal overall inference speed. To address these issues, we first propose a novel parameterized text shape method based on low-rank approximation. Unlike other shape representation methods that employ data-irrelevant parameterization, our approach utilizes singular value decomposition and reconstructs the text shape using a few eigenvectors learned from labeled text contours. By exploring the shape correlation among different text contours, our method achieves consistency, compactness, simplicity, and robustness in shape representation. Next, we propose a dual assignment scheme for speed acceleration. It adopts a sparse assignment branch to accelerate the inference speed, and meanwhile, provides ample supervised signals for training through a dense assignment branch. Building upon these designs, we implement an accurate and efficient arbitrary-shaped text detector named LRANet. Extensive experiments are conducted on several challenging benchmarks, demonstrating the superior accuracy and efficiency of LRANet compared to state-of-the-art methods. Code is available at: \url{https://github.com/ychensu/LRANet.git}
Authors: Raphael Schumann, Wanrong Zhu, Weixi Feng, Tsu-Jui Fu, Stefan Riezler, William Yang Wang
Incremental decision making in real-world environments is one of the most challenging tasks in embodied artificial intelligence. One particularly demanding scenario is Vision and Language Navigation~(VLN) which requires visual and natural language understanding as well as spatial and temporal reasoning capabilities. The embodied agent needs to ground its understanding of navigation instructions in observations of a real-world environment like Street View. Despite the impressive results of LLMs in other research areas, it is an ongoing problem of how to best connect them with an interactive visual environment. In this work, we propose VELMA, an embodied LLM agent that uses a verbalization of the trajectory and of visual environment observations as contextual prompt for the next action. Visual information is verbalized by a pipeline that extracts landmarks from the human written navigation instructions and uses CLIP to determine their visibility in the current panorama view. We show that VELMA is able to successfully follow navigation instructions in Street View with only two in-context examples. We further finetune the LLM agent on a few thousand examples and achieve 25%-30% relative improvement in task completion over the previous state-of-the-art for two datasets.
Authors: Andy Catruna, Adrian Cosma, Emilian Radoi
The analysis of patterns of walking is an important area of research that has numerous applications in security, healthcare, sports and human-computer interaction. Lately, walking patterns have been regarded as a unique fingerprinting method for automatic person identification at a distance. In this work, we propose a novel gait recognition architecture called Gait Pyramid Transformer (GaitPT) that leverages pose estimation skeletons to capture unique walking patterns, without relying on appearance information. GaitPT adopts a hierarchical transformer architecture that effectively extracts both spatial and temporal features of movement in an anatomically consistent manner, guided by the structure of the human skeleton. Our results show that GaitPT achieves state-of-the-art performance compared to other skeleton-based gait recognition works, in both controlled and in-the-wild scenarios. GaitPT obtains 82.6% average accuracy on CASIA-B, surpassing other works by a margin of 6%. Moreover, it obtains 52.16% Rank-1 accuracy on GREW, outperforming both skeleton-based and appearance-based approaches.
Authors: Pengcheng Lei, Faming Fang, Guixu Zhang, Ming Xu
Magnetic resonance imaging (MRI) tasks often involve multiple contrasts. Recently, numerous deep learning-based multi-contrast MRI super-resolution (SR) and reconstruction methods have been proposed to explore the complementary information from the multi-contrast images. However, these methods either construct parameter-sharing networks or manually design fusion rules, failing to accurately model the correlations between multi-contrast images and lacking certain interpretations. In this paper, we propose a multi-contrast convolutional dictionary (MC-CDic) model under the guidance of the optimization algorithm with a well-designed data fidelity term. Specifically, we bulid an observation model for the multi-contrast MR images to explicitly model the multi-contrast images as common features and unique features. In this way, only the useful information in the reference image can be transferred to the target image, while the inconsistent information will be ignored. We employ the proximal gradient algorithm to optimize the model and unroll the iterative steps into a deep CDic model. Especially, the proximal operators are replaced by learnable ResNet. In addition, multi-scale dictionaries are introduced to further improve the model performance. We test our MC-CDic model on multi-contrast MRI SR and reconstruction tasks. Experimental results demonstrate the superior performance of the proposed MC-CDic model against existing SOTA methods. Code is available at https://github.com/lpcccc-cv/MC-CDic.
Authors: Aman Bhatta, Gabriella Pangelinan, Michael C. King, Kevin W. Bowyer
Most studies to date that have examined demographic variations in face recognition accuracy have analyzed 1-to-1 matching accuracy, using images that could be described as "government ID quality". This paper analyzes the accuracy of 1-to-many facial identification across demographic groups, and in the presence of blur and reduced resolution in the probe image as might occur in "surveillance camera quality" images. Cumulative match characteristic curves (CMC) are not appropriate for comparing propensity for rank-one recognition errors across demographics, and so we use three metrics for our analysis: (1) the well-known d' metric between mated and non-mated score distributions, and introduced in this work, (2) absolute score difference between thresholds in the high-similarity tail of the non-mated and the low-similarity tail of the mated distribution, and (3) distribution of (mated - non-mated rank-one scores) across the set of probe images. We find that demographic variation in 1-to-many accuracy does not entirely follow what has been observed in 1-to-1 matching accuracy. Also, different from 1-to-1 accuracy, demographic comparison of 1-to-many accuracy can be affected by different numbers of identities and images across demographics. More importantly, we show that increased blur in the probe image, or reduced resolution of the face in the probe image, can significantly increase the false positive identification rate. And we show that the demographic variation in these high blur or low resolution conditions is much larger for male / female than for African-American / Caucasian. The point that 1-to-many accuracy can potentially collapse in the context of processing "surveillance camera quality" probe images against a "government ID quality" gallery is an important one.
Authors: Chenghao Li, Dake Chen, Yuke Zhang, Peter A. Beerel
While diffusion models demonstrate a remarkable capability for generating high-quality images, their tendency to `replicate' training data raises privacy concerns. Although recent research suggests that this replication may stem from the insufficient generalization of training data captions and duplication of training images, effective mitigation strategies remain elusive. To address this gap, our paper first introduces a generality score that measures the caption generality and employ large language model (LLM) to generalize training captions. Subsequently, we leverage generalized captions and propose a novel dual fusion enhancement approach to mitigate the replication of diffusion models. Our empirical results demonstrate that our proposed methods can significantly reduce replication by 43.5% compared to the original diffusion model while maintaining the diversity and quality of generations. Code is available at https://github.com/HowardLi0816/dual-fusion-diffusion.
Authors: Lingxiao Lu, Jiangtong Li, Bo Zhang, Li Niu
The goal of image composition is merging a foreground object into a background image to obtain a realistic composite image. Recently, generative composition methods are built on large pretrained diffusion models, due to their unprecedented image generation ability. However, they are weak in preserving the foreground object details. Inspired by recent text-to-image generation customized for certain object, we propose DreamCom by treating image composition as text-guided image inpainting customized for certain object. Specifically , we finetune pretrained text-guided image inpainting model based on a few reference images containing the same object, during which the text prompt contains a special token associated with this object. Then, given a new background, we can insert this object into the background with the text prompt containing the special token. In practice, the inserted object may be adversely affected by the background, so we propose masked attention mechanisms to avoid negative background interference. Experimental results on DreamEditBench and our contributed MureCom dataset show the outstanding performance of our DreamCom.
Authors: Size Wu, Wenwei Zhang, Lumin Xu, Sheng Jin, Xiangtai Li, Wentao Liu, Chen Change Loy
Open-vocabulary dense prediction tasks including object detection and image segmentation have been advanced by the success of Contrastive Language-Image Pre-training (CLIP). CLIP models, particularly those incorporating vision transformers (ViTs), have exhibited remarkable generalization ability in zero-shot image classification. However, when transferring the vision-language alignment of CLIP from global image representation to local region representation for the open-vocabulary dense prediction tasks, CLIP ViTs suffer from the domain shift from full images to local image regions. In this paper, we embark on an in-depth analysis of the region-language alignment in CLIP models, which is essential for downstream open-vocabulary dense prediction tasks. Subsequently, we propose an approach named CLIPSelf, which adapts the image-level recognition ability of CLIP ViT to local image regions without needing any region-text pairs. CLIPSelf empowers ViTs to distill itself by aligning a region representation extracted from its dense feature map with the image-level representation of the corresponding image crop. With the enhanced CLIP ViTs, we achieve new state-of-the-art performance on open-vocabulary object detection, semantic segmentation, and panoptic segmentation across various benchmarks. Models and code are released at https://github.com/wusize/CLIPSelf.
Authors: Ioannis Mademlis, Georgios Batsis, Adamantia Anna Rebolledo Chrysochoou, Georgios Th. Papadopoulos
Automated detection of contraband items in X-ray images can significantly increase public safety, by enhancing the productivity and alleviating the mental load of security officers in airports, subways, customs/post offices, etc. The large volume and high throughput of passengers, mailed parcels, etc., during rush hours practically make it a Big Data problem. Modern computer vision algorithms relying on Deep Neural Networks (DNNs) have proven capable of undertaking this task even under resource-constrained and embedded execution scenarios, e.g., as is the case with fast, single-stage object detectors. However, no comparative experimental assessment of the various relevant DNN components/methods has been performed under a common evaluation protocol, which means that reliable cross-method comparisons are missing. This paper presents exactly such a comparative assessment, utilizing a public relevant dataset and a well-defined methodology for selecting the specific DNN components/modules that are being evaluated. The results indicate the superiority of Transformer detectors, the obsolete nature of auxiliary neural modules that have been developed in the past few years for security applications and the efficiency of the CSP-DarkNet backbone CNN.
Authors: José Rodríguez-Ortega (1 and 2), Rohaifa Khaldi (2), Domingo Alcaraz-Segura (3), Siham Tabik (1) ((1) Department of Computer Science and Artificial Intelligence, DaSCI, University of Granada, Granada, Spain, (2) LifeWatch-ERIC ICT Core, Seville, Spain, (3) Department of Botany, Faculty of Science, University of Granada, Granada, Spain)
Remotely sensed data are dominated by mixed Land Use and Land Cover (LULC) types. Spectral unmixing (SU) is a key technique that disentangles mixed pixels into constituent LULC types and their abundance fractions. While existing studies on Deep Learning (DL) for SU typically focus on single time-step hyperspectral (HS) or multispectral (MS) data, our work pioneers SU using MODIS MS time series, addressing missing data with end-to-end DL models. Our approach enhances a Long-Short Term Memory (LSTM)-based model by incorporating geographic, topographic (geo-topographic), and climatic ancillary information. Notably, our method eliminates the need for explicit endmember extraction, instead learning the input-output relationship between mixed spectra and LULC abundances through supervised learning. Experimental results demonstrate that integrating spectral-temporal input data with geo-topographic and climatic information significantly improves the estimation of LULC abundances in mixed pixels. To facilitate this study, we curated a novel labeled dataset for Andalusia (Spain) with monthly MODIS multispectral time series at 460m resolution for 2013. Named Andalusia MultiSpectral MultiTemporal Unmixing (Andalusia-MSMTU), this dataset provides pixel-level annotations of LULC abundances along with ancillary information. The dataset (https://zenodo.org/records/7752348) and code (https://github.com/jrodriguezortega/MSMTU) are available to the public.
Authors: Lee Jollans, Mariana Bustamante, Lilian Henriksson, Anders Persson, Tino Ebbers
Accurate segmentation of the heart is essential for personalized blood flow simulations and surgical intervention planning. Segmentations need to be accurate in every spatial dimension, which is not ensured by segmenting data slice by slice. Two cardiac computed tomography (CT) datasets consisting of 760 volumes across the whole cardiac cycle from 39 patients, and of 60 volumes from 60 patients respectively were used to train networks to simultaneously segment multiple regions representing the whole heart in 3D. The segmented regions included the left and right atrium and ventricle, left ventricular myocardium, ascending aorta, pulmonary arteries, pulmonary veins, and left atrial appendage. The widely used 3D U-Net and the UNETR architecture were compared to our proposed method optimized for large volumetric inputs. The proposed network architecture, termed Transformer Residual U-Net (TRUNet), maintains the cascade downsampling encoder, cascade upsampling decoder and skip connections from U-Net, while incorporating a Vision Transformer (ViT) block in the encoder alongside a modified ResNet50 block. TRUNet reached higher segmentation performance for all structures within approximately half the training time needed for 3D U-Net and UNETR. The proposed method achieved more precise vessel boundary segmentations and better captured the heart's overall anatomical structure compared to the other methods. The fast training time and accurate delineation of adjacent structures makes TRUNet a promising candidate for medical image segmentation tasks. The code for TRUNet is available at github.com/ljollans/TRUNet.
Authors: Xiangyu Chen, Zheyuan Li, Yuandong Pu, Yihao Liu, Jiantao Zhou, Yu Qiao, Chao Dong
Despite the significant progress made by deep models in various image restoration tasks, existing image restoration networks still face challenges in terms of task generality. An intuitive manifestation is that networks which excel in certain tasks often fail to deliver satisfactory results in others. To illustrate this point, we select five representative networks and conduct a comparative study on five classic image restoration tasks. First, we provide a detailed explanation of the characteristics of different image restoration tasks and backbone networks. Following this, we present the benchmark results and analyze the reasons behind the performance disparity of different models across various tasks. Drawing from this comparative study, we propose that a general image restoration backbone network needs to meet the functional requirements of diverse tasks. Based on this principle, we design a new general image restoration backbone network, X-Restormer. Extensive experiments demonstrate that X-Restormer possesses good task generality and achieves state-of-the-art performance across a variety of tasks.
Authors: Jing Hu, Qinrui Fan, Shu Hu, Siwei Lyu, Xi Wu, Xin Wang
In the field of clinical medicine, computed tomography (CT) is an effective medical imaging modality for the diagnosis of various pathologies. Compared with X-ray images, CT images can provide more information, including multi-planar slices and three-dimensional structures for clinical diagnosis. However, CT imaging requires patients to be exposed to large doses of ionizing radiation for a long time, which may cause irreversible physical harm. In this paper, we propose an Uncertainty-aware MedNeRF (UMedNeRF) network based on generated radiation fields. The network can learn a continuous representation of CT projections from 2D X-ray images by obtaining the internal structure and depth information and using adaptive loss weights to ensure the quality of the generated images. Our model is trained on publicly available knee and chest datasets, and we show the results of CT projection rendering with a single X-ray and compare our method with other methods based on generated radiation fields.
Authors: Zhongyi Shui, Yunlong Zhang, Kai Yao, Chenglu Zhu, Sunyi Zheng, Jingxiong Li, Honglin Li, Yuxuan Sun, Ruizhe Guo, Lin Yang
Nucleus instance segmentation in histology images is crucial for a broad spectrum of clinical applications. Current dominant algorithms rely on regression of nuclear proxy maps. Distinguishing nucleus instances from the estimated maps requires carefully curated post-processing, which is error-prone and parameter-sensitive. Recently, the Segment Anything Model (SAM) has earned huge attention in medical image segmentation, owing to its impressive generalization ability and promptable property. Nevertheless, its potential on nucleus instance segmentation remains largely underexplored. In this paper, we present a novel prompt-driven framework that consists of a nucleus prompter and SAM for automatic nucleus instance segmentation. Specifically, the prompter learns to generate a unique point prompt for each nucleus while the SAM is fine-tuned to output the corresponding mask for the prompted nucleus. Furthermore, we propose the inclusion of adjacent nuclei as negative prompts to enhance the model's capability to identify overlapping nuclei. Without complicated post-processing, our proposed method sets a new state-of-the-art performance on three challenging benchmarks. Code is available at \url{github.com/windygoo/PromptNucSeg}
Authors: Jinsong Zhang, Minjie Zhu, Yuxiang Zhang, Yebin Liu, Kun Li
This paper addresses the problem of generating whole-body motion from speech. Despite great successes, prior methods still struggle to produce reasonable and diverse whole-body motions from speech. This is due to their reliance on suboptimal representations and a lack of strategies for generating diverse results. To address these challenges, we present a novel hybrid point representation to achieve accurate and continuous motion generation, e.g., avoiding foot skating, and this representation can be transformed into an easy-to-use representation, i.e., SMPL-X body mesh, for many applications. To generate whole-body motion from speech, for facial motion, closely tied to the audio signal, we introduce an encoder-decoder architecture to achieve deterministic outcomes. However, for the body and hands, which have weaker connections to the audio signal, we aim to generate diverse yet reasonable motions. To boost diversity in motion generation, we propose a contrastive motion learning method to encourage the model to produce more distinctive representations. Specifically, we design a robust VQ-VAE to learn a quantized motion codebook using our hybrid representation. Then, we regress the motion representation from the audio signal by a translation model employing our contrastive motion learning method. Experimental results validate the superior performance and the correctness of our model. The project page is available for research purposes at this http URL
Authors: Hongyang Li, Yang Li, Huijie Wang, Jia Zeng, Huilin Xu, Pinlong Cai, Li Chen, Junchi Yan, Feng Xu, Lu Xiong, Jingdong Wang, Futang Zhu, Kai Yan, Chunjing Xu, Tiancai Wang, Fei Xia, Beipeng Mu, Zhihui Peng, Dahua Lin, Yu Qiao
With the continuous maturation and application of autonomous driving technology, a systematic examination of open-source autonomous driving datasets becomes instrumental in fostering the robust evolution of the industry ecosystem. Current autonomous driving datasets can broadly be categorized into two generations. The first-generation autonomous driving datasets are characterized by relatively simpler sensor modalities, smaller data scale, and is limited to perception-level tasks. KITTI, introduced in 2012, serves as a prominent representative of this initial wave. In contrast, the second-generation datasets exhibit heightened complexity in sensor modalities, greater data scale and diversity, and an expansion of tasks from perception to encompass prediction and control. Leading examples of the second generation include nuScenes and Waymo, introduced around 2019. This comprehensive review, conducted in collaboration with esteemed colleagues from both academia and industry, systematically assesses over seventy open-source autonomous driving datasets from domestic and international sources. It offers insights into various aspects, such as the principles underlying the creation of high-quality datasets, the pivotal role of data engine systems, and the utilization of generative foundation models to facilitate scalable data generation. Furthermore, this review undertakes an exhaustive analysis and discourse regarding the characteristics and data scales that future third-generation autonomous driving datasets should possess. It also delves into the scientific and technical challenges that warrant resolution. These endeavors are pivotal in advancing autonomous innovation and fostering technological enhancement in critical domains. For further details, please refer to https://github.com/OpenDriveLab/DriveAGI.
Authors: Lingxiao Luo, Xuanzhong Chen, Bingda Tang, Xinsheng Chen, Rong Han, Chengpeng Hu, Yujiang Li, Ting Chen
Recent advancements in foundation models, typically trained with self-supervised learning on large-scale and diverse datasets, have shown great potential in medical image analysis. However, due to the significant spatial heterogeneity of medical imaging data, current models must tailor specific structures for different datasets, making it challenging to leverage the abundant unlabeled data. In this work, we propose a universal foundation model for medical image analysis that processes images with heterogeneous spatial properties using a unified structure. To accomplish this, we propose spatially adaptive networks (SPAD-Nets), a family of networks that dynamically adjust the structures to adapt to the spatial properties of input images, to build such a universal foundation model. We pre-train a spatial adaptive visual tokenizer (SPAD-VT) and then a spatial adaptive Vision Transformer (SPAD-ViT) via masked image modeling (MIM) on 55 public medical image datasets. The pre-training data comprises over 9 million image slices, representing the largest, most comprehensive, and most diverse dataset to our knowledge for pre-training universal foundation models for medical image analysis. The experimental results on downstream medical image classification and segmentation tasks demonstrate the superior performance and label efficiency of our model. Our code is available at https://github.com/function2-llx/PUMIT.
Authors: Jiaqi Tang, Hao Lu, Xiaogang Xu, Ruizheng Wu, Sixing Hu, Tong Zhang, Tsz Wa Cheng, Ming Ge, Ying-Cong Chen, Fugee Tsung
Artificial Intelligence (AI)-driven defect inspection is pivotal in industrial manufacturing. Yet, many methods, tailored to specific pipelines, grapple with diverse product portfolios and evolving processes. Addressing this, we present the Incremental Unified Framework (IUF), which can reduce the feature conflict problem when continuously integrating new objects in the pipeline, making it advantageous in object-incremental learning scenarios. Employing a state-of-the-art transformer, we introduce Object-Aware Self-Attention (OASA) to delineate distinct semantic boundaries. Semantic Compression Loss (SCL) is integrated to optimize non-primary semantic space, enhancing network adaptability for novel objects. Additionally, we prioritize retaining the features of established objects during weight updates. Demonstrating prowess in both image and pixel-level defect inspection, our approach achieves state-of-the-art performance, proving indispensable for dynamic and scalable industrial inspections. Our code will be released at \url{https://github.com/jqtangust/IUF}.
Authors: Ziteng Cui, Lin Gu, Xiao Sun, Xianzheng Ma, Yu Qiao, Tatsuya Harada
The standard Neural Radiance Fields (NeRF) paradigm employs a viewer-centered methodology, entangling the aspects of illumination and material reflectance into emission solely from 3D points. This simplified rendering approach presents challenges in accurately modeling images captured under adverse lighting conditions, such as low light or over-exposure. Motivated by the ancient Greek emission theory that posits visual perception as a result of rays emanating from the eyes, we slightly refine the conventional NeRF framework to train NeRF under challenging light conditions and generate normal-light condition novel views unsupervised. We introduce the concept of a "Concealing Field," which assigns transmittance values to the surrounding air to account for illumination effects. In dark scenarios, we assume that object emissions maintain a standard lighting level but are attenuated as they traverse the air during the rendering process. Concealing Field thus compel NeRF to learn reasonable density and colour estimations for objects even in dimly lit situations. Similarly, the Concealing Field can mitigate over-exposed emissions during the rendering stage. Furthermore, we present a comprehensive multi-view dataset captured under challenging illumination conditions for evaluation. Our code and dataset available at https://github.com/cuiziteng/Aleth-NeRF
Authors: Dimitrios Psychogyios, Emanuele Colleoni, Beatrice Van Amsterdam, Chih-Yang Li, Shu-Yu Huang, Yuchong Li, Fucang Jia, Baosheng Zou, Guotai Wang, Yang Liu, Maxence Boels, Jiayu Huo, Rachel Sparks, Prokar Dasgupta, Alejandro Granados, Sebastien Ourselin, Mengya Xu, An Wang, Yanan Wu, Long Bai, Hongliang Ren, Atsushi Yamada, Yuriko Harai, Yuto Ishikawa, Kazuyuki Hayashi, Jente Simoens, Pieter DeBacker, Francesco Cisternino, Gabriele Furnari, Alex Mottrie, Federica Ferraguti, Satoshi Kondo, Satoshi Kasai, Kousuke Hirasawa, Soohee Kim, Seung Hyun Lee, Kyu Eun Lee, Hyoun-Joong Kong, Kui Fu, Chao Li, Shan An, Stefanie Krell, Sebastian Bodenstedt, Nicolas Ayobi, Alejandra Perez, Santiago Rodriguez, Juanita Puentes, Pablo Arbelaez, Omid Mohareri, Danail Stoyanov
Surgical tool segmentation and action recognition are fundamental building blocks in many computer-assisted intervention applications, ranging from surgical skills assessment to decision support systems. Nowadays, learning-based action recognition and segmentation approaches outperform classical methods, relying, however, on large, annotated datasets. Furthermore, action recognition and tool segmentation algorithms are often trained and make predictions in isolation from each other, without exploiting potential cross-task relationships. With the EndoVis 2022 SAR-RARP50 challenge, we release the first multimodal, publicly available, in-vivo, dataset for surgical action recognition and semantic instrumentation segmentation, containing 50 suturing video segments of Robotic Assisted Radical Prostatectomy (RARP). The aim of the challenge is twofold. First, to enable researchers to leverage the scale of the provided dataset and develop robust and highly accurate single-task action recognition and tool segmentation approaches in the surgical domain. Second, to further explore the potential of multitask-based learning approaches and determine their comparative advantage against their single-task counterparts. A total of 12 teams participated in the challenge, contributing 7 action recognition methods, 9 instrument segmentation techniques, and 4 multitask approaches that integrated both action recognition and instrument segmentation. The complete SAR-RARP50 dataset is available at: https://rdr.ucl.ac.uk/projects/SARRARP50_Segmentation_of_surgical_instrumentation_and_Action_Recognition_on_Robot-Assisted_Radical_Prostatectomy_Challenge/191091
Authors: Qiao Jin, Fangyuan Chen, Yiliang Zhou, Ziyang Xu, Justin M. Cheung, Robert Chen, Ronald M. Summers, Justin F. Rousseau, Peiyun Ni, Marc J Landsman, Sally L. Baxter, Subhi J. Al'Aref, Yijia Li, Michael F. Chiang, Yifan Peng, Zhiyong Lu
Recent studies indicate that Generative Pre-trained Transformer 4 with Vision (GPT-4V) outperforms human physicians in medical challenge tasks. However, these evaluations primarily focused on the accuracy of multi-choice questions alone. Our study extends the current scope by conducting a comprehensive analysis of GPT-4V's rationales of image comprehension, recall of medical knowledge, and step-by-step multimodal reasoning when solving New England Journal of Medicine (NEJM) Image Challenges - an imaging quiz designed to test the knowledge and diagnostic capabilities of medical professionals. Evaluation results confirmed that GPT-4V outperforms human physicians regarding multi-choice accuracy (88.0% vs. 77.0%, p=0.034). GPT-4V also performs well in cases where physicians incorrectly answer, with over 80% accuracy. However, we discovered that GPT-4V frequently presents flawed rationales in cases where it makes the correct final choices (27.3%), most prominent in image comprehension (21.6%). Regardless of GPT-4V's high accuracy in multi-choice questions, our findings emphasize the necessity for further in-depth evaluations of its rationales before integrating such models into clinical workflows.
Authors: Xianfu Cheng, Weixiao Zhou, Xiang Li, Xiaoming Chen, Jian Yang, Tongliang Li, Zhoujun Li
Scene Text Recognition (STR) is a challenging task that involves recognizing text within images of natural scenes. Although current state-of-the-art models for STR exhibit high performance, they typically suffer from low inference efficiency due to their reliance on hybrid architectures comprised of visual encoders and sequence decoders. In this work, we propose the VIsion Permutable extractor for fast and efficient scene Text Recognition (VIPTR), which achieves an impressive balance between high performance and rapid inference speeds in the domain of STR. Specifically, VIPTR leverages a visual-semantic extractor with a pyramid structure, characterized by multiple self-attention layers, while eschewing the traditional sequence decoder. This design choice results in a lightweight and efficient model capable of handling inputs of varying sizes. Extensive experimental results on various standard datasets for both Chinese and English scene text recognition validate the superiority of VIPTR. Notably, the VIPTR-T (Tiny) variant delivers highly competitive accuracy on par with other lightweight models and achieves SOTA inference speeds. Meanwhile, the VIPTR-L (Large) variant attains greater recognition accuracy, while maintaining a low parameter count and favorable inference speed. Our proposed method provides a compelling solution for the STR challenge, which blends high accuracy with efficiency and greatly benefits real-world applications requiring fast and reliable text recognition. The code is publicly available at https://github.com/cxfyxl/VIPTR.
Authors: Hongyi Wang, Xiuju Du, Jing Liu, Shuyi Ouyang, Yen-Wei Chen, Lanfen Lin
The advancement of Spatial Transcriptomics (ST) has facilitated the spatially-aware profiling of gene expressions based on histopathology images. Although ST data offers valuable insights into the micro-environment of tumors, its acquisition cost remains expensive. Therefore, directly predicting the ST expressions from digital pathology images is desired. Current methods usually adopt existing regression backbones for this task, which ignore the inherent multi-scale hierarchical data structure of digital pathology images. To address this limit, we propose M2ORT, a many-to-one regression Transformer that can accommodate the hierarchical structure of the pathology images through a decoupled multi-scale feature extractor. Different from traditional models that are trained with one-to-one image-label pairs, M2ORT accepts multiple pathology images of different magnifications at a time to jointly predict the gene expressions at their corresponding common ST spot, aiming at learning a many-to-one relationship through training. We have tested M2ORT on three public ST datasets and the experimental results show that M2ORT can achieve state-of-the-art performance with fewer parameters and floating-point operations (FLOPs). The code is available at: https://github.com/Dootmaan/M2ORT/.
Authors: Chenyu Wang, Weixin Luo, Qianyu Chen, Haonan Mai, Jindi Guo, Sixun Dong, Xiaohua (Michael) Xuan, Zhengxin Li, Lin Ma, Shenghua Gao
Recently, the astonishing performance of large language models (LLMs) in natural language comprehension and generation tasks triggered lots of exploration of using them as central controllers to build agent systems. Multiple studies focus on bridging the LLMs to external tools to extend the application scenarios. However, the current LLMs' perceiving tool-use ability is limited to a single text query, which may result in ambiguity in understanding the users' real intentions. LLMs are expected to eliminate that by perceiving the visual- or auditory-grounded instructions' information. Therefore, in this paper, we propose MLLM-Tool, a system incorporating open-source LLMs and multi-modal encoders so that the learnt LLMs can be conscious of multi-modal input instruction and then select the function-matched tool correctly. To facilitate the evaluation of the model's capability, we collect a dataset featured by consisting of multi-modal input tools from HuggingFace. Another important feature of our dataset is that our dataset also contains multiple potential choices for the same instruction due to the existence of identical functions and synonymous functions, which provides more potential solutions for the same query. The experiments reveal that our MLLM-Tool is capable of recommending appropriate tools for multi-modal instructions. Codes and data are available at https://github.com/MLLM-Tool/MLLM-Tool.
Authors: Nhat M. Hoang, Kehong Gong, Chuan Guo, Michael Bi Mi
Controllable generation of 3D human motions becomes an important topic as the world embraces digital transformation. Existing works, though making promising progress with the advent of diffusion models, heavily rely on meticulously captured and annotated (e.g., text) high-quality motion corpus, a resource-intensive endeavor in the real world. This motivates our proposed MotionMix, a simple yet effective weakly-supervised diffusion model that leverages both noisy and unannotated motion sequences. Specifically, we separate the denoising objectives of a diffusion model into two stages: obtaining conditional rough motion approximations in the initial $T-T^*$ steps by learning the noisy annotated motions, followed by the unconditional refinement of these preliminary motions during the last $T^*$ steps using unannotated motions. Notably, though learning from two sources of imperfect data, our model does not compromise motion generation quality compared to fully supervised approaches that access gold data. Extensive experiments on several benchmarks demonstrate that our MotionMix, as a versatile framework, consistently achieves state-of-the-art performances on text-to-motion, action-to-motion, and music-to-dance tasks. Project page: https://nhathoang2002.github.io/MotionMix-page/
Authors: Jiang Wu, Rui Li, Yu Zhu, Wenxun Zhao, Jinqiu Sun, Yanning Zhang
Pairwise matching cost aggregation is a crucial step for modern learning-based Multi-view Stereo (MVS). Prior works adopt an early aggregation scheme, which adds up pairwise costs into an intermediate cost. However, we analyze that this process can degrade informative pairwise matchings, thereby blocking the depth network from fully utilizing the original geometric matching cues. To address this challenge, we present a late aggregation approach that allows for aggregating pairwise costs throughout the network feed-forward process, achieving accurate estimations with only minor changes of the plain CasMVSNet. Instead of building an intermediate cost by weighted sum, late aggregation preserves all pairwise costs along a distinct view channel. This enables the succeeding depth network to fully utilize the crucial geometric cues without loss of cost fidelity. Grounded in the new aggregation scheme, we propose further techniques addressing view order dependence inside the preserved cost, handling flexible testing views, and improving the depth filtering process. Despite its technical simplicity, our method improves significantly upon the baseline cascade-based approach, achieving comparable results with state-of-the-art methods with favorable computation overhead.
Authors: Feiwei Qin, Kang Yan, Changmiao Wang, Ruiquan Ge, Yong Peng, Kai Zhang
Given the broad application of infrared technology across diverse fields, there is an increasing emphasis on investigating super-resolution techniques for infrared images within the realm of deep learning. Despite the impressive results of current Transformer-based methods in image super-resolution tasks, their reliance on the self-attentive mechanism intrinsic to the Transformer architecture results in images being treated as one-dimensional sequences, thereby neglecting their inherent two-dimensional structure. Moreover, infrared images exhibit a uniform pixel distribution and a limited gradient range, posing challenges for the model to capture effective feature information. Consequently, we suggest a potent Transformer model, termed Large Kernel Transformer (LKFormer), to address this issue. Specifically, we have designed a Large Kernel Residual Attention (LKRA) module with linear complexity. This mainly employs depth-wise convolution with large kernels to execute non-local feature modeling, thereby substituting the standard self-attentive layer. Additionally, we have devised a novel feed-forward network structure called Gated-Pixel Feed-Forward Network (GPFN) to augment the LKFormer's capacity to manage the information flow within the network. Comprehensive experimental results reveal that our method surpasses the most advanced techniques available, using fewer parameters and yielding considerably superior performance.The source code will be available at https://github.com/sad192/large-kernel-Transformer.
Authors: Hongchi Xia, Yang Fu, Sifei Liu, Xiaolong Wang
We introduce a new RGB-D object dataset captured in the wild called WildRGB-D. Unlike most existing real-world object-centric datasets which only come with RGB capturing, the direct capture of the depth channel allows better 3D annotations and broader downstream applications. WildRGB-D comprises large-scale category-level RGB-D object videos, which are taken using an iPhone to go around the objects in 360 degrees. It contains around 8500 recorded objects and nearly 20000 RGB-D videos across 46 common object categories. These videos are taken with diverse cluttered backgrounds with three setups to cover as many real-world scenarios as possible: (i) a single object in one video; (ii) multiple objects in one video; and (iii) an object with a static hand in one video. The dataset is annotated with object masks, real-world scale camera poses, and reconstructed aggregated point clouds from RGBD videos. We benchmark four tasks with WildRGB-D including novel view synthesis, camera pose estimation, object 6d pose estimation, and object surface reconstruction. Our experiments show that the large-scale capture of RGB-D objects provides a large potential to advance 3D object learning. Our project page is https://wildrgbd.github.io/.
Authors: Zhongyuan Zhao, Zhenyu Bao, Qing Li, Guoping Qiu, Kanglin Liu
Despite much progress, achieving real-time high-fidelity head avatar animation is still difficult and existing methods have to trade-off between speed and quality. 3DMM based methods often fail to model non-facial structures such as eyeglasses and hairstyles, while neural implicit models suffer from deformation inflexibility and rendering inefficiency. Although 3D Gaussian has been demonstrated to possess promising capability for geometry representation and radiance field reconstruction, applying 3D Gaussian in head avatar creation remains a major challenge since it is difficult for 3D Gaussian to model the head shape variations caused by changing poses and expressions. In this paper, we introduce PSAvatar, a novel framework for animatable head avatar creation that utilizes discrete geometric primitive to create a parametric morphable shape model and employs 3D Gaussian for fine detail representation and high fidelity rendering. The parametric morphable shape model is a Point-based Morphable Shape Model (PMSM) which uses points instead of meshes for 3D representation to achieve enhanced representation flexibility. The PMSM first converts the FLAME mesh to points by sampling on the surfaces as well as off the meshes to enable the reconstruction of not only surface-like structures but also complex geometries such as eyeglasses and hairstyles. By aligning these points with the head shape in an analysis-by-synthesis manner, the PMSM makes it possible to utilize 3D Gaussian for fine detail representation and appearance modeling, thus enabling the creation of high-fidelity avatars. We show that PSAvatar can reconstruct high-fidelity head avatars of a variety of subjects and the avatars can be animated in real-time ($\ge$ 25 fps at a resolution of 512 $\times$ 512 ).
Authors: Zimeng Wang, Zhiyang Dou, Rui Xu, Cheng Lin, Yuan Liu, Xiaoxiao Long, Shiqing Xin, Lingjie Liu, Taku Komura, Xiaoming Yuan, Wenping Wang
We introduce Coverage Axis++, a novel and efficient approach to 3D shape skeletonization. The current state-of-the-art approaches for this task often rely on the watertightness of the input or suffer from substantial computational costs, thereby limiting their practicality. To address this challenge, Coverage Axis++ proposes a heuristic algorithm to select skeletal points, offering a high-accuracy approximation of the Medial Axis Transform (MAT) while significantly mitigating computational intensity for various shape representations. We introduce a simple yet effective strategy that considers both shape coverage and uniformity to derive skeletal points. The selection procedure enforces consistency with the shape structure while favoring the dominant medial balls, which thus introduces a compact underlying shape representation in terms of MAT. As a result, Coverage Axis++ allows for skeletonization for various shape representations (e.g., water-tight meshes, triangle soups, point clouds), specification of the number of skeletal points, few hyperparameters, and highly efficient computation with improved reconstruction accuracy. Extensive experiments across a wide range of 3D shapes validate the efficiency and effectiveness of Coverage Axis++. The code will be publicly available once the paper is published.
Authors: Hyeonwoo Kim, Sookwan Han, Patrick Kwon, Hanbyul Joo
One of the major challenges in AI is teaching machines to precisely respond and utilize environmental functionalities, thereby achieving the affordance awareness that humans possess. Despite its importance, the field has been lagging in terms of learning, especially in 3D, as annotating affordance accompanies a laborious process due to the numerous variations of human-object interaction. The low availability of affordance data limits the learning in terms of generalization for object categories, and also simplifies the representation of affordance, capturing only a fraction of the affordance. To overcome these challenges, we propose a novel, self-supervised method to generate the 3D affordance examples given only a 3D object, without any manual annotations. The method starts by capturing the 3D object into images and creating 2D affordance images by inserting humans into the image via inpainting diffusion models, where we present the Adaptive Mask algorithm to enable human insertion without altering the original details of the object. The method consequently lifts inserted humans back to 3D to create 3D human-object pairs, where the depth ambiguity is resolved within a depth optimization framework that utilizes pre-generated human postures from multiple viewpoints. We also provide a novel affordance representation defined on relative orientations and proximity between dense human and object points, that can be easily aggregated from any 3D HOI datasets. The proposed representation serves as a primitive that can be manifested to conventional affordance representations via simple transformations, ranging from physically exerted affordances to nonphysical ones. We demonstrate the efficacy of our method and representation by generating the 3D affordance samples and deriving high-quality affordance examples from the representation, including contact, orientation, and spatial occupancies.