Authors: Jialu Sui, Yiyang Ma, Wenhan Yang, Xiaokang Zhang, Man-On Pun, Jiaying Liu
The presence of cloud layers severely compromises the quality and effectiveness of optical remote sensing (RS) images. However, existing deep-learning (DL)-based Cloud Removal (CR) techniques encounter difficulties in accurately reconstructing the original visual authenticity and detailed semantic content of the images. To tackle this challenge, this work proposes to encompass enhancements at the data and methodology fronts. On the data side, an ultra-resolution benchmark named CUHK Cloud Removal (CUHK-CR) of 0.5m spatial resolution is established. This benchmark incorporates rich detailed textures and diverse cloud coverage, serving as a robust foundation for designing and assessing CR models. From the methodology perspective, a novel diffusion-based framework for CR called Diffusion Enhancement (DE) is proposed to perform progressive texture detail recovery, which mitigates the training difficulty with improved inference accuracy. Additionally, a Weight Allocation (WA) network is developed to dynamically adjust the weights for feature fusion, thereby further improving performance, particularly in the context of ultra-resolution image generation. Furthermore, a coarse-to-fine training strategy is applied to effectively expedite training convergence while reducing the computational complexity required to handle ultra-resolution images. Extensive experiments on the newly established CUHK-CR and existing datasets such as RICE confirm that the proposed DE framework outperforms existing DL-based methods in terms of both perceptual quality and signal fidelity.
Authors: Mingquan Lin, Tianhao Li, Zhaoyi Sun, Gregory Holste, Ying Ding, Fei Wang, George Shih, Yifan Peng
Purpose: Limited studies exploring concrete methods or approaches to tackle and enhance model fairness in the radiology domain. Our proposed AI model utilizes supervised contrastive learning to minimize bias in CXR diagnosis.
Materials and Methods: In this retrospective study, we evaluated our proposed method on two datasets: the Medical Imaging and Data Resource Center (MIDRC) dataset with 77,887 CXR images from 27,796 patients collected as of April 20, 2023 for COVID-19 diagnosis, and the NIH Chest X-ray (NIH-CXR) dataset with 112,120 CXR images from 30,805 patients collected between 1992 and 2015. In the NIH-CXR dataset, thoracic abnormalities include atelectasis, cardiomegaly, effusion, infiltration, mass, nodule, pneumonia, pneumothorax, consolidation, edema, emphysema, fibrosis, pleural thickening, or hernia. Our proposed method utilizes supervised contrastive learning with carefully selected positive and negative samples to generate fair image embeddings, which are fine-tuned for subsequent tasks to reduce bias in chest X-ray (CXR) diagnosis. We evaluated the methods using the marginal AUC difference ($\delta$ mAUC).
Results: The proposed model showed a significant decrease in bias across all subgroups when compared to the baseline models, as evidenced by a paired T-test (p<0.0001). The $\delta$ mAUC obtained by our method were 0.0116 (95\% CI, 0.0110-0.0123), 0.2102 (95% CI, 0.2087-0.2118), and 0.1000 (95\% CI, 0.0988-0.1011) for sex, race, and age on MIDRC, and 0.0090 (95\% CI, 0.0082-0.0097) for sex and 0.0512 (95% CI, 0.0512-0.0532) for age on NIH-CXR, respectively.
Conclusion: Employing supervised contrastive learning can mitigate bias in CXR diagnosis, addressing concerns of fairness and reliability in deep learning-based diagnostic methods.
Authors: Konstantin A. Maslov, Claudio Persello, Thomas Schellenberger, Alfred Stein
Accurate global glacier mapping is critical for understanding climate change impacts. It is challenged by glacier diversity, difficult-to-classify debris and big data processing. Here we propose Glacier-VisionTransformer-U-Net (GlaViTU), a convolutional-transformer deep learning model, and five strategies for multitemporal global-scale glacier mapping using open satellite imagery. Assessing the spatial, temporal and cross-sensor generalisation shows that our best strategy achieves intersection over union >0.85 on previously unobserved images in most cases, which drops to >0.75 for debris-rich areas such as High-Mountain Asia and increases to >0.90 for regions dominated by clean ice. Additionally, adding synthetic aperture radar data, namely, backscatter and interferometric coherence, increases the accuracy in all regions where available. The calibrated confidence for glacier extents is reported making the predictions more reliable and interpretable. We also release a benchmark dataset that covers 9% of glaciers worldwide. Our results support efforts towards automated multitemporal and global glacier mapping.
Authors: Feng Qi, Mian Dai, Zixian Zheng, Chao Wang
This paper presents GeoDecoder, a dedicated multimodal model designed for processing geospatial information in maps. Built on the BeitGPT architecture, GeoDecoder incorporates specialized expert modules for image and text processing. On the image side, GeoDecoder utilizes GaoDe Amap as the underlying base map, which inherently encompasses essential details about road and building shapes, relative positions, and other attributes. Through the utilization of rendering techniques, the model seamlessly integrates external data and features such as symbol markers, drive trajectories, heatmaps, and user-defined markers, eliminating the need for extra feature engineering. The text module of GeoDecoder accepts various context texts and question prompts, generating text outputs in the style of GPT. Furthermore, the GPT-based model allows for the training and execution of multiple tasks within the same model in an end-to-end manner. To enhance map cognition and enable GeoDecoder to acquire knowledge about the distribution of geographic entities in Beijing, we devised eight fundamental geospatial tasks and conducted pretraining of the model using large-scale text-image samples. Subsequently, rapid fine-tuning was performed on three downstream tasks, resulting in significant performance improvements. The GeoDecoder model demonstrates a comprehensive understanding of map elements and their associated operations, enabling efficient and high-quality application of diverse geospatial tasks in different business scenarios.
Authors: Lizhen Zhu, James Z. Wang, Wonseuk Lee, Brad Wyble
Visual learning often occurs in a specific context, where an agent acquires skills through exploration and tracking of its location in a consistent environment. The historical spatial context of the agent provides a similarity signal for self-supervised contrastive learning. We present a unique approach, termed Environmental Spatial Similarity (ESS), that complements existing contrastive learning methods. Using images from simulated, photorealistic environments as an experimental setting, we demonstrate that ESS outperforms traditional instance discrimination approaches. Moreover, sampling additional data from the same environment substantially improves accuracy and provides new augmentations. ESS allows remarkable proficiency in room classification and spatial prediction tasks, especially in unfamiliar environments. This learning paradigm has the potential to enable rapid visual learning in agents operating in new environments with unique visual characteristics. Potentially transformative applications span from robotics to space exploration. Our proof of concept demonstrates improved efficiency over methods that rely on extensive, disconnected datasets.
Authors: Naresh Kumar Devulapally, Sidharth Anand, Sreyasee Das Bhattacharjee, Junsong Yuan, Yu-Ping Chang
Analyzing individual emotions during group conversation is crucial in developing intelligent agents capable of natural human-machine interaction. While reliable emotion recognition techniques depend on different modalities (text, audio, video), the inherent heterogeneity between these modalities and the dynamic cross-modal interactions influenced by an individual's unique behavioral patterns make the task of emotion recognition very challenging. This difficulty is compounded in group settings, where the emotion and its temporal evolution are not only influenced by the individual but also by external contexts like audience reaction and context of the ongoing conversation. To meet this challenge, we propose a Multimodal Attention Network that captures cross-modal interactions at various levels of spatial abstraction by jointly learning its interactive bunch of mode-specific Peripheral and Central networks. The proposed MAN injects cross-modal attention via its Peripheral key-value pairs within each layer of a mode-specific Central query network. The resulting cross-attended mode-specific descriptors are then combined using an Adaptive Fusion technique that enables the model to integrate the discriminative and complementary mode-specific data patterns within an instance-specific multimodal descriptor. Given a dialogue represented by a sequence of utterances, the proposed AMuSE model condenses both spatial and temporal features into two dense descriptors: speaker-level and utterance-level. This helps not only in delivering better classification performance (3-5% improvement in Weighted-F1 and 5-7% improvement in Accuracy) in large-scale public datasets but also helps the users in understanding the reasoning behind each emotion prediction made by the model via its Multimodal Explainability Visualization module.
Authors: Raiyan Rahman, Mohsena Chowdhury, Yueyang Tang, Huayi Gao, George Yin, Guanghui Wang
The escalating global concern over extensive food wastage necessitates innovative solutions to foster a net-zero lifestyle and reduce emissions. The LILA home composter presents a convenient means of recycling kitchen scraps and daily food waste into nutrient-rich, high-quality compost. To capture the nutritional information of the produced compost, we have created and annotated a large high-resolution image dataset of kitchen food waste with segmentation masks of 19 nutrition-rich categories. Leveraging this dataset, we benchmarked four state-of-the-art semantic segmentation models on food waste segmentation, contributing to the assessment of compost quality of Nitrogen, Phosphorus, or Potassium. The experiments demonstrate promising results of using segmentation models to discern food waste produced in our daily lives. Based on the experiments, SegFormer, utilizing MIT-B5 backbone, yields the best performance with a mean Intersection over Union (mIoU) of 67.09. Class-based results are also provided to facilitate further analysis of different food waste classes.
Authors: A. Brateanu, R. Balmez, A. Avram, C. C. Orhei
In recent years, deep learning-based solutions have proven successful in the domains of image enhancement. This paper introduces LYT-Net, or Lightweight YUV Transformer-based Network, as a novel approach for low-light image enhancement. The proposed architecture, distinct from conventional Retinex-based models, leverages the YUV color space's natural separation of luminance (Y) and chrominance (U and V) to simplify the intricate task of disentangling light and color information in images. By utilizing the strengths of transformers, known for their capability to capture long-range dependencies, LYT-Net ensures a comprehensive contextual understanding of the image while maintaining reduced model complexity. By employing a novel hybrid loss function, our proposed method achieves state-of-the-art results on low-light image enhancement datasets, all while being considerably more compact than its counterparts. The source code and pre-trained models are available at https://github.com/albrateanu/LYT-Net
Authors: Mingshi Li, Dusan Grujicic, Steven De Saeger, Stien Heremans, Ben Somers, Matthew B. Blaschko
In recent years, machine learning has become crucial in remote sensing analysis, particularly in the domain of Land-use/Land-cover (LULC). The synergy of machine learning and satellite imagery analysis has demonstrated significant productivity in this field, as evidenced by several studies. A notable challenge within this area is the semantic segmentation mapping of land usage over extensive territories, where the accessibility of accurate land-use data and the reliability of ground truth land-use labels pose significant difficulties. For example, providing a detailed and accurate pixel-wise labeled dataset of the Flanders region, a first-level administrative division of Belgium, can be particularly insightful. Yet there is a notable lack of regulated, formalized datasets and workflows for such studies in many regions globally. This paper introduces a comprehensive approach to addressing these gaps. We present a densely labeled ground truth map of Flanders paired with Sentinel-2 satellite imagery. Our methodology includes a formalized dataset division and sampling method, utilizing the topographic map layout 'Kaartbladversnijdingen,' and a detailed semantic segmentation model training pipeline. Preliminary benchmarking results are also provided to demonstrate the efficacy of our approach.
Authors: Amirhosein Ghasemabadi, Mohammad Salameh, Muhammad Kamran Janjua, Chunhua Zhou, Fengyu Sun, Di Niu
Image restoration tasks traditionally rely on convolutional neural networks. However, given the local nature of the convolutional operator, they struggle to capture global information. The promise of attention mechanisms in Transformers is to circumvent this problem, but it comes at the cost of intensive computational overhead. Many recent studies in image restoration have focused on solving the challenge of balancing performance and computational cost via Transformer variants. In this paper, we present CascadedGaze Network (CGNet), an encoder-decoder architecture that employs Global Context Extractor (GCE), a novel and efficient way to capture global information for image restoration. The GCE module leverages small kernels across convolutional layers to learn global dependencies, without requiring self-attention. Extensive experimental results show that our approach outperforms a range of state-of-the-art methods on denoising benchmark datasets including both real image denoising and synthetic image denoising, as well as on image deblurring task, while being more computationally efficient.
Authors: Beatrice Alessandra Motetti, Luca Crupi, Mustafa Omer Mohammed Elamin Elshaigi, Matteo Risso, Daniele Jahier Pagliari, Daniele Palossi, Alessio Burrello
Sub-10cm diameter nano-drones are gaining momentum thanks to their applicability in scenarios prevented to bigger flying drones, such as in narrow environments and close to humans. However, their tiny form factor also brings their major drawback: ultra-constrained memory and processors for the onboard execution of their perception pipelines. Therefore, lightweight deep learning-based approaches are becoming increasingly popular, stressing how computational efficiency and energy-saving are paramount as they can make the difference between a fully working closed-loop system and a failing one. In this work, to maximize the exploitation of the ultra-limited resources aboard nano-drones, we present a novel adaptive deep learning-based mechanism for the efficient execution of a vision-based human pose estimation task. We leverage two State-of-the-Art (SoA) convolutional neural networks (CNNs) with different regression performance vs. computational costs trade-offs. By combining these CNNs with three novel adaptation strategies based on the output's temporal consistency and on auxiliary tasks to swap the CNN being executed proactively, we present six different systems. On a real-world dataset and the actual nano-drone hardware, our best-performing system, compared to executing only the bigger and most accurate SoA model, shows 28% latency reduction while keeping the same mean absolute error (MAE), 3% MAE reduction while being iso-latency, and the absolute peak performance, i.e., 6% better than SoA model.
Authors: Diandian Guo, Deng-Ping Fan, Tongyu Lu, Christos Sakaridis, Luc Van Gool
The estimation of implicit cross-frame correspondences and the high computational cost have long been major challenges in video semantic segmentation (VSS) for driving scenes. Prior works utilize keyframes, feature propagation, or cross-frame attention to address these issues. By contrast, we are the first to harness vanishing point (VP) priors for more effective segmentation. Intuitively, objects near VPs (i.e., away from the vehicle) are less discernible. Moreover, they tend to move radially away from the VP over time in the usual case of a forward-facing camera, a straight road, and linear forward motion of the vehicle. Our novel, efficient network for VSS, named VPSeg, incorporates two modules that utilize exactly this pair of static and dynamic VP priors: sparse-to-dense feature mining (DenseVP) and VP-guided motion fusion (MotionVP). MotionVP employs VP-guided motion estimation to establish explicit correspondences across frames and help attend to the most relevant features from neighboring frames, while DenseVP enhances weak dynamic features in distant regions around VPs. These modules operate within a context-detail framework, which separates contextual features from high-resolution local features at different input resolutions to reduce computational costs. Contextual and local features are integrated through contextualized motion attention (CMA) for the final prediction. Extensive experiments on two popular driving segmentation benchmarks, Cityscapes and ACDC, demonstrate that VPSeg outperforms previous SOTA methods, with only modest computational overhead.
Authors: Zehao Ye, Lucy Lovell, Asaad Faramarzi, Jelena Ninic
Automating visual inspection for capturing defects based on civil structures appearance is crucial due to its currently labour-intensive and time-consuming nature. An important aspect of automated inspection is image acquisition, which is rapid and cost-effective considering the pervasive developments in both software and hardware computing in recent years. Previous studies largely focused on concrete and asphalt, with less attention to masonry cracks. The latter also lacks publicly available datasets. In this paper, we first present a corresponding data set for instance segmentation with 1,300 annotated images (640 pixels x 640 pixels), named as MCrack1300, covering bricks, broken bricks, and cracks. We then test several leading algorithms for benchmarking, including the latest large-scale model, the prompt-based Segment Anything Model (SAM). We fine-tune the encoder using Low-Rank Adaptation (LoRA) and proposed two novel methods for automation of SAM execution. The first method involves abandoning the prompt encoder and connecting the SAM encoder to other decoders, while the second method introduces a learnable self-generating prompter. In order to ensure the seamless integration of the two proposed methods with SAM encoder section, we redesign the feature extractor. Both proposed methods exceed state-of-the-art performance, surpassing the best benchmark by approximately 3% for all classes and around 6% for cracks specifically. Based on successful detection, we propose a method based on a monocular camera and the Hough Line Transform to automatically transform images into orthographic projection maps. By incorporating known real sizes of brick units, we accurately estimate crack dimensions, with the results differing by less than 10% from those obtained by laser scanning. Overall, we address important research gaps in automated masonry crack detection and size estimation.
Authors: Yuliang Cai, Mohammad Rostami
Transformer neural networks are increasingly replacing prior architectures in a wide range of applications in different data modalities. The increasing size and computational demands of fine-tuning large pre-trained transformer neural networks pose significant challenges for the widespread adoption of these models for applications that demand on-edge computing. To tackle this challenge, continual learning (CL) emerges as a solution by facilitating the transfer of knowledge across tasks that arrive sequentially for an autonomously learning agent. However, current CL methods mainly focus on learning tasks that are exclusively vision-based or language-based. We propose a transformer-based CL framework focusing on learning tasks that involve both vision and language, known as Vision-and-Language (VaL) tasks. Due to the success of transformers in other modalities, our architecture has the potential to be used in multimodal learning settings. In our framework, we benefit from introducing extra parameters to a base transformer to specialize the network for each task. As a result, we enable dynamic model expansion to learn several tasks in a sequence. We also use knowledge distillation to benefit from relevant past experiences to learn the current task more efficiently. Our proposed method, Task Attentive Multimodal Continual Learning (TAM-CL), allows for the exchange of information between tasks while mitigating the problem of catastrophic forgetting. Notably, our approach is scalable, incurring minimal memory and time overhead. TAM-CL achieves state-of-the-art (SOTA) performance on challenging multimodal tasks
Authors: Jing Hao, Moyun Liu, Kuo Feng Hung
Detecting glass regions is a challenging task due to the ambiguity of their transparency and reflection properties. These transparent glasses share the visual appearance of both transmitted arbitrary background scenes and reflected objects, thus having no fixed patterns.Recent visual foundation models, which are trained on vast amounts of data, have manifested stunning performance in terms of image perception and image generation. To segment glass surfaces with higher accuracy, we make full use of two visual foundation models: Segment Anything (SAM) and Stable Diffusion.Specifically, we devise a simple glass surface segmentor named GEM, which only consists of a SAM backbone, a simple feature pyramid, a discerning query selection module, and a mask decoder. The discerning query selection can adaptively identify glass surface features, assigning them as initialized queries in the mask decoder. We also propose a Synthetic but photorealistic large-scale Glass Surface Detection dataset dubbed S-GSD via diffusion model with four different scales, which contain 1x, 5x, 10x, and 20x of the original real data size. This dataset is a feasible source for transfer learning. The scale of synthetic data has positive impacts on transfer learning, while the improvement will gradually saturate as the amount of data increases. Extensive experiments demonstrate that GEM achieves a new state-of-the-art on the GSD-S validation set (IoU +2.1%). Codes and datasets are available at: https://github.com/isbrycee/GEM-Glass-Segmentor.
Authors: Linmi Tao, Ruiyang Liu, Donglai Tao, Wu Xia, Feilong Ma, Yu Cheng, Jingmao Cui
Numerical difference computation is one of the cores and indispensable in the modern digital era. Tao general difference (TGD) is a novel theory and approach to difference computation for discrete sequences and arrays in multidimensional space. Built on the solid theoretical foundation of the general difference in a finite interval, the TGD operators demonstrate exceptional signal processing capabilities in real-world applications. A novel smoothness property of a sequence is defined on the first- and second TGD. This property is used to denoise one-dimensional signals, where the noise is the non-smooth points in the sequence. Meanwhile, the center of the gradient in a finite interval can be accurately location via TGD calculation. This solves a traditional challenge in computer vision, which is the precise localization of image edges with noise robustness. Furthermore, the power of TGD operators extends to spatio-temporal edge detection in three-dimensional arrays, enabling the identification of kinetic edges in video data. These diverse applications highlight the properties of TGD in discrete domain and the significant promise of TGD for the computation across signal processing, image analysis, and video analytic.
Authors: Volodymyr Vakhniuk, Ayush Sarkar, Ragini Gupta
We propose an efficient cross-cameras surveillance system called,STAC, that leverages spatio-temporal associations between multiple cameras to provide real-time analytics and inference under constrained network environments. STAC is built using the proposed omni-scale feature learning people reidentification (reid) algorithm that allows accurate detection, tracking and re-identification of people across cameras using the spatio-temporal characteristics of video frames. We integrate STAC with frame filtering and state-of-the-art compression for streaming technique (that is, ffmpeg libx264 codec) to remove redundant information from cross-camera frames. This helps in optimizing the cost of video transmission as well as compute/processing, while maintaining high accuracy for real-time query inference. The introduction of AICity Challenge 2023 Data [1] by NVIDIA has allowed exploration of systems utilizing multi-camera people tracking algorithms. We evaluate the performance of STAC using this dataset to measure the accuracy metrics and inference rate for reid. Additionally, we quantify the reduction in video streams achieved through frame filtering and compression using FFmpeg compared to the raw camera streams. For completeness, we make available our repository to reproduce the results, available at https://github.com/VolodymyrVakhniuk/CS444_Final_Project.
Authors: Foozhan Ataiefard, Walid Ahmed, Habib Hajimolahoseini, Saina Asani, Farnoosh Javadi, Mohammad Hassanpour, Omar Mohamed Awad, Austin Wen, Kangling Liu, Yang Liu
Vision transformers are known to be more computationally and data-intensive than CNN models. These transformer models such as ViT, require all the input image tokens to learn the relationship among them. However, many of these tokens are not informative and may contain irrelevant information such as unrelated background or unimportant scenery. These tokens are overlooked by the multi-head self-attention (MHSA), resulting in many redundant and unnecessary computations in MHSA and the feed-forward network (FFN). In this work, we propose a method to optimize the amount of unnecessary interactions between unimportant tokens by separating and sending them through a different low-cost computational path. Our method does not add any parameters to the ViT model and aims to find the best trade-off between training throughput and achieving a 0% loss in the Top-1 accuracy of the final model. Our experimental results on training ViT-small from scratch show that SkipViT is capable of effectively dropping 55% of the tokens while gaining more than 13% training throughput and maintaining classification accuracy at the level of the baseline model on Huawei Ascend910A.
Authors: Haocong Rao, Chunyan Miao
Person re-identification via 3D skeletons is an important emerging research area that triggers great interest in the pattern recognition community. With distinctive advantages for many application scenarios, a great diversity of 3D skeleton based person re-identification (SRID) methods have been proposed in recent years, effectively addressing prominent problems in skeleton modeling and feature learning. Despite recent advances, to the best of our knowledge, little effort has been made to comprehensively summarize these studies and their challenges. In this paper, we attempt to fill this gap by providing a systematic survey on current SRID approaches, model designs, challenges, and future directions. Specifically, we first formulate the SRID problem, and propose a taxonomy of SRID research with a summary of benchmark datasets, commonly-used model architectures, and an analytical review of different methods' characteristics. Then, we elaborate on the design principles of SRID models from multiple aspects to offer key insights for model improvement. Finally, we identify critical challenges confronting current studies and discuss several promising directions for future research of SRID.
Authors: Hongkun Sun, Jing Xu, Yuping Duan
The convolutional neural network-based methods have become more and more popular for medical image segmentation due to their outstanding performance. However, they struggle with capturing long-range dependencies, which are essential for accurately modeling global contextual correlations. Thanks to the ability to model long-range dependencies by expanding the receptive field, the transformer-based methods have gained prominence. Inspired by this, we propose an advanced 2D feature extraction method by combining the convolutional neural network and Transformer architectures. More specifically, we introduce a parallelized encoder structure, where one branch uses ResNet to extract local information from images, while the other branch uses Transformer to extract global information. Furthermore, we integrate pyramid structures into the Transformer to extract global information at varying resolutions, especially in intensive prediction tasks. To efficiently utilize the different information in the parallelized encoder at the decoder stage, we use a channel attention module to merge the features of the encoder and propagate them through skip connections and bottlenecks. Intensive numerical experiments are performed on both aortic vessel tree, cardiac, and multi-organ datasets. By comparing with state-of-the-art medical image segmentation methods, our method is shown with better segmentation accuracy, especially on small organs. The code is publicly available on https://github.com/HongkunSun/ParaTransCNN.
Authors: Kihoon Shin, Hyunjae Sim, Seungwon Nam, Yonghee Kim, Jae Hu, Kwang-Ki K. Kim
In this paper, we consider multi-robot localization problems with focus on cooperative localization and observability analysis of relative pose estimation. For cooperative localization, there is extra information available to each robot via communication network and message passing. If odometry data of a target robot can be transmitted to the ego-robot then the observability of their relative pose estimation can be achieved by range-only or bearing-only measurements provided both of their linear velocities are non-zero. If odometry data of a target robot is not directly transmitted but estimated by the ego-robot then there must be both range and bearing measurements to guarantee the observability of relative pose estimation. For ROS/Gazebo simulations, we consider four different sensing and communication structures in which extended Kalman filtering (EKF) and pose graph optimization (PGO) estimation with different robust loss functions (filtering and smoothing with different batch sizes of sliding window) are compared in terms of estimation accuracy. For hardware experiments, two Turtlebot3 equipped with UWB modules are used for real-world inter-robot relative pose estimation, in which both EKF and PGO are applied and compared.
Authors: Yutao Feng, Xiang Feng, Yintong Shang, Ying Jiang, Chang Yu, Zeshun Zong, Tianjia Shao, Hongzhi Wu, Kun Zhou, Chenfanfu Jiang, Yin Yang
We demonstrate the feasibility of integrating physics-based animations of solids and fluids with 3D Gaussian Splatting (3DGS) to create novel effects in virtual scenes reconstructed using 3DGS. Leveraging the coherence of the Gaussian splatting and position-based dynamics (PBD) in the underlying representation, we manage rendering, view synthesis, and the dynamics of solids and fluids in a cohesive manner. Similar to Gaussian shader, we enhance each Gaussian kernel with an added normal, aligning the kernel's orientation with the surface normal to refine the PBD simulation. This approach effectively eliminates spiky noises that arise from rotational deformation in solids. It also allows us to integrate physically based rendering to augment the dynamic surface reflections on fluids. Consequently, our framework is capable of realistically reproducing surface highlights on dynamic fluids and facilitating interactions between scene objects and fluids from new views. For more information, please visit our project page at \url{https://amysteriouscat.github.io/GaussianSplashing/}.
Authors: Kaixin Xiong, Dingyuan Zhang, Dingkang Liang, Zhe Liu, Hongcheng Yang, Wondimu Dikubab, Jianwei Cheng, Xiang Bai
Monocular 3D Object Detection is an essential task for autonomous driving. Meanwhile, accurate 3D object detection from pure images is very challenging due to the loss of depth information. Most existing image-based methods infer objects' location in 3D space based on their 2D sizes on the image plane, which usually ignores the intrinsic position clues from images, leading to unsatisfactory performances. Motivated by the fact that humans could leverage the bottom-up positional clues to locate objects in 3D space from a single image, in this paper, we explore the position modeling from the image feature column and propose a new method named You Only Look Bottum-Up (YOLOBU). Specifically, our YOLOBU leverages Column-based Cross Attention to determine how much a pixel contributes to pixels above it. Next, the Row-based Reverse Cumulative Sum (RRCS) is introduced to build the connections of pixels in the bottom-up direction. Our YOLOBU fully explores the position clues for monocular 3D detection via building the relationship of pixels from the bottom-up way. Extensive experiments on the KITTI dataset demonstrate the effectiveness and superiority of our method.
Authors: Ping Guo, Fei Liu, Xi Lin, Qingchuan Zhao, Qingfu Zhang
In the rapidly evolving field of machine learning, adversarial attacks present a significant challenge to model robustness and security. Decision-based attacks, which only require feedback on the decision of a model rather than detailed probabilities or scores, are particularly insidious and difficult to defend against. This work introduces L-AutoDA (Large Language Model-based Automated Decision-based Adversarial Attacks), a novel approach leveraging the generative capabilities of Large Language Models (LLMs) to automate the design of these attacks. By iteratively interacting with LLMs in an evolutionary framework, L-AutoDA automatically designs competitive attack algorithms efficiently without much human effort. We demonstrate the efficacy of L-AutoDA on CIFAR-10 dataset, showing significant improvements over baseline methods in both success rate and computational efficiency. Our findings underscore the potential of language models as tools for adversarial attack generation and highlight new avenues for the development of robust AI systems.
Authors: Beijia Chen, Yuefan Shen, Qing Shuai, Xiaowei Zhou, Kun Zhou, Youyi Zheng
Recent communities have seen significant progress in building photo-realistic animatable avatars from sparse multi-view videos. However, current workflows struggle to render realistic garment dynamics for loose-fitting characters as they predominantly rely on naked body models for human modeling while leaving the garment part un-modeled. This is mainly due to that the deformations yielded by loose garments are highly non-rigid, and capturing such deformations often requires dense views as supervision. In this paper, we introduce AniDress, a novel method for generating animatable human avatars in loose clothes using very sparse multi-view videos (4-8 in our setting). To allow the capturing and appearance learning of loose garments in such a situation, we employ a virtual bone-based garment rigging model obtained from physics-based simulation data. Such a model allows us to capture and render complex garment dynamics through a set of low-dimensional bone transformations. Technically, we develop a novel method for estimating temporal coherent garment dynamics from a sparse multi-view video. To build a realistic rendering for unseen garment status using coarse estimations, a pose-driven deformable neural radiance field conditioned on both body and garment motions is introduced, providing explicit control of both parts. At test time, the new garment poses can be captured from unseen situations, derived from a physics-based or neural network-based simulator to drive unseen garment dynamics. To evaluate our approach, we create a multi-view dataset that captures loose-dressed performers with diverse motions. Experiments show that our method is able to render natural garment dynamics that deviate highly from the body and generalize well to both unseen views and poses, surpassing the performance of existing methods. The code and data will be publicly available.
Authors: Ye Zhang, Yulu Gong, Dongji Cui, Xinrui Li, Xinyu Shen
Gastrointestinal (GI) tract cancers pose a global health challenge, demanding precise radiotherapy planning for optimal treatment outcomes. This paper introduces a cutting-edge approach to automate the segmentation of GI tract regions in magnetic resonance imaging (MRI) scans. Leveraging advanced deep learning architectures, the proposed model integrates Inception-V4 for initial classification, UNet++ with a VGG19 encoder for 2.5D data, and Edge UNet for grayscale data segmentation. Meticulous data preprocessing, including innovative 2.5D processing, is employed to enhance adaptability, robustness, and accuracy.
This work addresses the manual and time-consuming segmentation process in current radiotherapy planning, presenting a unified model that captures intricate anatomical details. The integration of diverse architectures, each specializing in unique aspects of the segmentation task, signifies a novel and comprehensive solution. This model emerges as an efficient and accurate tool for clinicians, marking a significant advancement in the field of GI tract image segmentation for radiotherapy planning.
Authors: Ayush Dubey, Shiv Ram Dubey, Satish Kumar Singh, Wei-Ta Chu
Unsupervised image retrieval aims to learn the important visual characteristics without any given level to retrieve the similar images for a given query image. The Convolutional Neural Network (CNN)-based approaches have been extensively exploited with self-supervised contrastive learning for image hashing. However, the existing approaches suffer due to lack of effective utilization of global features by CNNs and biased-ness created by false negative pairs in the contrastive learning. In this paper, we propose a TransClippedCLR model by encoding the global context of an image using Transformer having local context through patch based processing, by generating the hash codes through product quantization and by avoiding the potential false negative pairs through clipped contrastive learning. The proposed model is tested with superior performance for unsupervised image retrieval on benchmark datasets, including CIFAR10, NUS-Wide and Flickr25K, as compared to the recent state-of-the-art deep models. The results using the proposed clipped contrastive learning are greatly improved on all datasets as compared to same backbone network with vanilla contrastive learning.
Authors: Pengjie Wang, Kaile Zhang, Yuliang Liu, Jinpeng Wan, Haisu Guan, Zhebin Kuang, Xinyu Wang, Lianwen Jin, Xiang Bai
Oracle Bone Script (OBS), one of the earliest known forms of ancient Chinese writing, holds invaluable insights into the humanities and geography of the Shang Dynasty, dating back 3,000 years. The immense historical and cultural significance of these writings cannot be overstated. However, the passage of time has obscured much of their meaning, presenting a significant challenge in deciphering these ancient texts. With the advent of Artificial Intelligence (AI), employing AI to assist in interpreting OBS has become a feasible option. Yet, progress in this area has been hindered by a lack of high-quality datasets. To address this issue, this paper details the creation of the HUST-OBS dataset. This dataset encompasses 77,064 images of 1,588 individual deciphered scripts and 62,989 images of 9,411 undeciphered characters, with a total of 140,053 images, compiled from diverse sources. Additionally, all images and labels have been reviewed and corrected by experts in oracle bone studies. The hope is that this dataset could inspire and assist future research in deciphering those unknown OBS.
Authors: Trinetra Devkatte, Shiv Ram Dubey, Satish Kumar Singh, Abdenour Hadid
Facial super-resolution/hallucination is an important area of research that seeks to enhance low-resolution facial images for a variety of applications. While Generative Adversarial Networks (GANs) have shown promise in this area, their ability to adapt to new, unseen data remains a challenge. This paper addresses this problem by proposing an incremental super-resolution using GANs with knowledge distillation (ISR-KD) for face to cartoon. Previous research in this area has not investigated incremental learning, which is critical for real-world applications where new data is continually being generated. The proposed ISR-KD aims to develop a novel unified framework for facial super-resolution that can handle different settings, including different types of faces such as cartoon face and various levels of detail. To achieve this, a GAN-based super-resolution network was pre-trained on the CelebA dataset and then incrementally trained on the iCartoonFace dataset, using knowledge distillation to retain performance on the CelebA test set while improving the performance on iCartoonFace test set. Our experiments demonstrate the effectiveness of knowledge distillation in incrementally adding capability to the model for cartoon face super-resolution while retaining the learned knowledge for facial hallucination tasks in GANs.
Authors: Matthew Gadd, Paul Newman
Radar place recognition often involves encoding a live scan as a vector and matching this vector to a database in order to recognise that the vehicle is in a location that it has visited before. Radar is inherently robust to lighting or weather conditions, but place recognition with this sensor is still affected by: (1) viewpoint variation, i.e. translation and rotation, (2) sensor artefacts or "noises". For 360-degree scanning radar, rotation is readily dealt with by in some way aggregating across azimuths. Also, we argue in this work that it is more critical to deal with the richness of representation and sensor noises than it is to deal with translational invariance - particularly in urban driving where vehicles predominantly follow the same lane when repeating a route. In our method, for computational efficiency, we use only the polar representation. For partial translation invariance and robustness to signal noise, we use only a one-dimensional Fourier Transform along radial returns. We also achieve rotational invariance and a very discriminative descriptor space by building a vector of locally aggregated descriptors. Our method is more comprehensively tested than all prior radar place recognition work - over an exhaustive combination of all 870 pairs of trajectories from 30 Oxford Radar RobotCar Dataset sequences (each approximately 10 km). Code and detailed results are provided at github.com/mttgdd/open-radvlad, as an open implementation and benchmark for future work in this area. We achieve a median of 91.52% in Recall@1, outstripping the 69.55% for the only other open implementation, RaPlace, and at a fraction of its computational cost (relying on fewer integral transforms e.g. Radon, Fourier, and inverse Fourier).
Authors: Lingchen Yang, Gaspard Zoss, Prashanth Chandran, Paulo Gotardo, Markus Gross, Barbara Solenthaler, Eftychios Sifakis, Derek Bradley
3D facial animation is often produced by manipulating facial deformation models (or rigs), that are traditionally parameterized by expression controls. A key component that is usually overlooked is expression 'style', as in, how a particular expression is performed. Although it is common to define a semantic basis of expressions that characters can perform, most characters perform each expression in their own style. To date, style is usually entangled with the expression, and it is not possible to transfer the style of one character to another when considering facial animation. We present a new face model, based on a data-driven implicit neural physics model, that can be driven by both expression and style separately. At the core, we present a framework for learning implicit physics-based actuations for multiple subjects simultaneously, trained on a few arbitrary performance capture sequences from a small set of identities. Once trained, our method allows generalized physics-based facial animation for any of the trained identities, extending to unseen performances. Furthermore, it grants control over the animation style, enabling style transfer from one character to another or blending styles of different characters. Lastly, as a physics-based model, it is capable of synthesizing physical effects, such as collision handling, setting our method apart from conventional approaches.
Authors: Yue Zhou, Chenlu Guo, Xu Wang, Yi Chang, Yuan Wu
Large models, encompassing large language and diffusion models, have shown exceptional promise in approximating human-level intelligence, garnering significant interest from both academic and industrial spheres. However, the training of these large models necessitates vast quantities of high-quality data, and with continuous updates to these models, the existing reservoir of high-quality data may soon be depleted. This challenge has catalyzed a surge in research focused on data augmentation methods. Leveraging large models, these data augmentation techniques have outperformed traditional approaches. This paper offers an exhaustive review of large model-driven data augmentation methods, adopting a comprehensive perspective. We begin by establishing a classification of relevant studies into three main categories: image augmentation, text augmentation, and paired data augmentation. Following this, we delve into various data post-processing techniques pertinent to large model-based data augmentation. Our discussion then expands to encompass the array of applications for these data augmentation methods within natural language processing, computer vision, and audio signal processing. We proceed to evaluate the successes and limitations of large model-based data augmentation across different scenarios. Concluding our review, we highlight prospective challenges and avenues for future exploration in the field of data augmentation. Our objective is to furnish researchers with critical insights, ultimately contributing to the advancement of more sophisticated large models. We consistently maintain the related open-source materials at: https://github.com/MLGroup-JLU/LLM-data-aug-survey.
Authors: Jingyun Chen, Yading Yuan
Federated Learning (FL) enables collaborative model training among medical centers without sharing private data. However, traditional FL risks on server failures and suboptimal performance on local data due to the nature of centralized model aggregation. To address these issues, we present Gossip Mutual Learning (GML), a decentralized framework that uses Gossip Protocol for direct peer-to-peer communication. In addition, GML encourages each site to optimize its local model through mutual learning to account for data variations among different sites. For the task of tumor segmentation using 146 cases from four clinical sites in BraTS 2021 dataset, we demonstrated GML outperformed local models and achieved similar performance as FedAvg with only 25% communication overhead.
Authors: Xiao Liu, Alessandra Mileo, Alan F. Smeaton
In-situ monitoring incorporating data from visual and other sensor technologies, allows the collection of extensive datasets during the Additive Manufacturing (AM) process. These datasets have potential for determining the quality of the manufactured output and the detection of defects through the use of Machine Learning during the manufacturing process. Open and annotated datasets derived from AM processes are necessary for the machine learning community to address this opportunity, which creates difficulties in the application of computer vision-related machine learning in AM. This systematic review investigates the availability of open image-based datasets originating from AM processes that align with a number of pre-defined selection criteria. The review identifies existing gaps among the current image-based datasets in the domain of AM, and points to the need for greater availability of open datasets in order to allow quality assessment and defect detection during additive manufacturing, to develop.
Authors: Rahul Banavathu, Modem Veda Sree, Bollina Kavya Sri, Suddhasil De
Object detection in reduced visibility has become a prominent research area. The existing techniques are not accurate enough in recognizing objects under such circumstances. This paper introduces a new foggy object detection method through a two-staged architecture of region identification from input images and detecting objects in such regions. The paper confirms notable improvements of the proposed method's accuracy and detection time over existing techniques.
Authors: Yang Li, Doudou Zhang, Jianli Xiao
Intelligent Transportation Systems (ITS) utilize sensors, cameras, and big data analysis to monitor real-time traffic conditions, aiming to improve traffic efficiency and safety. Accurate vehicle recognition is crucial in this process, and Vehicle Logo Recognition (VLR) stands as a key method. VLR enables effective management and monitoring by distinguishing vehicles on the road. Convolutional Neural Networks (CNNs) have made impressive strides in VLR research. However, achieving higher performance demands significant time and computational resources for training. Recently, the rise of Transformer models has brought new opportunities to VLR. Swin Transformer, with its efficient computation and global feature modeling capabilities, outperforms CNNs under challenging conditions. In this paper, we implement real-time VLR using Swin Transformer and fine-tune it for optimal performance. Extensive experiments conducted on three public vehicle logo datasets (HFUT-VL1, XMU, CTGU-VLD) demonstrate impressive top accuracy results of 99.28%, 100%, and 99.17%, respectively. Additionally, the use of a transfer learning strategy enables our method to be on par with state-of-the-art VLR methods. These findings affirm the superiority of our approach over existing methods. Future research can explore and optimize the application of the Swin Transformer in other vehicle vision recognition tasks to drive advancements in ITS.
Authors: Bin Ren, Mengyuan Liu, Runwei Ding, Hong Liu
3D skeleton-based action recognition (3D SAR) has gained significant attention within the computer vision community, owing to the inherent advantages offered by skeleton data. As a result, a plethora of impressive works, including those based on conventional handcrafted features and learned feature extraction methods, have been conducted over the years. However, prior surveys on action recognition have primarily focused on video or RGB data-dominated approaches, with limited coverage of reviews related to skeleton data. Furthermore, despite the extensive application of deep learning methods in this field, there has been a notable absence of research that provides an introductory or comprehensive review from the perspective of deep learning architectures. To address these limitations, this survey first underscores the importance of action recognition and emphasizes the significance of 3D skeleton data as a valuable modality. Subsequently, we provide a comprehensive introduction to mainstream action recognition techniques based on four fundamental deep architectures, i.e., Recurrent Neural Networks (RNNs), Convolutional Neural Networks (CNNs), Graph Convolutional Network (GCN), and Transformers. All methods with the corresponding architectures are then presented in a data-driven manner with detailed discussion. Finally, we offer insights into the current largest 3D skeleton dataset, NTU-RGB+D, and its new edition, NTU-RGB+D 120, along with an overview of several top-performing algorithms on these datasets. To the best of our knowledge, this research represents the first comprehensive discussion of deep learning-based action recognition using 3D skeleton data.
Authors: Qianqian Wang, Xiaowei Zhou, Bharath Hariharan, Noah Snavely
Recent research on learned visual descriptors has shown promising improvements in correspondence estimation, a key component of many 3D vision tasks. However, existing descriptor learning frameworks typically require ground-truth correspondences between feature points for training, which are challenging to acquire at scale. In this paper we propose a novel weakly-supervised framework that can learn feature descriptors solely from relative camera poses between images. To do so, we devise both a new loss function that exploits the epipolar constraint given by camera poses, and a new model architecture that makes the whole pipeline differentiable and efficient. Because we no longer need pixel-level ground-truth correspondences, our framework opens up the possibility of training on much larger and more diverse datasets for better and unbiased descriptors. We call the resulting descriptors CAmera Pose Supervised, or CAPS, descriptors. Though trained with weak supervision, CAPS descriptors outperform even prior fully-supervised descriptors and achieve state-of-the-art performance on a variety of geometric tasks. Project Page: https://qianqianwang68.github.io/CAPS/
Authors: Yoon Gyo Jung, Jaewoo Park, Cheng Yaw Low, Jacky Chen Long Chai, Leslie Ching Ow Tiong, Andrew Beng Jin Teoh
Periocular biometric, the peripheral area of the ocular, is a collaborative alternative to the face, especially when the face is occluded or masked. However, in practice, sole periocular biometric capture the least salient facial features, thereby lacking discriminative information, particularly in wild environments. To address these problems, we transfer discriminatory information from the face to support the training of a periocular network by using knowledge distillation. Specifically, we leverage face images for periocular embedding learning, but periocular alone is utilized for identity identification or verification. To enhance periocular embeddings by face effectively, we proposeConsistent Knowledge Distillation (CKD) that imposes consistency between face and periocular networks across prediction and feature layers. We find that imposing consistency at the prediction layer enables (1) extraction of global discriminative relationship information from face images and (2) effective transfer of the information from the face network to the periocular network. Particularly, consistency regularizes the prediction units to extract and store profound inter-class relationship information of face images. (3) The feature layer consistency, on the other hand, makes the periocular features robust against identity-irrelevant attributes. Overall, CKD empowers the sole periocular network to produce robust discriminative embeddings for periocular recognition in the wild. We theoretically and empirically validate the core principles of the distillation mechanism in CKD, discovering that CKD is equivalent to label smoothing with a novel sparsity-oriented regularizer that helps the network prediction to capture the global discriminative relationship. Extensive experiments reveal that CKD achieves state-of-the-art results on standard periocular recognition benchmark datasets.
Authors: Abhranil Das, Wilson S Geisler
Univariate and multivariate normal probability distributions are widely used when modeling decisions under uncertainty. Computing the performance of such models requires integrating these distributions over specific domains, which can vary widely across models. Besides some special cases, there exist no general analytical expressions, standard numerical methods or software for these integrals. Here we present mathematical results and open-source software that provide (i) the probability in any domain of a normal in any dimensions with any parameters, (ii) the probability density, cumulative distribution, and inverse cumulative distribution of any function of a normal vector, (iii) the classification errors among any number of normal distributions, the Bayes-optimal discriminability index and relation to the operating characteristic, (iv) dimension reduction and visualizations for such problems, and (v) tests for how reliably these methods may be used on given data. We demonstrate these tools with vision research applications of detecting occluding objects in natural scenes, and detecting camouflage.
Authors: Haimin Zhang, Min Xu
Deep neural networks have been successfully applied in various machine learning tasks. However, studies show that neural networks are susceptible to adversarial attacks. This exposes a potential threat to neural network-based intelligent systems. We observe that the probability of the correct result outputted by the neural network increases by applying small first-order perturbations generated for non-predicted class labels to adversarial examples. Based on this observation, we propose a method for counteracting adversarial perturbations to improve adversarial robustness. In the proposed method, we randomly select a number of class labels and generate small first-order perturbations for these selected labels. The generated perturbations are added together and then clamped onto a specified space. The obtained perturbation is finally added to the adversarial example to counteract the adversarial perturbation contained in the example. The proposed method is applied at inference time and does not require retraining or finetuning the model. We experimentally validate the proposed method on CIFAR-10 and CIFAR-100. The results demonstrate that our method effectively improves the defense performance of several transformation-based defense methods, especially against strong adversarial examples generated using more iterations.
Authors: Cong Xu, Wei Zhang, Jun Wang, Min Yang
The adversarial robustness of a neural network mainly relies on two factors: model capacity and anti-perturbation ability. In this paper, we study the anti-perturbation ability of the network from the feature maps of convolutional layers. Our theoretical analysis discovers that larger convolutional feature maps before average pooling can contribute to better resistance to perturbations, but the conclusion is not true for max pooling. It brings new inspiration to the design of robust neural networks and urges us to apply these findings to improve existing architectures. The proposed modifications are very simple and only require upsampling the inputs or slightly modifying the stride configurations of downsampling operators. We verify our approaches on several benchmark neural network architectures, including AlexNet, VGG, RestNet18, and PreActResNet18. Non-trivial improvements in terms of both natural accuracy and adversarial robustness can be achieved under various attack and defense mechanisms. The code is available at \url{https://github.com/MTandHJ/rcm}.
Authors: Kiran Mantripragada, Faisal Z. Qureshi
We present a method for hyperspectral pixel {\it unmixing}. The proposed method assumes that (1) {\it abundances} can be encoded as Dirichlet distributions and (2) spectra of {\it endmembers} can be represented as multivariate Normal distributions. The method solves the problem of abundance estimation and endmember extraction within a variational autoencoder setting where a Dirichlet bottleneck layer models the abundances, and the decoder performs endmember extraction. The proposed method can also leverage transfer learning paradigm, where the model is only trained on synthetic data containing pixels that are linear combinations of one or more endmembers of interest. In this case, we retrieve endmembers (spectra) from the United States Geological Survey Spectral Library. The model thus trained can be subsequently used to perform pixel unmixing on "real data" that contains a subset of the endmembers used to generated the synthetic data. The model achieves state-of-the-art results on several benchmarks: Cuprite, Urban Hydice and Samson. We also present new synthetic dataset, OnTech-HSI-Syn-21, that can be used to study hyperspectral pixel unmixing methods. We showcase the transfer learning capabilities of the proposed model on Cuprite and OnTech-HSI-Syn-21 datasets. In summary, the proposed method can be applied for pixel unmixing a variety of domains, including agriculture, forestry, mineralogy, analysis of materials, healthcare, etc. Additionally, the proposed method eschews the need for labelled data for training by leveraging the transfer learning paradigm, where the model is trained on synthetic data generated using the endmembers present in the "real" data.
Authors: Minghui Wu, Yangdi Xu, Yingying Xu, Guangwei Wu, Qingqing Chen, Hongxiang Lin
Large Vision Model (LVM) has recently demonstrated great potential for medical imaging tasks, potentially enabling image enhancement for sparse-view Cone-Beam Computed Tomography (CBCT), despite requiring a substantial amount of data for training. Meanwhile, Deep Image Prior (DIP) effectively guides an untrained neural network to generate high-quality CBCT images without any training data. However, the original DIP method relies on a well-defined forward model and a large-capacity backbone network, which is notoriously difficult to converge. In this paper, we propose a stable optimization method for the forward-model-free, LVM-based DIP model for sparse-view CBCT. Our approach consists of two main characteristics: (1) multi-scale perceptual loss (MSPL) which measures the similarity of perceptual features between the reference and output images at multiple resolutions without the need for any forward model, and (2) a reweighting mechanism that stabilizes the iteration trajectory of MSPL. One shot optimization is used to simultaneously and stably reweight MSPL and optimize LVM. We evaluate our approach on two publicly available datasets: SPARE and Walnut. The results show significant improvements in both image quality metrics and visualization that demonstrates reduced streak artifacts. The source code is available upon request.
Authors: Tianshui Chen, Tao Pu, Lingbo Liu, Yukai Shi, Zhijing Yang, Liang Lin
Multi-label image recognition with partial labels (MLR-PL), in which some labels are known while others are unknown for each image, may greatly reduce the cost of annotation and thus facilitate large-scale MLR. We find that strong semantic correlations exist within each image and across different images, and these correlations can help transfer the knowledge possessed by the known labels to retrieve the unknown labels and thus improve the performance of the MLR-PL task (see Figure 1). In this work, we propose a novel heterogeneous semantic transfer (HST) framework that consists of two complementary transfer modules that explore both within-image and cross-image semantic correlations to transfer the knowledge possessed by known labels to generate pseudo labels for the unknown labels. Specifically, an intra-image semantic transfer (IST) module learns an image-specific label co-occurrence matrix for each image and maps the known labels to complement the unknown labels based on these matrices. Additionally, a cross-image transfer (CST) module learns category-specific feature-prototype similarities and then helps complement the unknown labels that have high degrees of similarity with the corresponding prototypes. Finally, both the known and generated pseudo labels are used to train MLR models. Extensive experiments conducted on the Microsoft COCO, Visual Genome, and Pascal VOC 2007 datasets show that the proposed HST framework achieves superior performance to that of current state-of-the-art algorithms. Specifically, it obtains mean average precision (mAP) improvements of 1.4%, 3.3%, and 0.4% on the three datasets over the results of the best-performing previously developed algorithm.
Authors: Tao Pu, Tianshui Chen, Hefeng Wu, Yukai Shi, Zhijing Yang, Liang Lin
Despite achieving impressive progress, current multi-label image recognition (MLR) algorithms heavily depend on large-scale datasets with complete labels, making collecting large-scale datasets extremely time-consuming and labor-intensive. Training the multi-label image recognition models with partial labels (MLR-PL) is an alternative way, in which merely some labels are known while others are unknown for each image. However, current MLP-PL algorithms rely on pre-trained image similarity models or iteratively updating the image classification models to generate pseudo labels for the unknown labels. Thus, they depend on a certain amount of annotations and inevitably suffer from obvious performance drops, especially when the known label proportion is low. To address this dilemma, we propose a dual-perspective semantic-aware representation blending (DSRB) that blends multi-granularity category-specific semantic representation across different images, from instance and prototype perspective respectively, to transfer information of known labels to complement unknown labels. Specifically, an instance-perspective representation blending (IPRB) module is designed to blend the representations of the known labels in an image with the representations of the corresponding unknown labels in another image to complement these unknown labels. Meanwhile, a prototype-perspective representation blending (PPRB) module is introduced to learn more stable representation prototypes for each category and blends the representation of unknown labels with the prototypes of corresponding labels, in a location-sensitive manner, to complement these unknown labels. Extensive experiments on the MS-COCO, Visual Genome, and Pascal VOC 2007 datasets show that the proposed DSRB consistently outperforms current state-of-the-art algorithms on all known label proportion settings.
Authors: Angtian Wang, Peng Wang, Jian Sun, Adam Kortylewski, Alan Yuille
The Gaussian reconstruction kernels have been proposed by Westover (1990) and studied by the computer graphics community back in the 90s, which gives an alternative representation of object 3D geometry from meshes and point clouds. On the other hand, current state-of-the-art (SoTA) differentiable renderers, Liu et al. (2019), use rasterization to collect triangles or points on each image pixel and blend them based on the viewing distance. In this paper, we propose VoGE, which utilizes the volumetric Gaussian reconstruction kernels as geometric primitives. The VoGE rendering pipeline uses ray tracing to capture the nearest primitives and blends them as mixtures based on their volume density distributions along the rays. To efficiently render via VoGE, we propose an approximate closeform solution for the volume density aggregation and a coarse-to-fine rendering strategy. Finally, we provide a CUDA implementation of VoGE, which enables real-time level rendering with a competitive rendering speed in comparison to PyTorch3D. Quantitative and qualitative experiment results show VoGE outperforms SoTA counterparts when applied to various vision tasks, e.g., object pose estimation, shape/texture fitting, and occlusion reasoning. The VoGE library and demos are available at: https://github.com/Angtian/VoGE.
Authors: Kyle Otstot, Andrew Yang, John Kevin Cava, Lalitha Sankar
Deep Learning (DL) models achieve great successes in many domains. However, DL models increasingly face safety and robustness concerns, including noisy labeling in the training stage and feature distribution shifts in the testing stage. Previous works made significant progress in addressing these problems, but the focus has largely been on developing solutions for only one problem at a time. For example, recent work has argued for the use of tunable robust loss functions to mitigate label noise, and data augmentation (e.g., AugMix) to combat distribution shifts. As a step towards addressing both problems simultaneously, we introduce AugLoss, a simple but effective methodology that achieves robustness against both train-time noisy labeling and test-time feature distribution shifts by unifying data augmentation and robust loss functions. We conduct comprehensive experiments in varied settings of real-world dataset corruption to showcase the gains achieved by AugLoss compared to previous state-of-the-art methods. Lastly, we hope this work will open new directions for designing more robust and reliable DL models under real-world corruptions.
Authors: Zhicheng Huang, Xiaojie Jin, Chengze Lu, Qibin Hou, Ming-Ming Cheng, Dongmei Fu, Xiaohui Shen, Jiashi Feng
Masked image modeling (MIM) has achieved promising results on various vision tasks. However, the limited discriminability of learned representation manifests there is still plenty to go for making a stronger vision learner. Towards this goal, we propose Contrastive Masked Autoencoders (CMAE), a new self-supervised pre-training method for learning more comprehensive and capable vision representations. By elaboratively unifying contrastive learning (CL) and masked image model (MIM) through novel designs, CMAE leverages their respective advantages and learns representations with both strong instance discriminability and local perceptibility. Specifically, CMAE consists of two branches where the online branch is an asymmetric encoder-decoder and the momentum branch is a momentum updated encoder. During training, the online encoder reconstructs original images from latent representations of masked images to learn holistic features. The momentum encoder, fed with the full images, enhances the feature discriminability via contrastive learning with its online counterpart. To make CL compatible with MIM, CMAE introduces two new components, i.e. pixel shifting for generating plausible positive views and feature decoder for complementing features of contrastive pairs. Thanks to these novel designs, CMAE effectively improves the representation quality and transfer performance over its MIM counterpart. CMAE achieves the state-of-the-art performance on highly competitive benchmarks of image classification, semantic segmentation and object detection. Notably, CMAE-Base achieves $85.3\%$ top-1 accuracy on ImageNet and $52.5\%$ mIoU on ADE20k, surpassing previous best results by $0.7\%$ and $1.8\%$ respectively. The source code is publicly accessible at \url{https://github.com/ZhichengHuang/CMAE}.
Authors: Kun Yan, Lei Ji, Chenfei Wu, Jian Liang, Ming Zhou, Nan Duan, Shuai Ma
Panorama synthesis endeavors to craft captivating 360-degree visual landscapes, immersing users in the heart of virtual worlds. Nevertheless, contemporary panoramic synthesis techniques grapple with the challenge of semantically guiding the content generation process. Although recent breakthroughs in visual synthesis have unlocked the potential for semantic control in 2D flat images, a direct application of these methods to panorama synthesis yields distorted content. In this study, we unveil an innovative framework for generating high-resolution panoramas, adeptly addressing the issues of spherical distortion and edge discontinuity through sophisticated spherical modeling. Our pioneering approach empowers users with semantic control, harnessing both image and text inputs, while concurrently streamlining the generation of high-resolution panoramas using parallel decoding. We rigorously evaluate our methodology on a diverse array of indoor and outdoor datasets, establishing its superiority over recent related work, in terms of both quantitative and qualitative performance metrics. Our research elevates the controllability, efficiency, and fidelity of panorama synthesis to new levels.
Authors: Hanieh Naderi, Chinthaka Dinesh, Ivan V. Bajic, Shohreh Kasaei
Adversarial attacks pose serious challenges for deep neural network (DNN)-based analysis of various input signals. In the case of 3D point clouds, methods have been developed to identify points that play a key role in network decision, and these become crucial in generating existing adversarial attacks. For example, a saliency map approach is a popular method for identifying adversarial drop points, whose removal would significantly impact the network decision. Generally, methods for identifying adversarial points rely on the access to the DNN model itself to determine which points are critically important for the model's decision. This paper aims to provide a novel viewpoint on this problem, where adversarial points can be predicted without access to the target DNN model, which is referred to as a ``no-box'' attack. To this end, we define 14 point cloud features and use multiple linear regression to examine whether these features can be used for adversarial point prediction, and which combination of features is best suited for this purpose. Experiments show that a suitable combination of features is able to predict adversarial points of four different networks -- PointNet, PointNet++, DGCNN, and PointConv -- significantly better than a random guess and comparable to white-box attacks. Additionally, we show that no-box attack is transferable to unseen models. The results also provide further insight into DNNs for point cloud classification, by showing which features play key roles in their decision-making process.
Authors: Guoyang Xie, Jinbao Wang, Jiaqi Liu, Jiayi Lyu, Yong Liu, Chengjie Wang, Feng Zheng, Yaochu Jin
Image anomaly detection (IAD) is an emerging and vital computer vision task in industrial manufacturing (IM). Recently, many advanced algorithms have been reported, but their performance deviates considerably with various IM settings. We realize that the lack of a uniform IM benchmark is hindering the development and usage of IAD methods in real-world applications. In addition, it is difficult for researchers to analyze IAD algorithms without a uniform benchmark. To solve this problem, we propose a uniform IM benchmark, for the first time, to assess how well these algorithms perform, which includes various levels of supervision (unsupervised versus fully supervised), learning paradigms (few-shot, continual and noisy label), and efficiency (memory usage and inference speed). Then, we construct a comprehensive image anomaly detection benchmark (IM-IAD), which includes 19 algorithms on seven major datasets with a uniform setting. Extensive experiments (17,017 total) on IM-IAD provide in-depth insights into IAD algorithm redesign or selection. Moreover, the proposed IM-IAD benchmark challenges existing algorithms and suggests future research directions. To foster reproducibility and accessibility, the source code of IM-IAD is uploaded on the website, https://github.com/M-3LAB/IM-IAD.
Authors: Pu Zhang, Tianhua Chen, Bin Liu
Deep learning has become the dominating approach for object detection. To achieve accurate fine-grained detection, one needs to employ a large enough model and a vast amount of data annotations. In this paper, we propose a commonsense knowledge inference module (CKIM) which leverages commonsense knowledge to assist a lightweight deep neural network base coarse-grained object detector to achieve accurate fine-grained detection. Specifically, we focus on a scenario where a single image contains objects of similar categories but varying sizes, and we establish a size-related commonsense knowledge inference module (CKIM) that maps the coarse-grained labels produced by the DL detector to size-related fine-grained labels. Considering that rule-based systems are one of the popular methods of knowledge representation and reasoning, our experiments explored two types of rule-based CKIMs, implemented using crisp-rule and fuzzy-rule approaches, respectively. Experimental results demonstrate that compared with baseline methods, our approach achieves accurate fine-grained detection with a reduced amount of annotated data and smaller model size. Our code is available at: https://github.com/ZJLAB-AMMI/CKIM.
Authors: Hadar Hezi, Daniel Shats, Daniel Gurevich, Yosef E. Maruvka, Moti Freiman
Molecular subtypes of colorectal cancer (CRC) significantly influence treatment decisions. While convolutional neural networks (CNNs) have recently been introduced for automated CRC subtype identification using H&E stained histopathological images, the correlation between CRC subtype genomic variants and their corresponding cellular morphology expressed by their imaging phenotypes is yet to be fully explored. The goal of this study was to determine such correlations by incorporating genomic variants in CNN models for CRC subtype classification from H&E images. We utilized the publicly available TCGA-CRC-DX dataset, which comprises whole slide images from 360 CRC-diagnosed patients (260 for training and 100 for testing). This dataset also provides information on CRC subtype classifications and genomic variations. We trained CNN models for CRC subtype classification that account for potential correlation between genomic variations within CRC subtypes and their corresponding cellular morphology patterns. We assessed the interplay between CRC subtypes' genomic variations and cellular morphology patterns by evaluating the CRC subtype classification accuracy of the different models in a stratified 5-fold cross-validation experimental setup using the area under the ROC curve (AUROC) and average precision (AP) as the performance metrics. Combining the CNN models account for variations in CIMP and SNP further improved classification accuracy (AUROC: 0.847$\pm$0.01 vs. 0.787$\pm$0.03, p$=$0.01, AP: 0.68$\pm$0.02 vs. 0.64$\pm$0.05).
Authors: Xianfan Gu, Chuan Wen, Weirui Ye, Jiaming Song, Yang Gao
Imagining the future trajectory is the key for robots to make sound planning and successfully reach their goals. Therefore, text-conditioned video prediction (TVP) is an essential task to facilitate general robot policy learning. To tackle this task and empower robots with the ability to foresee the future, we propose a sample and computation-efficient model, named \textbf{Seer}, by inflating the pretrained text-to-image (T2I) stable diffusion models along the temporal axis. We enhance the U-Net and language conditioning model by incorporating computation-efficient spatial-temporal attention. Furthermore, we introduce a novel Frame Sequential Text Decomposer module that dissects a sentence's global instruction into temporally aligned sub-instructions, ensuring precise integration into each frame of generation. Our framework allows us to effectively leverage the extensive prior knowledge embedded in pretrained T2I models across the frames. With the adaptable-designed architecture, Seer makes it possible to generate high-fidelity, coherent, and instruction-aligned video frames by fine-tuning a few layers on a small amount of data. The experimental results on Something Something V2 (SSv2), Bridgedata and EpicKitchens-100 datasets demonstrate our superior video prediction performance with around 480-GPU hours versus CogVideo with over 12,480-GPU hours: achieving the 31% FVD improvement compared to the current SOTA model on SSv2 and 83.7% average preference in the human evaluation.
Authors: Pengwei Liang, Junjun Jiang, Xianming Liu, Jiayi Ma
Image deblurring continues to achieve impressive performance with the development of generative models. Nonetheless, there still remains a displeasing problem if one wants to improve perceptual quality and quantitative scores of recovered image at the same time. In this study, drawing inspiration from the research of transformer properties, we introduce the pretrained transformers to address this problem. In particular, we leverage deep features extracted from a pretrained vision transformer (ViT) to encourage recovered images to be sharp without sacrificing the performance measured by the quantitative metrics. The pretrained transformer can capture the global topological relations (i.e., self-similarity) of image, and we observe that the captured topological relations about the sharp image will change when blur occurs. By comparing the transformer features between recovered image and target one, the pretrained transformer provides high-resolution blur-sensitive semantic information, which is critical in measuring the sharpness of the deblurred image. On the basis of the advantages, we present two types of novel perceptual losses to guide image deblurring. One regards the features as vectors and computes the discrepancy between representations extracted from recovered image and target one in Euclidean space. The other type considers the features extracted from an image as a distribution and compares the distribution discrepancy between recovered image and target one. We demonstrate the effectiveness of transformer properties in improving the perceptual quality while not sacrificing the quantitative scores (PSNR) over the most competitive models, such as Uformer, Restormer, and NAFNet, on defocus deblurring and motion deblurring tasks.
Authors: Sonia Raychaudhuri, Tommaso Campari, Unnat Jain, Manolis Savva, Angel X. Chang
We propose a simple but effective modular approach MOPA (Modular ObjectNav with PointGoal agents) to systematically investigate the inherent modularity of the object navigation task in Embodied AI. MOPA consists of four modules: (a) an object detection module trained to identify objects from RGB images, (b) a map building module to build a semantic map of the observed objects, (c) an exploration module enabling the agent to explore the environment, and (d) a navigation module to move to identified target objects. We show that we can effectively reuse a pretrained PointGoal agent as the navigation model instead of learning to navigate from scratch, thus saving time and compute. We also compare various exploration strategies for MOPA and find that a simple uniform strategy significantly outperforms more advanced exploration methods.
Authors: Mahdi S. Hosseini, Babak Ehteshami Bejnordi, Vincent Quoc-Huy Trinh, Danial Hasan, Xingwen Li, Taehyo Kim, Haochen Zhang, Theodore Wu, Kajanan Chinniah, Sina Maghsoudlou, Ryan Zhang, Stephen Yang, Jiadai Zhu, Lyndon Chan, Samir Khaki, Andrei Buin, Fatemeh Chaji, Ala Salehi, Bich Ngoc Nguyen, Dimitris Samaras, Konstantinos N. Plataniotis
Computational Pathology CPath is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images. The main objective for CPath is to develop infrastructure and workflows of digital diagnostics as an assistive CAD system for clinical pathology, facilitating transformational changes in the diagnosis and treatment of cancer that are mainly address by CPath tools. With evergrowing developments in deep learning and computer vision algorithms, and the ease of the data flow from digital pathology, currently CPath is witnessing a paradigm shift. Despite the sheer volume of engineering and scientific works being introduced for cancer image analysis, there is still a considerable gap of adopting and integrating these algorithms in clinical practice. This raises a significant question regarding the direction and trends that are undertaken in CPath. In this article we provide a comprehensive review of more than 800 papers to address the challenges faced in problem design all-the-way to the application and implementation viewpoints. We have catalogued each paper into a model-card by examining the key works and challenges faced to layout the current landscape in CPath. We hope this helps the community to locate relevant works and facilitate understanding of the field's future directions. In a nutshell, we oversee the CPath developments in cycle of stages which are required to be cohesively linked together to address the challenges associated with such multidisciplinary science. We overview this cycle from different perspectives of data-centric, model-centric, and application-centric problems. We finally sketch remaining challenges and provide directions for future technical developments and clinical integration of CPath (https://github.com/AtlasAnalyticsLab/CPath_Survey).
Authors: Cilin Yan, Haochen Wang, Jie Liu, Xiaolong Jiang, Yao Hu, Xu Tang, Guoliang Kang, Efstratios Gavves
Click-based interactive segmentation aims to generate target masks via human clicking, which facilitates efficient pixel-level annotation and image editing. In such a task, target ambiguity remains a problem hindering the accuracy and efficiency of segmentation. That is, in scenes with rich context, one click may correspond to multiple potential targets, while most previous interactive segmentors only generate a single mask and fail to deal with target ambiguity. In this paper, we propose a novel interactive segmentation network named PiClick, to yield all potentially reasonable masks and suggest the most plausible one for the user. Specifically, PiClick utilizes a Transformer-based architecture to generate all potential target masks by mutually interactive mask queries. Moreover, a Target Reasoning module is designed in PiClick to automatically suggest the user-desired mask from all candidates, relieving target ambiguity and extra-human efforts. Extensive experiments on 9 interactive segmentation datasets demonstrate PiClick performs favorably against previous state-of-the-arts considering the segmentation results. Moreover, we show that PiClick effectively reduces human efforts in annotating and picking the desired masks. To ease the usage and inspire future research, we release the source code of PiClick together with a plug-and-play annotation tool at https://github.com/cilinyan/PiClick.
Authors: Iris de Gélis (1 and 2), Thomas Corpetti (3), Sébastien Lefèvre (2) ((1) Magellium, (2) Institut de Recherche en Informatique et Systèmes Aléatoires IRISA - UMR 6074 - Université Bretagne Sud, (3) Littoral - Environnement - Télédétection - Géomatique LETG - UMR 6554 - Université Rennes 2)
Change detection is an important task that rapidly identifies modified areas, particularly when multi-temporal data are concerned. In landscapes with a complex geometry (e.g., urban environment), vertical information is a very useful source of knowledge that highlights changes and classifies them into different categories. In this study, we focus on change segmentation using raw three-dimensional (3D) point clouds (PCs) directly to avoid any information loss due to the rasterization processes. While deep learning has recently proven its effectiveness for this particular task by encoding the information through Siamese networks, we investigate herein the idea of also using change information in the early steps of deep networks. To do this, we first propose to provide a Siamese KPConv state-of-the-art (SoTA) network with hand-crafted features, especially a change-related one, which improves the mean of the Intersection over Union (IoU) over the classes of change by 4.70%. Considering that a major improvement is obtained due to the change-related feature, we then propose three new architectures to address 3D PC change segmentation: OneConvFusion, Triplet KPConv, and Encoder Fusion SiamKPConv. All these networks consider the change information in the early steps and outperform the SoTA methods. In particular, Encoder Fusion SiamKPConv overtakes the SoTA approaches by more than 5% of the mean of the IoU over the classes of change, emphasizing the value of having the network focus on change information for the change detection task. The code is available at https://github.com/IdeGelis/torch-points3d-SiamKPConvVariants.
Authors: Yicheng Zhan, Koray Kavaklı, Hakan Urey, Qi Sun, Kaan Akşit
Multi-color holograms rely on simultaneous illumination from multiple light sources. These multi-color holograms could utilize light sources better than conventional single-color holograms and can improve the dynamic range of holographic displays. In this letter, we introduce AutoColor , the first learned method for estimating the optimal light source powers required for illuminating multi-color holograms. For this purpose, we establish the first multi-color hologram dataset using synthetic images and their depth information. We generate these synthetic images using a trending pipeline combining generative, large language, and monocular depth estimation models. Finally, we train our learned model using our dataset and experimentally demonstrate that AutoColor significantly decreases the number of steps required to optimize multi-color holograms from > 1000 to 70 iteration steps without compromising image quality.
Authors: Mrinal Kanti Dhar, Taiyu Zhang, Yash Patel, Sandeep Gopalakrishnan, Zeyun Yu
This paper presents FUSegNet, a new model for foot ulcer segmentation in diabetes patients, which uses the pre-trained EfficientNet-b7 as a backbone to address the issue of limited training samples. A modified spatial and channel squeeze-and-excitation (scSE) module called parallel scSE or P-scSE is proposed that combines additive and max-out scSE. A new arrangement is introduced for the module by fusing it in the middle of each decoder stage. As the top decoder stage carries a limited number of feature maps, max-out scSE is bypassed there to form a shorted P-scSE. A set of augmentations, comprising geometric, morphological, and intensity-based augmentations, is applied before feeding the data into the network. The proposed model is first evaluated on a publicly available chronic wound dataset where it achieves a data-based dice score of 92.70%, which is the highest score among the reported approaches. The model outperforms other scSE-based UNet models in terms of Pratt's figure of merits (PFOM) scores in most categories, which evaluates the accuracy of edge localization. The model is then tested in the MICCAI 2021 FUSeg challenge, where a variation of FUSegNet called x-FUSegNet is submitted. The x-FUSegNet model, which takes the average of outputs obtained by FUSegNet using 5-fold cross-validation, achieves a dice score of 89.23%, placing it at the top of the FUSeg Challenge leaderboard. The source code for the model is available on https://github.com/mrinal054/FUSegNet.
Authors: Farhin Farhad Riya, Shahinul Hoque, Md Saif Hassan Onim, Edward Michaud, Edmon Begoli, Jinyuan Stella Sun
The widespread adoption of Image Processing has propelled Object Recognition (OR) models into essential roles across various applications, demonstrating the power of AI and enabling crucial services. Among the applications, traffic sign recognition stands out as a popular research topic, given its critical significance in the development of autonomous vehicles. Despite their significance, real-world challenges, such as alterations to traffic signs, can negatively impact the performance of OR models. This study investigates the influence of altered traffic signs on the accuracy and effectiveness of object recognition, employing a publicly available dataset to introduce alterations in shape, color, content, visibility, angles and background. Focusing on the YOLOv7 (You Only Look Once) model, the study demonstrates a notable decline in detection and classification accuracy when confronted with traffic signs in unusual conditions including the altered traffic signs. Notably, the alterations explored in this study are benign examples and do not involve algorithms used for generating adversarial machine learning samples. This study highlights the significance of enhancing the robustness of object detection models in real-life scenarios and the need for further investigation in this area to improve their accuracy and reliability.
Authors: Junqiao Zhao, Fenglin Zhang, Yingfeng Cai, Gengxuan Tian, Wenjie Mu, Chen Ye, Tiantian Feng
Visual Place Recognition (VPR) aims to retrieve frames from a geotagged database that are located at the same place as the query frame. To improve the robustness of VPR in perceptually aliasing scenarios, sequence-based VPR methods are proposed. These methods are either based on matching between frame sequences or extracting sequence descriptors for direct retrieval. However, the former is usually based on the assumption of constant velocity, which is difficult to hold in practice, and is computationally expensive and subject to sequence length. Although the latter overcomes these problems, existing sequence descriptors are constructed by aggregating features of multiple frames only, without interaction on temporal information, and thus cannot obtain descriptors with spatio-temporal discrimination.In this paper, we propose a sequence descriptor that effectively incorporates spatio-temporal information. Specifically, spatial attention within the same frame is utilized to learn spatial feature patterns, while attention in corresponding local regions of different frames is utilized to learn the persistence or change of features over time. We use a sliding window to control the temporal range of attention and use relative positional encoding to construct sequential relationships between different features. This allows our descriptors to capture the intrinsic dynamics in a sequence of frames.Comprehensive experiments on challenging benchmark datasets show that the proposed approach outperforms recent state-of-the-art methods.The code is available at https://github.com/tiev-tongji/Spatio-Temporal-SeqVPR.
Authors: Zheyuan Liu, Weixuan Sun, Damien Teney, Stephen Gould
Composed image retrieval aims to find an image that best matches a given multi-modal user query consisting of a reference image and text pair. Existing methods commonly pre-compute image embeddings over the entire corpus and compare these to a reference image embedding modified by the query text at test time. Such a pipeline is very efficient at test time since fast vector distances can be used to evaluate candidates, but modifying the reference image embedding guided only by a short textual description can be difficult, especially independent of potential candidates. An alternative approach is to allow interactions between the query and every possible candidate, i.e., reference-text-candidate triplets, and pick the best from the entire set. Though this approach is more discriminative, for large-scale datasets the computational cost is prohibitive since pre-computation of candidate embeddings is no longer possible. We propose to combine the merits of both schemes using a two-stage model. Our first stage adopts the conventional vector distancing metric and performs a fast pruning among candidates. Meanwhile, our second stage employs a dual-encoder architecture, which effectively attends to the input triplet of reference-text-candidate and re-ranks the candidates. Both stages utilize a vision-and-language pre-trained network, which has proven beneficial for various downstream tasks. Our method consistently outperforms state-of-the-art approaches on standard benchmarks for the task. Our implementation is available at https://github.com/Cuberick-Orion/Candidate-Reranking-CIR.
Authors: Linhao Qu, Xiaoyuan Luo, Kexue Fu, Manning Wang, Zhijian Song
This paper introduces the novel concept of few-shot weakly supervised learning for pathology Whole Slide Image (WSI) classification, denoted as FSWC. A solution is proposed based on prompt learning and the utilization of a large language model, GPT-4. Since a WSI is too large and needs to be divided into patches for processing, WSI classification is commonly approached as a Multiple Instance Learning (MIL) problem. In this context, each WSI is considered a bag, and the obtained patches are treated as instances. The objective of FSWC is to classify both bags and instances with only a limited number of labeled bags. Unlike conventional few-shot learning problems, FSWC poses additional challenges due to its weak bag labels within the MIL framework. Drawing inspiration from the recent achievements of vision-language models (V-L models) in downstream few-shot classification tasks, we propose a two-level prompt learning MIL framework tailored for pathology, incorporating language prior knowledge. Specifically, we leverage CLIP to extract instance features for each patch, and introduce a prompt-guided pooling strategy to aggregate these instance features into a bag feature. Subsequently, we employ a small number of labeled bags to facilitate few-shot prompt learning based on the bag features. Our approach incorporates the utilization of GPT-4 in a question-and-answer mode to obtain language prior knowledge at both the instance and bag levels, which are then integrated into the instance and bag level language prompts. Additionally, a learnable component of the language prompts is trained using the available few-shot labeled data. We conduct extensive experiments on three real WSI datasets encompassing breast cancer, lung cancer, and cervical cancer, demonstrating the notable performance of the proposed method in bag and instance classification. All codes will be available.
Authors: Nour Neifar, Achraf Ben-Hamadou, Afef Mdhaffar, Mohamed Jmaiel
Within cardiovascular disease detection using deep learning applied to ECG signals, the complexities of handling physiological signals have sparked growing interest in leveraging deep generative models for effective data augmentation. In this paper, we introduce a novel versatile approach based on denoising diffusion probabilistic models for ECG synthesis, addressing three scenarios: (i) heartbeat generation, (ii) partial signal imputation, and (iii) full heartbeat forecasting. Our approach presents the first generalized conditional approach for ECG synthesis, and our experimental results demonstrate its effectiveness for various ECG-related tasks. Moreover, we show that our approach outperforms other state-of-the-art ECG generative models and can enhance the performance of state-of-the-art classifiers.
Authors: Dingyuan Zhang, Dingkang Liang, Hongcheng Yang, Zhikang Zou, Xiaoqing Ye, Zhe Liu, Xiang Bai
With the development of large language models, many remarkable linguistic systems like ChatGPT have thrived and achieved astonishing success on many tasks, showing the incredible power of foundation models. In the spirit of unleashing the capability of foundation models on vision tasks, the Segment Anything Model (SAM), a vision foundation model for image segmentation, has been proposed recently and presents strong zero-shot ability on many downstream 2D tasks. However, whether SAM can be adapted to 3D vision tasks has yet to be explored, especially 3D object detection. With this inspiration, we explore adapting the zero-shot ability of SAM to 3D object detection in this paper. We propose a SAM-powered BEV processing pipeline to detect objects and get promising results on the large-scale Waymo open dataset. As an early attempt, our method takes a step toward 3D object detection with vision foundation models and presents the opportunity to unleash their power on 3D vision tasks. The code is released at https://github.com/DYZhang09/SAM3D.
Authors: Bohan Li, Yasheng Sun, Jingxin Dong, Zheng Zhu, Jinming Liu, Xin Jin, Wenjun Zeng
Numerous studies have investigated the pivotal role of reliable 3D volume representation in scene perception tasks, such as multi-view stereo (MVS) and semantic scene completion (SSC). They typically construct 3D probability volumes directly with geometric correspondence, attempting to fully address the scene perception tasks in a single forward pass. However, such a single-step solution makes it hard to learn accurate and convincing volumetric probability, especially in challenging regions like unexpected occlusions and complicated light reflections. Therefore, this paper proposes to decompose the complicated 3D volume representation learning into a sequence of generative steps to facilitate fine and reliable scene perception. Considering the recent advances achieved by strong generative diffusion models, we introduce a multi-step learning framework, dubbed as VPD, dedicated to progressively refining the Volumetric Probability in a Diffusion process. Extensive experiments are conducted on scene perception tasks including multi-view stereo (MVS) and semantic scene completion (SSC), to validate the efficacy of our method in learning reliable volumetric representations. Notably, for the SSC task, our work stands out as the first to surpass LiDAR-based methods on the SemanticKITTI dataset.
Authors: Zhenlin Xu, Yi Zhu, Tiffany Deng, Abhay Mittal, Yanbei Chen, Manchen Wang, Paolo Favaro, Joseph Tighe, Davide Modolo
This paper introduces innovative benchmarks to evaluate Vision-Language Models (VLMs) in real-world zero-shot recognition tasks, focusing on the granularity and specificity of prompting text. We propose a unique evaluation protocol using adapted ImageNet and MS-COCO datasets to assess models' consistency in recognizing concepts at varying granularity levels and their sensitivity to the specificity of language inputs. Our extensive evaluation reveals that state-of-the-art VLMs, including contrastive models like CLIP, struggle with granularity and are sensitive to text specificity, impacting their effectiveness in open-world settings. This comprehensive study, a first in evaluating VLMs from these perspectives, provides valuable insights and tools for the community, highlighting the limitations and paving the way for enhanced models with better generalization in zero-shot recognition.
Authors: Sahil Tyagi, Martin Swany
In distributed training, deep neural networks (DNNs) are launched over multiple workers concurrently and aggregate their local updates on each step in bulk-synchronous parallel (BSP) training. However, BSP does not linearly scale-out due to high communication cost of aggregation. To mitigate this overhead, alternatives like Federated Averaging (FedAvg) and Stale-Synchronous Parallel (SSP) either reduce synchronization frequency or eliminate it altogether, usually at the cost of lower final accuracy. In this paper, we present \texttt{SelSync}, a practical, low-overhead method for DNN training that dynamically chooses to incur or avoid communication at each step either by calling the aggregation op or applying local updates based on their significance. We propose various optimizations as part of \texttt{SelSync} to improve convergence in the context of \textit{semi-synchronous} training. Our system converges to the same or better accuracy than BSP while reducing training time by up to 14$\times$.
Authors: Donghao Zhou, Jialin Li, Jinpeng Li, Jiancheng Huang, Qiang Nie, Yong Liu, Bin-Bin Gao, Qiong Wang, Pheng-Ann Heng, Guangyong Chen
Large-scale well-annotated datasets are of great importance for training an effective object detector. However, obtaining accurate bounding box annotations is laborious and demanding. Unfortunately, the resultant noisy bounding boxes could cause corrupt supervision signals and thus diminish detection performance. Motivated by the observation that the real ground-truth is usually situated in the aggregation region of the proposals assigned to a noisy ground-truth, we propose DIStribution-aware CalibratiOn (DISCO) to model the spatial distribution of proposals for calibrating supervision signals. In DISCO, spatial distribution modeling is performed to statistically extract the potential locations of objects. Based on the modeled distribution, three distribution-aware techniques, i.e., distribution-aware proposal augmentation (DA-Aug), distribution-aware box refinement (DA-Ref), and distribution-aware confidence estimation (DA-Est), are developed to improve classification, localization, and interpretability, respectively. Extensive experiments on large-scale noisy image datasets (i.e., Pascal VOC and MS-COCO) demonstrate that DISCO can achieve state-of-the-art detection performance, especially at high noise levels.
Authors: Huaxin Zhang, Xiang Wang, Xiaohao Xu, Zhiwu Qing, Changxin Gao, Nong Sang
Point-supervised Temporal Action Localization (PSTAL) is an emerging research direction for label-efficient learning. However, current methods mainly focus on optimizing the network either at the snippet-level or the instance-level, neglecting the inherent reliability of point annotations at both levels. In this paper, we propose a Hierarchical Reliability Propagation (HR-Pro) framework, which consists of two reliability-aware stages: Snippet-level Discrimination Learning and Instance-level Completeness Learning, both stages explore the efficient propagation of high-confidence cues in point annotations. For snippet-level learning, we introduce an online-updated memory to store reliable snippet prototypes for each class. We then employ a Reliability-aware Attention Block to capture both intra-video and inter-video dependencies of snippets, resulting in more discriminative and robust snippet representation. For instance-level learning, we propose a point-based proposal generation approach as a means of connecting snippets and instances, which produces high-confidence proposals for further optimization at the instance level. Through multi-level reliability-aware learning, we obtain more reliable confidence scores and more accurate temporal boundaries of predicted proposals. Our HR-Pro achieves state-of-the-art performance on multiple challenging benchmarks, including an impressive average mAP of 60.3% on THUMOS14. Notably, our HR-Pro largely surpasses all previous point-supervised methods, and even outperforms several competitive fully supervised methods. Code will be available at https://github.com/pipixin321/HR-Pro.
Authors: Marko Mihajlovic, Sergey Prokudin, Marc Pollefeys, Siyu Tang
Neural fields, a category of neural networks trained to represent high-frequency signals, have gained significant attention in recent years due to their impressive performance in modeling complex 3D data, such as signed distance (SDFs) or radiance fields (NeRFs), via a single multi-layer perceptron (MLP). However, despite the power and simplicity of representing signals with an MLP, these methods still face challenges when modeling large and complex temporal signals due to the limited capacity of MLPs. In this paper, we propose an effective approach to address this limitation by incorporating temporal residual layers into neural fields, dubbed ResFields. It is a novel class of networks specifically designed to effectively represent complex temporal signals. We conduct a comprehensive analysis of the properties of ResFields and propose a matrix factorization technique to reduce the number of trainable parameters and enhance generalization capabilities. Importantly, our formulation seamlessly integrates with existing MLP-based neural fields and consistently improves results across various challenging tasks: 2D video approximation, dynamic shape modeling via temporal SDFs, and dynamic NeRF reconstruction. Lastly, we demonstrate the practical utility of ResFields by showcasing its effectiveness in capturing dynamic 3D scenes from sparse RGBD cameras of a lightweight capture system.
Authors: Jingwen Fu, Tao Yang, Yuwang Wang, Yan Lu, Nanning Zheng
In-context learning, i.e., learning from context examples, is an impressive ability of Transformer. Training Transformers to possess this in-context learning skill is computationally intensive due to the occurrence of learning plateaus, which are periods within the training process where there is minimal or no enhancement in the model's in-context learning capability. To study the mechanism behind the learning plateaus, we conceptually seperate a component within the model's internal representation that is exclusively affected by the model's weights. We call this the "weights component", and the remainder is identified as the "context component". By conducting meticulous and controlled experiments on synthetic tasks, we note that the persistence of learning plateaus correlates with compromised functionality of the weights component. Recognizing the impaired performance of the weights component as a fundamental behavior drives learning plateaus, we have developed three strategies to expedite the learning of Transformers. The effectiveness of these strategies is further confirmed in natural language processing tasks. In conclusion, our research demonstrates the feasibility of cultivating a powerful in-context learning ability within AI systems in an eco-friendly manner.
Authors: Aravind R. Krishnan, Kaiwen Xu, Thomas Li, Chenyu Gao, Lucas W. Remedios, Praitayini Kanakaraj, Ho Hin Lee, Shunxing Bao, Kim L. Sandler, Fabien Maldonado, Ivana Isgum, Bennett A. Landman
The reconstruction kernel in computed tomography (CT) generation determines the texture of the image. Consistency in reconstruction kernels is important as the underlying CT texture can impact measurements during quantitative image analysis. Harmonization (i.e., kernel conversion) minimizes differences in measurements due to inconsistent reconstruction kernels. Existing methods investigate harmonization of CT scans in single or multiple manufacturers. However, these methods require paired scans of hard and soft reconstruction kernels that are spatially and anatomically aligned. Additionally, a large number of models need to be trained across different kernel pairs within manufacturers. In this study, we adopt an unpaired image translation approach to investigate harmonization between and across reconstruction kernels from different manufacturers by constructing a multipath cycle generative adversarial network (GAN). We use hard and soft reconstruction kernels from the Siemens and GE vendors from the National Lung Screening Trial dataset. We use 50 scans from each reconstruction kernel and train a multipath cycle GAN. To evaluate the effect of harmonization on the reconstruction kernels, we harmonize 50 scans each from Siemens hard kernel, GE soft kernel and GE hard kernel to a reference Siemens soft kernel (B30f) and evaluate percent emphysema. We fit a linear model by considering the age, smoking status, sex and vendor and perform an analysis of variance (ANOVA) on the emphysema scores. Our approach minimizes differences in emphysema measurement and highlights the impact of age, sex, smoking status and vendor on emphysema quantification.
Authors: Florian Gunsilius, David Van Dijcke
Discontinuities in regression functions can reveal important insights. In many contexts, like geographic settings, such discontinuities are multivariate and unknown a priori. We propose a non-parametric regression method that estimates the location and size of discontinuities by segmenting the regression surface. This estimator is based on a convex relaxation of the Mumford-Shah functional, for which we establish identification and convergence. We use it to show that an internet shutdown in India resulted in a reduction of economic activity by 25--35%, greatly surpassing previous estimates and shedding new light on the true cost of such shutdowns for digital economies globally.
Authors: Etienne Meunier, Patrick Bouthemy
Human beings have the ability to continuously analyze a video and immediately extract the main motion components. Motion segmentation methods based on deep learning often proceed frame by frame. We want to go beyond this paradigm, and perform the motion segmentation in series of flow fields of any length, up to the complete video sequence. It will be a prominent added value for downstream computer vision tasks, and could provide a pretext criterion for unsupervised video representation learning. In this perspective, we propose a novel long-term spatio-temporal model operating in a totally unsupervised way. It takes as input the volume of consecutive optical flow (OF) fields, and delivers a volume of segments of coherent motion over the video. More specifically, we have designed a transformer-based network, where we leverage a mathematically well-founded framework, the Evidence Lower Bound (ELBO), to infer the loss function. The loss function combines a flow reconstruction term involving spatio-temporal parametric motion models combining, in a novel way, polynomial (quadratic) motion models for the $(x,y)$-spatial dimensions and B-splines for the time dimension of the video sequence, and a regularization term enforcing temporal consistency on the masks. We report experiments on four VOS benchmarks with convincing quantitative results. We also highlight through visual results the key contributions on temporal consistency brought by our method.
Authors: Shuai Yang, Yukang Chen, Luozhou Wang, Shu Liu, Yingcong Chen
Denoising Diffusion Probabilistic Models (DDPMs) have garnered popularity for data generation across various domains. However, a significant bottleneck is the necessity for whole-network computation during every step of the generative process, leading to high computational overheads. This paper presents a novel framework, Denoising Diffusion Step-aware Models (DDSM), to address this challenge. Unlike conventional approaches, DDSM employs a spectrum of neural networks whose sizes are adapted according to the importance of each generative step, as determined through evolutionary search. This step-wise network variation effectively circumvents redundant computational efforts, particularly in less critical steps, thereby enhancing the efficiency of the diffusion model. Furthermore, the step-aware design can be seamlessly integrated with other efficiency-geared diffusion models such as DDIMs and latent diffusion, thus broadening the scope of computational savings. Empirical evaluations demonstrate that DDSM achieves computational savings of 49% for CIFAR-10, 61% for CelebA-HQ, 59% for LSUN-bedroom, 71% for AFHQ, and 76% for ImageNet, all without compromising the generation quality.
Authors: Arief Purnama Muharram, Hollyana Puteri Haryono, Abassi Haji Juma, Ira Puspasari, Nugraha Priya Utama
Reading and interpreting chest X-ray images is one of the most radiologist's routines. However, it still can be challenging, even for the most experienced ones. Therefore, we proposed a multi-model deep learning-based automated chest X-ray report generator system designed to assist radiologists in their work. The basic idea of the proposed system is by utilizing multi binary-classification models for detecting multi abnormalities, with each model responsible for detecting one abnormality, in a single image. In this study, we limited the radiology abnormalities detection to only cardiomegaly, lung effusion, and consolidation. The system generates a radiology report by performing the following three steps: image pre-processing, utilizing deep learning models to detect abnormalities, and producing a report. The aim of the image pre-processing step is to standardize the input by scaling it to 128x128 pixels and slicing it into three segments, which covers the upper, lower, and middle parts of the lung. After pre-processing, each corresponding model classifies the image, resulting in a 0 (zero) for no abnormality detected and a 1 (one) for the presence of an abnormality. The prediction outputs of each model are then concatenated to form a 'result code'. The 'result code' is used to construct a report by selecting the appropriate pre-determined sentence for each detected abnormality in the report generation step. The proposed system is expected to reduce the workload of radiologists and increase the accuracy of chest X-ray diagnosis.
Authors: Shahin Doroudian
Virtual Reality (VR) and Augmented Reality (AR) tools have been applied in all engineering fields in order to avoid the use of physical prototypes, to train in high-risk situations, and to interpret real or simulated results. In order to complete a shared task or assign tasks to the agents in such immersive environments, collaboration or Shared Cooperative Activities are a necessity. Collaboration in immersive environments is an emerging field of research that aims to study and enhance the ways in which people interact and work together in Virtual and Augmented Reality settings. Collaboration in immersive environments is a complex process that involves different factors such as communication, coordination, and social presence. This paper provides an overview of the current state of research on collaboration in immersive environments. It discusses the different types of immersive environments, including VR and AR, and the different forms of collaboration that can occur in these environments. The paper also highlights the challenges and limitations of collaboration in immersive environments, such as the lack of physical cues, cost and usability and the need for further research in this area. Overall, collaboration in immersive environments is a promising field with a wide range of potential applications, from education to industry, and it can benefit both individuals and groups by enhancing their ability to work together effectively.
Authors: Miaojie Feng, Junda Cheng, Hao Jia, Longliang Liu, Gangwei Xu, Qingyong Hu, Xin Yang
Stereo matching is a fundamental task in scene comprehension. In recent years, the method based on iterative optimization has shown promise in stereo matching. However, the current iteration framework employs a single-peak lookup, which struggles to handle the multi-peak problem effectively. Additionally, the fixed search range used during the iteration process limits the final convergence effects. To address these issues, we present a novel iterative optimization architecture called MC-Stereo. This architecture mitigates the multi-peak distribution problem in matching through the multi-peak lookup strategy, and integrates the coarse-to-fine concept into the iterative framework via the cascade search range. Furthermore, given that feature representation learning is crucial for successful learn-based stereo matching, we introduce a pre-trained network to serve as the feature extractor, enhancing the front end of the stereo matching pipeline. Based on these improvements, MC-Stereo ranks first among all publicly available methods on the KITTI-2012 and KITTI-2015 benchmarks, and also achieves state-of-the-art performance on ETH3D. Code is available at https://github.com/MiaoJieF/MC-Stereo.
Authors: Jiuqing Dong, Yongbin Gao, Heng Zhou, Jun Cen, Yifan Yao, Sook Yoon, Park Dong Sun
Out-of-distribution (OOD) detection is critical for ensuring the reliability of open-world intelligent systems. Despite the notable advancements in existing OOD detection methodologies, our study identifies a significant performance drop under the scarcity of training samples. In this context, we introduce a novel few-shot OOD detection benchmark, carefully constructed to address this gap. Our empirical analysis reveals the superiority of ParameterEfficient Fine-Tuning (PEFT) strategies, such as visual prompt tuning and visual adapter tuning, over conventional techniques, including fully fine-tuning and linear probing tuning in the few-shot OOD detection task. Recognizing some crucial information from the pre-trained model, which is pivotal for OOD detection, may be lost during the fine-tuning process, we propose a method termed DomainSpecific and General Knowledge Fusion (DSGF). This approach is designed to be compatible with diverse fine-tuning frameworks. Our experiments show that the integration of DSGF significantly enhances the few-shot OOD detection capabilities across various methods and fine-tuning methodologies, including fully fine-tuning, visual adapter tuning, and visual prompt tuning. The code will be released.
Authors: Guanzhou Ji, Azadeh O. Sawyer, Srinivasa G. Narasimhan
We propose a novel inverse rendering method that enables the transformation of existing indoor panoramas with new indoor furniture layouts under natural illumination. To achieve this, we captured indoor HDR panoramas along with real-time outdoor hemispherical HDR photographs. Indoor and outdoor HDR images were linearly calibrated with measured absolute luminance values for accurate scene relighting. Our method consists of three key components: (1) panoramic furniture detection and removal, (2) automatic floor layout design, and (3) global rendering with scene geometry, new furniture objects, and a real-time outdoor photograph. We demonstrate the effectiveness of our workflow in rendering indoor scenes under different outdoor illumination conditions. Additionally, we contribute a new calibrated HDR (Cali-HDR) dataset that consists of 137 calibrated indoor panoramas and their associated outdoor photographs.
Authors: Sahil Tyagi, Martin Swany
Gradient compression alleviates expensive communication in distributed deep learning by sending fewer values and its corresponding indices, typically via Allgather (AG). Training with high compression ratio (CR) achieves high accuracy like DenseSGD, but has lower parallel scaling due to high communication cost (i.e., parallel efficiency). Using lower CRs improves parallel efficiency by lowering synchronization cost, but degrades model accuracy as well (statistical efficiency). Further, speedup attained with different models and CRs also varies with network latency, effective bandwidth and collective op used for aggregation. In many cases, collectives like Allreduce (AR) have lower cost than AG to exchange the same amount of data. In this paper, we propose an AR-compatible Topk compressor that is bandwidth-optimal and thus performs better than AG in certain network configurations. We develop a flexible communication strategy that switches between AG and AR based on which collective is optimal in the current settings, and model the pareto-relationship between parallel and statistical efficiency as a multi-objective optimization (MOO) problem to dynamically adjust CR and accelerate training while still converging to high accuracy.
Authors: Joonwoo Kwon, Sooyoung Kim, Yuewei Lin, Shinjae Yoo, Jiook Cha
Neural style transfer (NST) has evolved significantly in recent years. Yet, despite its rapid progress and advancement, existing NST methods either struggle to transfer aesthetic information from a style effectively or suffer from high computational costs and inefficiencies in feature disentanglement due to using pre-trained models. This work proposes a lightweight but effective model, AesFA -- Aesthetic Feature-Aware NST. The primary idea is to decompose the image via its frequencies to better disentangle aesthetic styles from the reference image while training the entire model in an end-to-end manner to exclude pre-trained models at inference completely. To improve the network's ability to extract more distinct representations and further enhance the stylization quality, this work introduces a new aesthetic feature: contrastive loss. Extensive experiments and ablations show the approach not only outperforms recent NST methods in terms of stylization quality, but it also achieves faster inference. Codes are available at https://github.com/Sooyyoungg/AesFA.
Authors: Zixian Su, Jingwei Guo, Kai Yao, Xi Yang, Qiufeng Wang, Kaizhu Huang
While recent test-time adaptations exhibit efficacy by adjusting batch normalization to narrow domain disparities, their effectiveness diminishes with realistic mini-batches due to inaccurate target estimation. As previous attempts merely introduce source statistics to mitigate this issue, the fundamental problem of inaccurate target estimation still persists, leaving the intrinsic test-time domain shifts unresolved. This paper delves into the problem of mini-batch degradation. By unraveling batch normalization, we discover that the inexact target statistics largely stem from the substantially reduced class diversity in batch. Drawing upon this insight, we introduce a straightforward tool, Test-time Exponential Moving Average (TEMA), to bridge the class diversity gap between training and testing batches. Importantly, our TEMA adaptively extends the scope of typical methods beyond the current batch to incorporate a diverse set of class information, which in turn boosts an accurate target estimation. Built upon this foundation, we further design a novel layer-wise rectification strategy to consistently promote test-time performance. Our proposed method enjoys a unique advantage as it requires neither training nor tuning parameters, offering a truly hassle-free solution. It significantly enhances model robustness against shifted domains and maintains resilience in diverse real-world scenarios with various batch sizes, achieving state-of-the-art performance on several major benchmarks. Code is available at \url{https://github.com/kiwi12138/RealisticTTA}.
Authors: Sreetama Das, Stefano Martina, Filippo Caruso
Geometric deep learning refers to the scenario in which the symmetries of a dataset are used to constrain the parameter space of a neural network and thus, improve their trainability and generalization. Recently this idea has been incorporated into the field of quantum machine learning, which has given rise to equivariant quantum neural networks (EQNNs). In this work, we investigate the role of classical-to-quantum embedding on the performance of equivariant quantum convolutional neural networks (EQCNNs) for the classification of images. We discuss the connection between the data embedding method and the resulting representation of a symmetry group and analyze how changing representation affects the expressibility of an EQCNN. We numerically compare the classification accuracy of EQCNNs with three different basis-permuted amplitude embeddings to the one obtained from a non-equivariant quantum convolutional neural network (QCNN). Our results show a clear dependence of classification accuracy on the underlying embedding, especially for initial training iterations. The improvement in classification accuracy of EQCNN over non-equivariant QCNN may be present or absent depending on the particular embedding and dataset used. It is expected that the results of this work can be useful to the community for a better understanding of the importance of data embedding choice in the context of geometric quantum machine learning.
Authors: Linger Deng, Mingxin Huang, Xudong Xie, Yuliang Liu, Lianwen Jin, Xiang Bai
The advancement of text shape representations towards compactness has enhanced text detection and spotting performance, but at a high annotation cost. Current models use single-point annotations to reduce costs, yet they lack sufficient localization information for downstream applications. To overcome this limitation, we introduce Point2Polygon, which can efficiently transform single-points into compact polygons. Our method uses a coarse-to-fine process, starting with creating and selecting anchor points based on recognition confidence, then vertically and horizontally refining the polygon using recognition information to optimize its shape. We demonstrate the accuracy of the generated polygons through extensive experiments: 1) By creating polygons from ground truth points, we achieved an accuracy of 82.0% on ICDAR 2015; 2) In training detectors with polygons generated by our method, we attained 86% of the accuracy relative to training with ground truth (GT); 3) Additionally, the proposed Point2Polygon can be seamlessly integrated to empower single-point spotters to generate polygons. This integration led to an impressive 82.5% accuracy for the generated polygons. It is worth mentioning that our method relies solely on synthetic recognition information, eliminating the need for any manual annotation beyond single points.
Authors: Zhengzhuo Xu, Sinan Du, Yiyan Qi, Chengjin Xu, Chun Yuan, Jian Guo
Multimodal Large Language Models (MLLMs) demonstrate impressive image understanding and generating capabilities. However, existing benchmarks employ limited charts that deviate from real-world scenarios, posing challenges in accurately assessing the chart comprehension of MLLMs. To overcome this constraint, we propose ChartBench, an exhaustive chart benchmark specifically designed to evaluate MLLMs' chart comprehension and data reliability through complex visual reasoning. ChartBench encompasses a wide spectrum, including 42 categories, 2.1K charts, and 16.8K question-answer pairs. Diverging from previous benchmarks, ChartBench avoids employing data point annotation charts or metadata prompts directly. Instead, it compels MLLMs to derive values akin to human understanding by leveraging inherent chart elements such as color, legends, or coordinate systems. Additionally, we propose an enhanced evaluation metric, Acc+, which facilitates the evaluation of MLLMs without needing labor-intensive manual efforts or costly evaluations based on GPT. Our extensive experimental evaluation involves 12 widely-used open-sourced and 2 proprietary MLLMs, revealing the limitations of MLLMs in interpreting charts and providing valuable insights to encourage closer scrutiny of this aspect.
Authors: Huan Liu, Julia Qi, Zhenhao Li, Mohammad Hassanpour, Yang Wang, Konstantinos Plataniotis, Yuanhao Yu
Despite the recent remarkable achievement in gaze estimation, efficient and accurate personalization of gaze estimation without labels is a practical problem but rarely touched on in the literature. To achieve efficient personalization, we take inspiration from the recent advances in Natural Language Processing (NLP) by updating a negligible number of parameters, "prompts", at the test time. Specifically, the prompt is additionally attached without perturbing original network and can contain less than 1% of a ResNet-18's parameters. Our experiments show high efficiency of the prompt tuning approach. The proposed one can be 10 times faster in terms of adaptation speed than the methods compared. However, it is non-trivial to update the prompt for personalized gaze estimation without labels. At the test time, it is essential to ensure that the minimizing of particular unsupervised loss leads to the goals of minimizing gaze estimation error. To address this difficulty, we propose to meta-learn the prompt to ensure that its updates align with the goal. Our experiments show that the meta-learned prompt can be effectively adapted even with a simple symmetry loss. In addition, we experiment on four cross-dataset validations to show the remarkable advantages of the proposed method.
Authors: Lucas W. Remedios, Shunxing Bao, Samuel W. Remedios, Ho Hin Lee, Leon Y. Cai, Thomas Li, Ruining Deng, Can Cui, Jia Li, Qi Liu, Ken S. Lau, Joseph T. Roland, Mary K. Washington, Lori A. Coburn, Keith T. Wilson, Yuankai Huo, Bennett A. Landman
Understanding the way cells communicate, co-locate, and interrelate is essential to understanding human physiology. Hematoxylin and eosin (H&E) staining is ubiquitously available both for clinical studies and research. The Colon Nucleus Identification and Classification (CoNIC) Challenge has recently innovated on robust artificial intelligence labeling of six cell types on H&E stains of the colon. However, this is a very small fraction of the number of potential cell classification types. Specifically, the CoNIC Challenge is unable to classify epithelial subtypes (progenitor, endocrine, goblet), lymphocyte subtypes (B, helper T, cytotoxic T), or connective subtypes (fibroblasts, stromal). In this paper, we propose to use inter-modality learning to label previously un-labelable cell types on virtual H&E. We leveraged multiplexed immunofluorescence (MxIF) histology imaging to identify 14 subclasses of cell types. We performed style transfer to synthesize virtual H&E from MxIF and transferred the higher density labels from MxIF to these virtual H&E images. We then evaluated the efficacy of learning in this approach. We identified helper T and progenitor nuclei with positive predictive values of $0.34 \pm 0.15$ (prevalence $0.03 \pm 0.01$) and $0.47 \pm 0.1$ (prevalence $0.07 \pm 0.02$) respectively on virtual H&E. This approach represents a promising step towards automating annotation in digital pathology.
Authors: Mengtian Li, Shengxiang Yao, Zhifeng Xie, Keyu Chen
In this work, we propose a novel clothed human reconstruction method called GaussianBody, based on 3D Gaussian Splatting. Compared with the costly neural radiance based models, 3D Gaussian Splatting has recently demonstrated great performance in terms of training time and rendering quality. However, applying the static 3D Gaussian Splatting model to the dynamic human reconstruction problem is non-trivial due to complicated non-rigid deformations and rich cloth details. To address these challenges, our method considers explicit pose-guided deformation to associate dynamic Gaussians across the canonical space and the observation space, introducing a physically-based prior with regularized transformations helps mitigate ambiguity between the two spaces. During the training process, we further propose a pose refinement strategy to update the pose regression for compensating the inaccurate initial estimation and a split-with-scale mechanism to enhance the density of regressed point clouds. The experiments validate that our method can achieve state-of-the-art photorealistic novel-view rendering results with high-quality details for dynamic clothed human bodies, along with explicit geometry reconstruction.
Authors: Haibo Wang, Chenghang Lai, Yixuan Sun, Weifeng Ge
Video Question Answering (VideoQA) aims to answer natural language questions based on the information observed in videos. Despite the recent success of Large Multimodal Models (LMMs) in image-language understanding and reasoning, they deal with VideoQA insufficiently by simply taking uniformly sampled frames as visual inputs, which ignores question-relevant visual clues. Moreover, there are no human annotations for question-critical timestamps in existing VideoQA datasets. In light of this, we propose a novel weakly supervised framework to enforce the LMMs to reason out the answers with question-critical moments as visual inputs. Specifically, we fuse the question and answer pairs as event descriptions to find multiple keyframes as target moments, which will be pseudo-labels. With these pseudo-labels as additionally weak supervision, we devise a lightweight Gaussian-based Contrastive Grounding (GCG) module. GCG learns multiple Gaussian functions to characterize the temporal structure of the video, and sample question-critical frames as positive moments to be the visual inputs of LMMs. Extensive experiments on several VideoQA benchmarks verify the effectiveness of our framework, and we achieve substantial improvements compared to previous state-of-the-art methods.
Authors: Zhiyuan Wu, Yi Feng, Chuang-Wei Liu, Fisher Yu, Qijun Chen, Rui Fan
Semantic segmentation and stereo matching are two essential components of 3D environmental perception systems for autonomous driving. Nevertheless, conventional approaches often address these two problems independently, employing separate models for each task. This approach poses practical limitations in real-world scenarios, particularly when computational resources are scarce or real-time performance is imperative. Hence, in this article, we introduce S$^3$M-Net, a novel joint learning framework developed to perform semantic segmentation and stereo matching simultaneously. Specifically, S$^3$M-Net shares the features extracted from RGB images between both tasks, resulting in an improved overall scene understanding capability. This feature sharing process is realized using a feature fusion adaption (FFA) module, which effectively transforms the shared features into semantic space and subsequently fuses them with the encoded disparity features. The entire joint learning framework is trained by minimizing a novel semantic consistency-guided (SCG) loss, which places emphasis on the structural consistency in both tasks. Extensive experimental results conducted on the vKITTI2 and KITTI datasets demonstrate the effectiveness of our proposed joint learning framework and its superior performance compared to other state-of-the-art single-task networks. Our project webpage is accessible at mias.group/S3M-Net.
Authors: Shengze Li, Jianjian Cao, Peng Ye, Yuhan Ding, Chongjun Tu, Tao Chen
Recently, foundational models such as CLIP and SAM have shown promising performance for the task of Zero-Shot Anomaly Segmentation (ZSAS). However, either CLIP-based or SAM-based ZSAS methods still suffer from non-negligible key drawbacks: 1) CLIP primarily focuses on global feature alignment across different inputs, leading to imprecise segmentation of local anomalous parts; 2) SAM tends to generate numerous redundant masks without proper prompt constraints, resulting in complex post-processing requirements. In this work, we innovatively propose a CLIP and SAM collaboration framework called ClipSAM for ZSAS. The insight behind ClipSAM is to employ CLIP's semantic understanding capability for anomaly localization and rough segmentation, which is further used as the prompt constraints for SAM to refine the anomaly segmentation results. In details, we introduce a crucial Unified Multi-scale Cross-modal Interaction (UMCI) module for interacting language with visual features at multiple scales of CLIP to reason anomaly positions. Then, we design a novel Multi-level Mask Refinement (MMR) module, which utilizes the positional information as multi-level prompts for SAM to acquire hierarchical levels of masks and merges them. Extensive experiments validate the effectiveness of our approach, achieving the optimal segmentation performance on the MVTec-AD and VisA datasets.
Authors: Jibinraj Antony, Vinit Hegiste, Ali Nazeri, Hooman Tavakoli, Snehal Walunj, Christiane Plociennik, Martin Ruskowski
Object Detection (OD) has proven to be a significant computer vision method in extracting localized class information and has multiple applications in the industry. Although many of the state-of-the-art (SOTA) OD models perform well on medium and large sized objects, they seem to under perform on small objects. In most of the industrial use cases, it is difficult to collect and annotate data for small objects, as it is time-consuming and prone to human errors. Additionally, those datasets are likely to be unbalanced and often result in an inefficient model convergence. To tackle this challenge, this study presents a novel approach that injects additional data points to improve the performance of the OD models. Using synthetic data generation, the difficulties in data collection and annotations for small object data points can be minimized and to create a dataset with balanced distribution. This paper discusses the effects of a simple proportional class-balancing technique, to enable better anchor matching of the OD models. A comparison was carried out on the performances of the SOTA OD models: YOLOv5, YOLOv7 and SSD, for combinations of real and synthetic datasets within an industrial use case.
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: Dezhao Luo, Shaogang Gong, Jiabo Huang, 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: Xuanchao Ma, Yanlin Jiang, Hongyan Liu, Chengxu Zhou, Ke Gu
Recent years have witnessed a broader range of applications of image processing technologies in multiple industrial processes, such as smoke detection, security monitoring, and workpiece inspection. Different kinds of distortion types and levels must be introduced into an image during the processes of acquisition, compression, transmission, storage, and display, which might heavily degrade the image quality and thus strongly reduce the final display effect and clarity. To verify the reliability of existing image quality assessment methods, we establish a new industrial process image database (IPID), which contains 3000 distorted images generated by applying different levels of distortion types to each of the 50 source images. We conduct the subjective test on the aforementioned 3000 images to collect their subjective quality ratings in a well-suited laboratory environment. Finally, we perform comparison experiments on IPID database to investigate the performance of some objective image quality assessment algorithms. The experimental results show that the state-of-the-art image quality assessment methods have difficulty in predicting the quality of images that contain multiple distortion types.
Authors: Haitao Gan, Lingchao Fu, Ran Zhou, Weiyan Gan, Furong Wang, Xiaoyan Wu, Zhi Yang, Zhongwei Huang
The classification of carotid artery ultrasound images is a crucial means for diagnosing carotid plaques, holding significant clinical relevance for predicting the risk of stroke. Recent research suggests that utilizing plaque segmentation as an auxiliary task for classification can enhance performance by leveraging the correlation between segmentation and classification tasks. However, this approach relies on obtaining a substantial amount of challenging-to-acquire segmentation annotations. This paper proposes a novel weakly supervised auxiliary task learning network model (WAL-Net) to explore the interdependence between carotid plaque classification and segmentation tasks. The plaque classification task is primary task, while the plaque segmentation task serves as an auxiliary task, providing valuable information to enhance the performance of the primary task. Weakly supervised learning is adopted in the auxiliary task to completely break away from the dependence on segmentation annotations. Experiments and evaluations are conducted on a dataset comprising 1270 carotid plaque ultrasound images from Wuhan University Zhongnan Hospital. Results indicate that the proposed method achieved an approximately 1.3% improvement in carotid plaque classification accuracy compared to the baseline network. Specifically, the accuracy of mixed-echoic plaques classification increased by approximately 3.3%, demonstrating the effectiveness of our approach.
Authors: Chulhong Min, Juheon Yi, Utku Gunay Acer, Fahim Kawsar
Overlapping cameras offer exciting opportunities to view a scene from different angles, allowing for more advanced, comprehensive and robust analysis. However, existing visual analytics systems for multi-camera streams are mostly limited to (i) per-camera processing and aggregation and (ii) workload-agnostic centralized processing architectures. In this paper, we present Argus, a distributed video analytics system with cross-camera collaboration on smart cameras. We identify multi-camera, multi-target tracking as the primary task of multi-camera video analytics and develop a novel technique that avoids redundant, processing-heavy identification tasks by leveraging object-wise spatio-temporal association in the overlapping fields of view across multiple cameras. We further develop a set of techniques to perform these operations across distributed cameras without cloud support at low latency by (i) dynamically ordering the camera and object inspection sequence and (ii) flexibly distributing the workload across smart cameras, taking into account network transmission and heterogeneous computational capacities. Evaluation of three real-world overlapping camera datasets with two Nvidia Jetson devices shows that Argus reduces the number of object identifications and end-to-end latency by up to 7.13x and 2.19x (4.86x and 1.60x compared to the state-of-the-art), while achieving comparable tracking quality.
Authors: Minglin Chen, Weihao Yuan, Yukun Wang, Zhe Sheng, Yisheng He, Zilong Dong, Liefeng Bo, Yulan Guo
Recently, text-to-3D approaches have achieved high-fidelity 3D content generation using text description. However, the generated objects are stochastic and lack fine-grained control. Sketches provide a cheap approach to introduce such fine-grained control. Nevertheless, it is challenging to achieve flexible control from these sketches due to their abstraction and ambiguity. In this paper, we present a multi-view sketch-guided text-to-3D generation framework (namely, Sketch2NeRF) to add sketch control to 3D generation. Specifically, our method leverages pretrained 2D diffusion models (e.g., Stable Diffusion and ControlNet) to supervise the optimization of a 3D scene represented by a neural radiance field (NeRF). We propose a novel synchronized generation and reconstruction method to effectively optimize the NeRF. In the experiments, we collected two kinds of multi-view sketch datasets to evaluate the proposed method. We demonstrate that our method can synthesize 3D consistent contents with fine-grained sketch control while being high-fidelity to text prompts. Extensive results show that our method achieves state-of-the-art performance in terms of sketch similarity and text alignment.
Authors: Haoyu Xiong, Russell Mendonca, Kenneth Shaw, Deepak Pathak
Deploying robots in open-ended unstructured environments such as homes has been a long-standing research problem. However, robots are often studied only in closed-off lab settings, and prior mobile manipulation work is restricted to pick-move-place, which is arguably just the tip of the iceberg in this area. In this paper, we introduce Open-World Mobile Manipulation System, a full-stack approach to tackle realistic articulated object operation, e.g. real-world doors, cabinets, drawers, and refrigerators in open-ended unstructured environments. The robot utilizes an adaptive learning framework to initially learns from a small set of data through behavior cloning, followed by learning from online practice on novel objects that fall outside the training distribution. We also develop a low-cost mobile manipulation hardware platform capable of safe and autonomous online adaptation in unstructured environments with a cost of around 20,000 USD. In our experiments we utilize 20 articulate objects across 4 buildings in the CMU campus. With less than an hour of online learning for each object, the system is able to increase success rate from 50% of BC pre-training to 95% using online adaptation. Video results at https://open-world-mobilemanip.github.io/
Authors: Chaochao Lu, Chen Qian, Guodong Zheng, Hongxing Fan, Hongzhi Gao, Jie Zhang, Jing Shao, Jingyi Deng, Jinlan Fu, Kexin Huang, Kunchang Li, Lijun Li, Limin Wang, Lu Sheng, Meiqi Chen, Ming Zhang, Qibing Ren, Sirui Chen, Tao Gui, Wanli Ouyang, Yali Wang, Yan Teng, Yaru Wang, Yi Wang, Yinan He, Yingchun Wang, Yixu Wang, Yongting Zhang, Yu Qiao, Yujiong Shen, Yurong Mou, Yuxi Chen, Zaibin Zhang, Zhelun Shi, Zhenfei Yin, Zhipin Wang
Multi-modal Large Language Models (MLLMs) have shown impressive abilities in generating reasonable responses with respect to multi-modal contents. However, there is still a wide gap between the performance of recent MLLM-based applications and the expectation of the broad public, even though the most powerful OpenAI's GPT-4 and Google's Gemini have been deployed. This paper strives to enhance understanding of the gap through the lens of a qualitative study on the generalizability, trustworthiness, and causal reasoning capabilities of recent proprietary and open-source MLLMs across four modalities: ie, text, code, image, and video, ultimately aiming to improve the transparency of MLLMs. We believe these properties are several representative factors that define the reliability of MLLMs, in supporting various downstream applications. To be specific, we evaluate the closed-source GPT-4 and Gemini and 6 open-source LLMs and MLLMs. Overall we evaluate 230 manually designed cases, where the qualitative results are then summarized into 12 scores (ie, 4 modalities times 3 properties). In total, we uncover 14 empirical findings that are useful to understand the capabilities and limitations of both proprietary and open-source MLLMs, towards more reliable downstream multi-modal applications.