Authors: Nafisa Labiba Ishrat Huda, Angona Biswas, MD Abdullah Al Nasim, Md. Fahim Rahman, Shoaib Ahmed
Invariant scattering transform introduces new area of research that merges the signal processing with deep learning for computer vision. Nowadays, Deep Learning algorithms are able to solve a variety of problems in medical sector. Medical images are used to detect diseases brain cancer or tumor, Alzheimer's disease, breast cancer, Parkinson's disease and many others. During pandemic back in 2020, machine learning and deep learning has played a critical role to detect COVID-19 which included mutation analysis, prediction, diagnosis and decision making. Medical images like X-ray, MRI known as magnetic resonance imaging, CT scans are used for detecting diseases. There is another method in deep learning for medical imaging which is scattering transform. It builds useful signal representation for image classification. It is a wavelet technique; which is impactful for medical image classification problems. This research article discusses scattering transform as the efficient system for medical image analysis where it's figured by scattering the signal information implemented in a deep convolutional network. A step by step case study is manifested at this research work.
Authors: Subin Kim, Kyungmin Lee, June Suk Choi, Jongheon Jeong, Kihyuk Sohn, Jinwoo Shin
Generative priors of large-scale text-to-image diffusion models enable a wide range of new generation and editing applications on diverse visual modalities. However, when adapting these priors to complex visual modalities, often represented as multiple images (e.g., video), achieving consistency across a set of images is challenging. In this paper, we address this challenge with a novel method, Collaborative Score Distillation (CSD). CSD is based on the Stein Variational Gradient Descent (SVGD). Specifically, we propose to consider multiple samples as "particles" in the SVGD update and combine their score functions to distill generative priors over a set of images synchronously. Thus, CSD facilitates seamless integration of information across 2D images, leading to a consistent visual synthesis across multiple samples. We show the effectiveness of CSD in a variety of tasks, encompassing the visual editing of panorama images, videos, and 3D scenes. Our results underline the competency of CSD as a versatile method for enhancing inter-sample consistency, thereby broadening the applicability of text-to-image diffusion models.
Authors: Mingze Wang, Huixin Sun, Jun Shi, Xuhui Liu, Baochang Zhang, Xianbin Cao
Real-time object detection plays a vital role in various computer vision applications. However, deploying real-time object detectors on resource-constrained platforms poses challenges due to high computational and memory requirements. This paper describes a low-bit quantization method to build a highly efficient one-stage detector, dubbed as Q-YOLO, which can effectively address the performance degradation problem caused by activation distribution imbalance in traditional quantized YOLO models. Q-YOLO introduces a fully end-to-end Post-Training Quantization (PTQ) pipeline with a well-designed Unilateral Histogram-based (UH) activation quantization scheme, which determines the maximum truncation values through histogram analysis by minimizing the Mean Squared Error (MSE) quantization errors. Extensive experiments on the COCO dataset demonstrate the effectiveness of Q-YOLO, outperforming other PTQ methods while achieving a more favorable balance between accuracy and computational cost. This research contributes to advancing the efficient deployment of object detection models on resource-limited edge devices, enabling real-time detection with reduced computational and memory overhead.
Authors: Rakshith Subramanyam, T. S. Jayram, Rushil Anirudh, Jayaraman J. Thiagarajan
In this paper, we explore the potential of Vision-Language Models (VLMs), specifically CLIP, in predicting visual object relationships, which involves interpreting visual features from images into language-based relations. Current state-of-the-art methods use complex graphical models that utilize language cues and visual features to address this challenge. We hypothesize that the strong language priors in CLIP embeddings can simplify these graphical models paving for a simpler approach. We adopt the UVTransE relation prediction framework, which learns the relation as a translational embedding with subject, object, and union box embeddings from a scene. We systematically explore the design of CLIP-based subject, object, and union-box representations within the UVTransE framework and propose CREPE (CLIP Representation Enhanced Predicate Estimation). CREPE utilizes text-based representations for all three bounding boxes and introduces a novel contrastive training strategy to automatically infer the text prompt for union-box. Our approach achieves state-of-the-art performance in predicate estimation, mR@5 27.79, and mR@20 31.95 on the Visual Genome benchmark, achieving a 15.3\% gain in performance over recent state-of-the-art at mR@20. This work demonstrates CLIP's effectiveness in object relation prediction and encourages further research on VLMs in this challenging domain.
Authors: Shaokai Ye, Jessy Lauer, Mu Zhou, Alexander Mathis, Mackenzie W. Mathis
The process of quantifying and analyzing animal behavior involves translating the naturally occurring descriptive language of their actions into machine-readable code. Yet, codifying behavior analysis is often challenging without deep understanding of animal behavior and technical machine learning knowledge. To limit this gap, we introduce AmadeusGPT: a natural language interface that turns natural language descriptions of behaviors into machine-executable code. Large-language models (LLMs) such as GPT3.5 and GPT4 allow for interactive language-based queries that are potentially well suited for making interactive behavior analysis. However, the comprehension capability of these LLMs is limited by the context window size, which prevents it from remembering distant conversations. To overcome the context window limitation, we implement a novel dual-memory mechanism to allow communication between short-term and long-term memory using symbols as context pointers for retrieval and saving. Concretely, users directly use language-based definitions of behavior and our augmented GPT develops code based on the core AmadeusGPT API, which contains machine learning, computer vision, spatio-temporal reasoning, and visualization modules. Users then can interactively refine results, and seamlessly add new behavioral modules as needed. We benchmark AmadeusGPT and show we can produce state-of-the-art performance on the MABE 2022 behavior challenge tasks. Note, an end-user would not need to write any code to achieve this. Thus, collectively AmadeusGPT presents a novel way to merge deep biological knowledge, large-language models, and core computer vision modules into a more naturally intelligent system. Code and demos can be found at: https://github.com/AdaptiveMotorControlLab/AmadeusGPT.
Authors: Alexander W. Bergman, Wang Yifan, Gordon Wetzstein
The ability to generate diverse 3D articulated head avatars is vital to a plethora of applications, including augmented reality, cinematography, and education. Recent work on text-guided 3D object generation has shown great promise in addressing these needs. These methods directly leverage pre-trained 2D text-to-image diffusion models to generate 3D-multi-view-consistent radiance fields of generic objects. However, due to the lack of geometry and texture priors, these methods have limited control over the generated 3D objects, making it difficult to operate inside a specific domain, e.g., human heads. In this work, we develop a new approach to text-guided 3D head avatar generation to address this limitation. Our framework directly operates on the geometry and texture of an articulable 3D morphable model (3DMM) of a head, and introduces novel optimization procedures to update the geometry and texture while keeping the 2D and 3D facial features aligned. The result is a 3D head avatar that is consistent with the text description and can be readily articulated using the deformation model of the 3DMM. We show that our diffusion-based articulated head avatars outperform state-of-the-art approaches for this task. The latter are typically based on CLIP, which is known to provide limited diversity of generation and accuracy for 3D object generation.
Authors: Gaurav Bagwe, Xiaoyong Yuan, Miao Pan, Lan Zhang
Federated continual learning (FCL) learns incremental tasks over time from confidential datasets distributed across clients. This paper focuses on rehearsal-free FCL, which has severe forgetting issues when learning new tasks due to the lack of access to historical task data. To address this issue, we propose Fed-CPrompt based on prompt learning techniques to obtain task-specific prompts in a communication-efficient way. Fed-CPrompt introduces two key components, asynchronous prompt learning, and contrastive continual loss, to handle asynchronous task arrival and heterogeneous data distributions in FCL, respectively. Extensive experiments demonstrate the effectiveness of Fed-CPrompt in achieving SOTA rehearsal-free FCL performance.
Authors: Andreas Bock, Colin J. Cotter, Robert C. Kirby
We study parameterisation-independent closed planar curve matching as a Bayesian inverse problem. The motion of the curve is modelled via a curve on the diffeomorphism group acting on the ambient space, leading to a large deformation diffeomorphic metric mapping (LDDMM) functional penalising the kinetic energy of the deformation. We solve Hamilton's equations for the curve matching problem using the Wu-Xu element [S. Wu, J. Xu, Nonconforming finite element spaces for $2m^\text{th}$ order partial differential equations on $\mathbb{R}^n$ simplicial grids when $m=n+1$, Mathematics of Computation 88 (316) (2019) 531-551] which provides mesh-independent Lipschitz constants for the forward motion of the curve, and solve the inverse problem for the momentum using Bayesian inversion. Since this element is not affine-equivalent we provide a pullback theory which expedites the implementation and efficiency of the forward map. We adopt ensemble Kalman inversion using a negative Sobolev norm mismatch penalty to measure the discrepancy between the target and the ensemble mean shape. We provide several numerical examples to validate the approach.
Authors: Gabor Fodor, Marcos V. Conde
Deforestation estimation and fire detection in the Amazon forest poses a significant challenge due to the vast size of the area and the limited accessibility. However, these are crucial problems that lead to severe environmental consequences, including climate change, global warming, and biodiversity loss. To effectively address this problem, multimodal satellite imagery and remote sensing offer a promising solution for estimating deforestation and detecting wildfire in the Amazonia region. This research paper introduces a new curated dataset and a deep learning-based approach to solve these problems using convolutional neural networks (CNNs) and comprehensive data processing techniques. Our dataset includes curated images and diverse channel bands from Sentinel, Landsat, VIIRS, and MODIS satellites. We design the dataset considering different spatial and temporal resolution requirements. Our method successfully achieves high-precision deforestation estimation and burned area detection on unseen images from the region. Our code, models and dataset are open source: https://github.com/h2oai/cvpr-multiearth-deforestation-segmentation
Authors: Riccardo Parosi, Mattia Risiglione, Darwin G. Caldwell, Claudio Semini, Victor Barasuol
We propose a control pipeline for SAG (Searching, Approaching, and Grasping) of objects, based on a decoupled arm kinematic chain and impedance control, which integrates image-based visual servoing (IBVS). The kinematic decoupling allows for fast end-effector motions and recovery that leads to robust visual servoing. The whole approach and pipeline can be generalized for any mobile platform (wheeled or tracked vehicles), but is most suitable for dynamically moving quadruped manipulators thanks to their reactivity against disturbances. The compliance of the impedance controller makes the robot safer for interactions with humans and the environment. We demonstrate the performance and robustness of the proposed approach with various experiments on our 140 kg HyQReal quadruped robot equipped with a 7-DoF manipulator arm. The experiments consider dynamic locomotion, tracking under external disturbances, and fast motions of the target object.
Authors: Atul Ingle, David Maier
Single-photon cameras (SPCs) have emerged as a promising technology for high-resolution 3D imaging. A single-photon 3D camera determines the round-trip time of a laser pulse by capturing the arrival of individual photons at each camera pixel. Constructing photon-timestamp histograms is a fundamental operation for a single-photon 3D camera. However, in-pixel histogram processing is computationally expensive and requires large amount of memory per pixel. Digitizing and transferring photon timestamps to an off-sensor histogramming module is bandwidth and power hungry. Here we present an online approach for distance estimation without explicitly storing photon counts. The two key ingredients of our approach are (a) processing photon streams using race logic, which maintains photon data in the time-delay domain, and (b) constructing count-free equi-depth histograms. Equi-depth histograms are a succinct representation for ``peaky'' distributions, such as those obtained by an SPC pixel from a laser pulse reflected by a surface. Our approach uses a binner element that converges on the median (or, more generally, to another quantile) of a distribution. We cascade multiple binners to form an equi-depth histogrammer that produces multi-bin histograms. Our evaluation shows that this method can provide an order of magnitude reduction in bandwidth and power consumption while maintaining similar distance reconstruction accuracy as conventional processing methods.
Authors: Kyle Luther, H. Sebastian Seung
Inverse problems generally require a regularizer or prior for a good solution. A recent trend is to train a convolutional net to denoise images, and use this net as a prior when solving the inverse problem. Several proposals depend on a singular value decomposition of the forward operator, and several others backpropagate through the denoising net at runtime. Here we propose a simpler approach that combines the traditional gradient-based minimization of reconstruction error with denoising. Noise is also added at each step, so the iterative dynamics resembles a Langevin or diffusion process. Both the level of added noise and the size of the denoising step decay exponentially with time. We apply our method to the problem of tomographic reconstruction from electron micrographs acquired at multiple tilt angles. With empirical studies using simulated tilt views, we find parameter settings for our method that produce good results. We show that high accuracy can be achieved with as few as 50 denoising steps. We also compare with DDRM and DPS, more complex diffusion methods of the kinds mentioned above. These methods are less accurate (as measured by MSE and SSIM) for our tomography problem, even after the generation hyperparameters are optimized. Finally we extend our method to reconstruction of arbitrary-sized images and show results on 128 $\times$ 1568 pixel images
Authors: Yachuan Li, Zongmin Li, Xavier Soria P., Chaozhi Yang, Qian Xiao, Yun Bai, Hua Li, Xiangdong Wang
The significance of multi-scale features has been gradually recognized by the edge detection community. However, the fusion of multi-scale features increases the complexity of the model, which is not friendly to practical application. In this work, we propose a Compact Twice Fusion Network (CTFN) to fully integrate multi-scale features while maintaining the compactness of the model. CTFN includes two lightweight multi-scale feature fusion modules: a Semantic Enhancement Module (SEM) that can utilize the semantic information contained in coarse-scale features to guide the learning of fine-scale features, and a Pseudo Pixel-level Weighting (PPW) module that aggregate the complementary merits of multi-scale features by assigning weights to all features. Notwithstanding all this, the interference of texture noise makes the correct classification of some pixels still a challenge. For these hard samples, we propose a novel loss function, coined Dynamic Focal Loss, which reshapes the standard cross-entropy loss and dynamically adjusts the weights to correct the distribution of hard samples. We evaluate our method on three datasets, i.e., BSDS500, NYUDv2, and BIPEDv2. Compared with state-of-the-art methods, CTFN achieves competitive accuracy with less parameters and computational cost. Apart from the backbone, CTFN requires only 0.1M additional parameters, which reduces its computation cost to just 60% of other state-of-the-art methods. The codes are available at https://github.com/Li-yachuan/CTFN-pytorch-master.
Authors: Jian Zhang, Ge Yang, Miaoju Ban, Runwei Ding
Visual anomaly detection is essential and commonly used for many tasks in the field of computer vision. Recent anomaly detection datasets mainly focus on industrial automated inspection, medical image analysis and video surveillance. In order to broaden the application and research of anomaly detection in unmanned supermarkets and smart manufacturing, we introduce the supermarket goods anomaly detection (GoodsAD) dataset. It contains 6124 high-resolution images of 484 different appearance goods divided into 6 categories. Each category contains several common different types of anomalies such as deformation, surface damage and opened. Anomalies contain both texture changes and structural changes. It follows the unsupervised setting and only normal (defect-free) images are used for training. Pixel-precise ground truth regions are provided for all anomalies. Moreover, we also conduct a thorough evaluation of current state-of-the-art unsupervised anomaly detection methods. This initial benchmark indicates that some methods which perform well on the industrial anomaly detection dataset (e.g., MVTec AD), show poor performance on our dataset. This is a comprehensive, multi-object dataset for supermarket goods anomaly detection that focuses on real-world applications.
Authors: Guoyao Deng, Ke Zou, Kai Ren, Meng Wang, Xuedong Yuan, Sancong Ying, Huazhu Fu
Recently, Segmenting Anything has taken an important step towards general artificial intelligence. At the same time, its reliability and fairness have also attracted great attention, especially in the field of health care. In this study, we propose multi-box prompts triggered uncertainty estimation for SAM cues to demonstrate the reliability of segmented lesions or tissues. We estimate the distribution of SAM predictions via Monte Carlo with prior distribution parameters, which employs different prompts as formulation of test-time augmentation. Our experimental results found that multi-box prompts augmentation improve the SAM performance, and endowed each pixel with uncertainty. This provides the first paradigm for a reliable SAM.
Authors: Nikhil Verma
Cross-Modal learning tasks have picked up pace in recent times. With plethora of applications in diverse areas, generation of novel content using multiple modalities of data has remained a challenging problem. To address the same, various generative modelling techniques have been proposed for specific tasks. Novel and creative image generation is one important aspect for industrial application which could help as an arm for novel content generation. Techniques proposed previously used Generative Adversarial Network(GAN), autoregressive models and Variational Autoencoders (VAE) for accomplishing similar tasks. These approaches are limited in their capability to produce images guided by either text instructions or rough sketch images decreasing the overall performance of image generator. We used state of the art diffusion models to generate creative art by primarily leveraging text with additional support of rough sketches. Diffusion starts with a pattern of random dots and slowly converts that pattern into a design image using the guiding information fed into the model. Diffusion models have recently outperformed other generative models in image generation tasks using cross modal data as guiding information. The initial experiments for this task of novel image generation demonstrated promising qualitative results.
Authors: Guoyao Deng, Ke Zou, Meng Wang, Xuedong Yuan, Sancong Ying, Huazhu Fu
Frontotemporal Dementia (FTD) diagnosis has been successfully progress using deep learning techniques. However, current FTD identification methods suffer from two limitations. Firstly, they do not exploit the potential of multi-view functional magnetic resonance imaging (fMRI) for classifying FTD. Secondly, they do not consider the reliability of the multi-view FTD diagnosis. To address these limitations, we propose a reliable multi-view impartial decision network (MID-Net) for FTD diagnosis in fMRI. Our MID-Net provides confidence for each view and generates a reliable prediction without any conflict. To achieve this, we employ multiple expert models to extract evidence from the abundant neural network information contained in fMRI images. We then introduce the Dirichlet Distribution to characterize the expert class probability distribution from an evidence level. Additionally, a novel Impartial Decision Maker (IDer) is proposed to combine the different opinions inductively to arrive at an unbiased prediction without additional computation cost. Overall, our MID-Net dynamically integrates the decisions of different experts on FTD disease, especially when dealing with multi-view high-conflict cases. Extensive experiments on a high-quality FTD fMRI dataset demonstrate that our model outperforms previous methods and provides high uncertainty for hard-to-classify examples. We believe that our approach represents a significant step toward the deployment of reliable FTD decision-making under multi-expert conditions. We will release the codes for reproduction after acceptance.
Authors: Cong Wang, Di Kang, Yanpei Cao, Linchao Bao, Ying Shan, Song-Hai Zhang
Rendering photorealistic and dynamically moving human heads is crucial for ensuring a pleasant and immersive experience in AR/VR and video conferencing applications. However, existing methods often struggle to model challenging facial regions (e.g., mouth interior, eyes, hair/beard), resulting in unrealistic and blurry results. In this paper, we propose {\fullname} ({\name}), a method that adopts the neural point representation as well as the neural volume rendering process and discards the predefined connectivity and hard correspondence imposed by mesh-based approaches. Specifically, the neural points are strategically constrained around the surface of the target expression via a high-resolution UV displacement map, achieving increased modeling capacity and more accurate control. We introduce three technical innovations to improve the rendering and training efficiency: a patch-wise depth-guided (shading point) sampling strategy, a lightweight radiance decoding process, and a Grid-Error-Patch (GEP) ray sampling strategy during training. By design, our {\name} is better equipped to handle topologically changing regions and thin structures while also ensuring accurate expression control when animating avatars. Experiments conducted on three subjects from the Multiface dataset demonstrate the effectiveness of our designs, outperforming previous state-of-the-art methods, especially in handling challenging facial regions.
Authors: Renhao Wang, Yu Sun, Yossi Gandelsman, Xinlei Chen, Alexei A. Efros, Xiaolong Wang
Prior work has established test-time training (TTT) as a general framework to further improve a trained model at test time. Before making a prediction on each test instance, the model is trained on the same instance using a self-supervised task, such as image reconstruction with masked autoencoders. We extend TTT to the streaming setting, where multiple test instances - video frames in our case - arrive in temporal order. Our extension is online TTT: The current model is initialized from the previous model, then trained on the current frame and a small window of frames immediately before. Online TTT significantly outperforms the fixed-model baseline for four tasks, on three real-world datasets. The relative improvement is 45% and 66% for instance and panoptic segmentation. Surprisingly, online TTT also outperforms its offline variant that accesses more information, training on all frames from the entire test video regardless of temporal order. This differs from previous findings using synthetic videos. We conceptualize locality as the advantage of online over offline TTT. We analyze the role of locality with ablations and a theory based on bias-variance trade-off.
Authors: Jeongyun Kim, Myung-Hwan Jeon, Sangwoo Jung, Wooseong Yang, Minwoo Jung, Jaeho Shin, Ayoung Kim
Transparent objects are encountered frequently in our daily lives, yet recognizing them poses challenges for conventional vision sensors due to their unique material properties, not being well perceived from RGB or depth cameras. Overcoming this limitation, thermal infrared cameras have emerged as a solution, offering improved visibility and shape information for transparent objects. In this paper, we present TRansPose, the first large-scale multispectral dataset that combines stereo RGB-D, thermal infrared (TIR) images, and object poses to promote transparent object research. The dataset includes 99 transparent objects, encompassing 43 household items, 27 recyclable trashes, 29 chemical laboratory equivalents, and 12 non-transparent objects. It comprises a vast collection of 333,819 images and 4,000,056 annotations, providing instance-level segmentation masks, ground-truth poses, and completed depth information. The data was acquired using a FLIR A65 thermal infrared (TIR) camera, two Intel RealSense L515 RGB-D cameras, and a Franka Emika Panda robot manipulator. Spanning 87 sequences, TRansPose covers various challenging real-life scenarios, including objects filled with water, diverse lighting conditions, heavy clutter, non-transparent or translucent containers, objects in plastic bags, and multi-stacked objects. TRansPose dataset can be accessed from the following link: https://sites.google.com/view/transpose-dataset
Authors: Yi Liao, Yongsheng Gao, Weichuan Zhang
Decisions made by convolutional neural networks(CNN) can be understood and explained by visualizing discriminative regions on images. To this end, Class Activation Map (CAM) based methods were proposed as powerful interpretation tools, making the prediction of deep learning models more explainable, transparent, and trustworthy. However, all the CAM-based methods (e.g., CAM, Grad-CAM, and Relevance-CAM) can only be used for interpreting CNN models with fully-connected (FC) layers as a classifier. It is worth noting that many deep learning models classify images without FC layers, e.g., few-shot learning image classification, contrastive learning image classification, and image retrieval tasks. In this work, a post-hoc interpretation tool named feature activation map (FAM) is proposed, which can interpret deep learning models without FC layers as a classifier. In the proposed FAM algorithm, the channel-wise contribution weights are derived from the similarity scores between two image embeddings. The activation maps are linearly combined with the corresponding normalized contribution weights, forming the explanation map for visualization. The quantitative and qualitative experiments conducted on ten deep learning models for few-shot image classification, contrastive learning image classification and image retrieval tasks demonstrate the effectiveness of the proposed FAM algorithm.
Authors: Hui Kang, Sheng Liu, Huaxi Huang, Jun Yu, Bo Han, Dadong Wang, Tongliang Liu
In recent years, research on learning with noisy labels has focused on devising novel algorithms that can achieve robustness to noisy training labels while generalizing to clean data. These algorithms often incorporate sophisticated techniques, such as noise modeling, label correction, and co-training. In this study, we demonstrate that a simple baseline using cross-entropy loss, combined with widely used regularization strategies like learning rate decay, model weights average, and data augmentations, can outperform state-of-the-art methods. Our findings suggest that employing a combination of regularization strategies can be more effective than intricate algorithms in tackling the challenges of learning with noisy labels. While some of these regularization strategies have been utilized in previous noisy label learning research, their full potential has not been thoroughly explored. Our results encourage a reevaluation of benchmarks for learning with noisy labels and prompt reconsideration of the role of specialized learning algorithms designed for training with noisy labels.
Authors: Yaozu Ye, Hao Shi, Kailun Yang, Ze Wang, Xiaoting Yin, Yaonan Wang, Kaiwei Wang
Event cameras are capable of responding to log-brightness changes in microseconds. Its characteristic of producing responses only to the changing region is particularly suitable for optical flow estimation. In contrast to the super low-latency response speed of event cameras, existing datasets collected via event cameras, however, only provide limited frame rate optical flow ground truth, (e.g., at 10Hz), greatly restricting the potential of event-driven optical flow. To address this challenge, we put forward a high-frame-rate, low-latency event representation Unified Voxel Grid, sequentially fed into the network bin by bin. We then propose EVA-Flow, an EVent-based Anytime Flow estimation network to produce high-frame-rate event optical flow with only low-frame-rate optical flow ground truth for supervision. The key component of our EVA-Flow is the stacked Spatiotemporal Motion Refinement (SMR) module, which predicts temporally-dense optical flow and enhances the accuracy via spatial-temporal motion refinement. The time-dense feature warping utilized in the SMR module provides implicit supervision for the intermediate optical flow. Additionally, we introduce the Rectified Flow Warp Loss (RFWL) for the unsupervised evaluation of intermediate optical flow in the absence of ground truth. This is, to the best of our knowledge, the first work focusing on anytime optical flow estimation via event cameras. A comprehensive variety of experiments on MVSEC, DESC, and our EVA-FlowSet demonstrates that EVA-Flow achieves competitive performance, super-low-latency (5ms), fastest inference (9.2ms), time-dense motion estimation (200Hz), and strong generalization. Our code will be available at https://github.com/Yaozhuwa/EVA-Flow.
Authors: Guanzhou Lan, Bin Zhao, Xuelong Li
Nighttime surveillance suffers from degradation due to poor illumination and arduous human annotations. It is challengable and remains a security risk at night. Existing methods rely on multi-spectral images to perceive objects in the dark, which are troubled by low resolution and color absence. We argue that the ultimate solution for nighttime surveillance is night-to-day translation, or Night2Day, which aims to translate a surveillance scene from nighttime to the daytime while maintaining semantic consistency. To achieve this, this paper presents a Disentangled Contrastive (DiCo) learning method. Specifically, to address the poor and complex illumination in the nighttime scenes, we propose a learnable physical prior, i.e., the color invariant, which provides a stable perception of a highly dynamic night environment and can be incorporated into the learning pipeline of neural networks. Targeting the surveillance scenes, we develop a disentangled representation, which is an auxiliary pretext task that separates surveillance scenes into the foreground and background with contrastive learning. Such a strategy can extract the semantics without supervision and boost our model to achieve instance-aware translation. Finally, we incorporate all the modules above into generative adversarial networks and achieve high-fidelity translation. This paper also contributes a new surveillance dataset called NightSuR. It includes six scenes to support the study on nighttime surveillance. This dataset collects nighttime images with different properties of nighttime environments, such as flare and extreme darkness. Extensive experiments demonstrate that our method outperforms existing works significantly. The dataset and source code will be released on GitHub soon.
Authors: Yongheng Zhang, Danfeng Yan, Yuanqiang Cai
Removing multiple degradations, such as haze, rain, and blur, from real-world images poses a challenging and illposed problem. Recently, unified models that can handle different degradations have been proposed and yield promising results. However, these approaches focus on synthetic images and experience a significant performance drop when applied to realworld images. In this paper, we introduce Uni-Removal, a twostage semi-supervised framework for addressing the removal of multiple degradations in real-world images using a unified model and parameters. In the knowledge transfer stage, Uni-Removal leverages a supervised multi-teacher and student architecture in the knowledge transfer stage to facilitate learning from pretrained teacher networks specialized in different degradation types. A multi-grained contrastive loss is introduced to enhance learning from feature and image spaces. In the domain adaptation stage, unsupervised fine-tuning is performed by incorporating an adversarial discriminator on real-world images. The integration of an extended multi-grained contrastive loss and generative adversarial loss enables the adaptation of the student network from synthetic to real-world domains. Extensive experiments on real-world degraded datasets demonstrate the effectiveness of our proposed method. We compare our Uni-Removal framework with state-of-the-art supervised and unsupervised methods, showcasing its promising results in real-world image dehazing, deraining, and deblurring simultaneously.
Authors: Vedang Lad, Jonas Mueller
The labor-intensive annotation process of semantic segmentation datasets is often prone to errors, since humans struggle to label every pixel correctly. We study algorithms to automatically detect such annotation errors, in particular methods to score label quality, such that the images with the lowest scores are least likely to be correctly labeled. This helps prioritize what data to review in order to ensure a high-quality training/evaluation dataset, which is critical in sensitive applications such as medical imaging and autonomous vehicles. Widely applicable, our label quality scores rely on probabilistic predictions from a trained segmentation model -- any model architecture and training procedure can be utilized. Here we study 7 different label quality scoring methods used in conjunction with a DeepLabV3+ or a FPN segmentation model to detect annotation errors in a version of the SYNTHIA dataset. Precision-recall evaluations reveal a score -- the soft-minimum of the model-estimated likelihoods of each pixel's annotated class -- that is particularly effective to identify images that are mislabeled, across multiple types of annotation error.
Authors: Zhengxin Lei, Feng Xu, Jiangtao Wei, Feng Cai, Feng Wang, Ya-Qiu Jin
SAR images are highly sensitive to observation configurations, and they exhibit significant variations across different viewing angles, making it challenging to represent and learn their anisotropic features. As a result, deep learning methods often generalize poorly across different view angles. Inspired by the concept of neural radiance fields (NeRF), this study combines SAR imaging mechanisms with neural networks to propose a novel NeRF model for SAR image generation. Following the mapping and projection pinciples, a set of SAR images is modeled implicitly as a function of attenuation coefficients and scattering intensities in the 3D imaging space through a differentiable rendering equation. SAR-NeRF is then constructed to learn the distribution of attenuation coefficients and scattering intensities of voxels, where the vectorized form of 3D voxel SAR rendering equation and the sampling relationship between the 3D space voxels and the 2D view ray grids are analytically derived. Through quantitative experiments on various datasets, we thoroughly assess the multi-view representation and generalization capabilities of SAR-NeRF. Additionally, it is found that SAR-NeRF augumented dataset can significantly improve SAR target classification performance under few-shot learning setup, where a 10-type classification accuracy of 91.6\% can be achieved by using only 12 images per class.
Authors: Chuanbo Tang, Xihua Sheng, Zhuoyuan Li, Haotian Zhang, Li Li, Dong Liu
Video compression relies heavily on exploiting the temporal redundancy between video frames, which is usually achieved by estimating and using the motion information. The motion information is represented as optical flows in most of the existing deep video compression networks. Indeed, these networks often adopt pre-trained optical flow estimation networks for motion estimation. The optical flows, however, may be less suitable for video compression due to the following two factors. First, the optical flow estimation networks were trained to perform inter-frame prediction as accurately as possible, but the optical flows themselves may cost too many bits to encode. Second, the optical flow estimation networks were trained on synthetic data, and may not generalize well enough to real-world videos. We address the twofold limitations by enhancing the optical flows in two stages: offline and online. In the offline stage, we fine-tune a trained optical flow estimation network with the motion information provided by a traditional (non-deep) video compression scheme, e.g. H.266/VVC, as we believe the motion information of H.266/VVC achieves a better rate-distortion trade-off. In the online stage, we further optimize the latent features of the optical flows with a gradient descent-based algorithm for the video to be compressed, so as to enhance the adaptivity of the optical flows. We conduct experiments on a state-of-the-art deep video compression scheme, DCVC. Experimental results demonstrate that the proposed offline and online enhancement together achieves on average 12.8% bitrate saving on the tested videos, without increasing the model or computational complexity of the decoder side.
Authors: Kevin Hernandez-Diaz, Fernando Alonso-Fernandez, Josef Bigun
One weakness of machine-learning algorithms is the need to train the models for a new task. This presents a specific challenge for biometric recognition due to the dynamic nature of databases and, in some instances, the reliance on subject collaboration for data collection. In this paper, we investigate the behavior of deep representations in widely used CNN models under extreme data scarcity for One-Shot periocular recognition, a biometric recognition task. We analyze the outputs of CNN layers as identity-representing feature vectors. We examine the impact of Domain Adaptation on the network layers' output for unseen data and evaluate the method's robustness concerning data normalization and generalization of the best-performing layer. We improved state-of-the-art results that made use of networks trained with biometric datasets with millions of images and fine-tuned for the target periocular dataset by utilizing out-of-the-box CNNs trained for the ImageNet Recognition Challenge and standard computer vision algorithms. For example, for the Cross-Eyed dataset, we could reduce the EER by 67% and 79% (from 1.70% and 3.41% to 0.56% and 0.71%) in the Close-World and Open-World protocols, respectively, for the periocular case. We also demonstrate that traditional algorithms like SIFT can outperform CNNs in situations with limited data or scenarios where the network has not been trained with the test classes like the Open-World mode. SIFT alone was able to reduce the EER by 64% and 71.6% (from 1.7% and 3.41% to 0.6% and 0.97%) for Cross-Eyed in the Close-World and Open-World protocols, respectively, and a reduction of 4.6% (from 3.94% to 3.76%) in the PolyU database for the Open-World and single biometric case.
Authors: Yongcong Zhang, Yifei Xue, Ming Liao, Huiqing Zhang, Yizhen Lao
Despite the increasing prevalence of rotating-style capture (e.g., surveillance cameras), conventional stereo rectification techniques frequently fail due to the rotation-dominant motion and small baseline between views. In this paper, we tackle the challenge of performing stereo rectification for uncalibrated rotating cameras. To that end, we propose Depth-from-Rotation (DfR), a novel image rectification solution that analytically rectifies two images with two-point correspondences and serves for further depth estimation. Specifically, we model the motion of a rotating camera as the camera rotates on a sphere with fixed latitude. The camera's optical axis lies perpendicular to the sphere's surface. We call this latitudinal motion assumption. Then we derive a 2-point analytical solver from directly computing the rectified transformations on the two images. We also present a self-adaptive strategy to reduce the geometric distortion after rectification. Extensive synthetic and real data experiments demonstrate that the proposed method outperforms existing works in effectiveness and efficiency by a significant margin.
Authors: Paul Grimal, Hervé Le Borgne, Olivier Ferret, Julien Tourille
The progress in the generation of synthetic images has made it crucial to assess their quality. While several metrics have been proposed to assess the rendering of images, it is crucial for Text-to-Image (T2I) models, which generate images based on a prompt, to consider additional aspects such as to which extent the generated image matches the important content of the prompt. Moreover, although the generated images usually result from a random starting point, the influence of this one is generally not considered. In this article, we propose a new metric based on prompt templates to study the alignment between the content specified in the prompt and the corresponding generated images. It allows us to better characterize the alignment in terms of the type of the specified objects, their number, and their color. We conducted a study on several recent T2I models about various aspects. An additional interesting result we obtained with our approach is that image quality can vary drastically depending on the latent noise used as a seed for the images. We also quantify the influence of the number of concepts in the prompt, their order as well as their (color) attributes. Finally, our method allows us to identify some latent seeds that produce better images than others, opening novel directions of research on this understudied topic.
Authors: Adel Oulefki, Yassine Himeur, Thaweesak Trongtiraku, Kahina Amara, Sos Agaian, Samir, Benbelkacem, Mohamed Amine Guerroudji, Mohamed Zemmouri, Sahla Ferhat, Nadia Zenati, Shadi Atalla, Wathiq Mansoor
Solar Photovoltaic (PV) is increasingly being used to address the global concern of energy security. However, hot spot and snail trails in PV modules caused mostly by crakes reduce their efficiency and power capacity. This article presents a groundbreaking methodology for automatically identifying and analyzing anomalies like hot spots and snail trails in Solar Photovoltaic (PV) modules, leveraging unsupervised sensing algorithms and 3D Augmented Reality (AR) visualization. By transforming the traditional methods of diagnosis and repair, our approach not only enhances efficiency but also substantially cuts down the cost of PV system maintenance. Validated through computer simulations and real-world image datasets, the proposed framework accurately identifies dirty regions, emphasizing the critical role of regular maintenance in optimizing the power capacity of solar PV modules. Our immediate objective is to leverage drone technology for real-time, automatic solar panel detection, significantly boosting the efficacy of PV maintenance. The proposed methodology could revolutionize solar PV maintenance, enabling swift, precise anomaly detection without human intervention. This could result in significant cost savings, heightened energy production, and improved overall performance of solar PV systems. Moreover, the novel combination of unsupervised sensing algorithms with 3D AR visualization heralds new opportunities for further research and development in solar PV maintenance.
Authors: Fadi Boutros, Marcel Klemt, Meiling Fang, Arjan Kuijper, Naser Damer
Deep generative models have recently presented impressive results in generating realistic face images of random synthetic identities. To generate multiple samples of a certain synthetic identity, several previous works proposed to disentangle the latent space of GANs by incorporating additional supervision or regularization, enabling the manipulation of certain attributes, e.g. identity, hairstyle, pose, or expression. Most of these works require designing special loss functions and training dedicated network architectures. Others proposed to disentangle specific factors in unconditional pretrained GANs latent spaces to control their output, which also requires supervision by attribute classifiers. Moreover, these attributes are entangled in GAN's latent space, making it difficult to manipulate them without affecting the identity information. We propose in this work a framework, ExFaceGAN, to disentangle identity information in state-of-the-art pretrained GANs latent spaces, enabling the generation of multiple samples of any synthetic identity. The variations in our generated images are not limited to specific attributes as ExFaceGAN explicitly aims at disentangling identity information, while other visual attributes are randomly drawn from a learned GAN latent space. As an example of the practical benefit of our ExFaceGAN, we empirically prove that data generated by ExFaceGAN can be successfully used to train face recognition models.
Authors: Anshul Gupta, Samy Tafasca, Jean-Marc Odobez
Predicting where a person is looking is a complex task, requiring to understand not only the person's gaze and scene content, but also the 3D scene structure and the person's situation (are they manipulating? interacting or observing others? attentive?) to detect obstructions in the line of sight or apply attention priors that humans typically have when observing others. In this paper, we hypothesize that identifying and leveraging such priors can be better achieved through the exploitation of explicitly derived multimodal cues such as depth and pose. We thus propose a modular multimodal architecture allowing to combine these cues using an attention mechanism. The architecture can naturally be exploited in privacy-sensitive situations such as surveillance and health, where personally identifiable information cannot be released. We perform extensive experiments on the GazeFollow and VideoAttentionTarget public datasets, obtaining state-of-the-art performance and demonstrating very competitive results in the privacy setting case.
Authors: Yuxin Deng, Jiayi Ma
Attention-based graph neural networks have made great progress in feature matching learning. However, insight of how attention mechanism works for feature matching is lacked in the literature. In this paper, we rethink cross- and self-attention from the viewpoint of traditional feature matching and filtering. In order to facilitate the learning of matching and filtering, we inject the similarity of descriptors and relative positions into cross- and self-attention score, respectively. In this way, the attention can focus on learning residual matching and filtering functions with reference to the basic functions of measuring visual and spatial correlation. Moreover, we mine intra- and inter-neighbors according to the similarity of descriptors and relative positions. Then sparse attention for each point can be performed only within its neighborhoods to acquire higher computation efficiency. Feature matching networks equipped with our full and sparse residual attention learning strategies are termed ResMatch and sResMatch respectively. Extensive experiments, including feature matching, pose estimation and visual localization, confirm the superiority of our networks.
Authors: Long Bai, Mobarakol Islam, Hongliang Ren
Medical students and junior surgeons often rely on senior surgeons and specialists to answer their questions when learning surgery. However, experts are often busy with clinical and academic work, and have little time to give guidance. Meanwhile, existing deep learning (DL)-based surgical Visual Question Answering (VQA) systems can only provide simple answers without the location of the answers. In addition, vision-language (ViL) embedding is still a less explored research in these kinds of tasks. Therefore, a surgical Visual Question Localized-Answering (VQLA) system would be helpful for medical students and junior surgeons to learn and understand from recorded surgical videos. We propose an end-to-end Transformer with Co-Attention gaTed Vision-Language (CAT-ViL) for VQLA in surgical scenarios, which does not require feature extraction through detection models. The CAT-ViL embedding module is designed to fuse heterogeneous features from visual and textual sources. The fused embedding will feed a standard Data-Efficient Image Transformer (DeiT) module, before the parallel classifier and detector for joint prediction. We conduct the experimental validation on public surgical videos from MICCAI EndoVis Challenge 2017 and 2018. The experimental results highlight the superior performance and robustness of our proposed model compared to the state-of-the-art approaches. Ablation studies further prove the outstanding performance of all the proposed components. The proposed method provides a promising solution for surgical scene understanding, and opens up a primary step in the Artificial Intelligence (AI)-based VQLA system for surgical training. Our code is publicly available.
Authors: Chao Wang, Zheng Tang
In the context of label-efficient learning on video data, the distillation method and the structural design of the teacher-student architecture have a significant impact on knowledge distillation. However, the relationship between these factors has been overlooked in previous research. To address this gap, we propose a new weakly supervised learning framework for knowledge distillation in video classification that is designed to improve the efficiency and accuracy of the student model. Our approach leverages the concept of substage-based learning to distill knowledge based on the combination of student substages and the correlation of corresponding substages. We also employ the progressive cascade training method to address the accuracy loss caused by the large capacity gap between the teacher and the student. Additionally, we propose a pseudo-label optimization strategy to improve the initial data label. To optimize the loss functions of different distillation substages during the training process, we introduce a new loss method based on feature distribution. We conduct extensive experiments on both real and simulated data sets, demonstrating that our proposed approach outperforms existing distillation methods in terms of knowledge distillation for video classification tasks. Our proposed substage-based distillation approach has the potential to inform future research on label-efficient learning for video data.
Authors: Quan Sun, Qiying Yu, Yufeng Cui, Fan Zhang, Xiaosong Zhang, Yueze Wang, Hongcheng Gao, Jingjing Liu, Tiejun Huang, Xinlong Wang
We present Emu, a Transformer-based multimodal foundation model, which can seamlessly generate images and texts in multimodal context. This omnivore model can take in any single-modality or multimodal data input indiscriminately (e.g., interleaved image, text and video) through a one-model-for-all autoregressive training process. First, visual signals are encoded into embeddings, and together with text tokens form an interleaved input sequence. Emu is then end-to-end trained with a unified objective of classifying the next text token or regressing the next visual embedding in the multimodal sequence. This versatile multimodality empowers the exploration of diverse pretraining data sources at scale, such as videos with interleaved frames and text, webpages with interleaved images and text, as well as web-scale image-text pairs and video-text pairs. Emu can serve as a generalist multimodal interface for both image-to-text and text-to-image tasks, and supports in-context image and text generation. Across a broad range of zero-shot/few-shot tasks including image captioning, visual question answering, video question answering and text-to-image generation, Emu demonstrates superb performance compared to state-of-the-art large multimodal models. Extended capabilities such as multimodal assistants via instruction tuning are also demonstrated with impressive performance.
Authors: Bruno Machado Pacheco, Victor Hugo Rocha de Oliveira, Augusto Braga Fernandes Antunes, Saulo Domingos de Souza Pedro, Danilo Silva
Brain age prediction using neuroimaging data has shown great potential as an indicator of overall brain health and successful aging, as well as a disease biomarker. Deep learning models have been established as reliable and efficient brain age estimators, being trained to predict the chronological age of healthy subjects. In this paper, we investigate the impact of a pre-training step on deep learning models for brain age prediction. More precisely, instead of the common approach of pre-training on natural imaging classification, we propose pre-training the models on brain-related tasks, which led to state-of-the-art results in our experiments on ADNI data. Furthermore, we validate the resulting brain age biomarker on images of patients with mild cognitive impairment and Alzheimer's disease. Interestingly, our results indicate that better-performing deep learning models in terms of brain age prediction on healthy patients do not result in more reliable biomarkers.
Authors: Zhiwen Yang, Yang Zhou, Hui Zhang, Bingzheng Wei, Yubo Fan, Yan Xu
Multi-center positron emission tomography (PET) image synthesis aims at recovering low-dose PET images from multiple different centers. The generalizability of existing methods can still be suboptimal for a multi-center study due to domain shifts, which result from non-identical data distribution among centers with different imaging systems/protocols. While some approaches address domain shifts by training specialized models for each center, they are parameter inefficient and do not well exploit the shared knowledge across centers. To address this, we develop a generalist model that shares architecture and parameters across centers to utilize the shared knowledge. However, the generalist model can suffer from the center interference issue, \textit{i.e.} the gradient directions of different centers can be inconsistent or even opposite owing to the non-identical data distribution. To mitigate such interference, we introduce a novel dynamic routing strategy with cross-layer connections that routes data from different centers to different experts. Experiments show that our generalist model with dynamic routing (DRMC) exhibits excellent generalizability across centers. Code and data are available at: https://github.com/Yaziwel/Multi-Center-PET-Image-Synthesis.
Authors: Linhao Qu, Yingfan Ma, Zhiwei Yang, Manning Wang, Zhijian Song
Active learning (AL) is an effective approach to select the most informative samples to label so as to reduce the annotation cost. Existing AL methods typically work under the closed-set assumption, i.e., all classes existing in the unlabeled sample pool need to be classified by the target model. However, in some practical clinical tasks, the unlabeled pool may contain not only the target classes that need to be fine-grainedly classified, but also non-target classes that are irrelevant to the clinical tasks. Existing AL methods cannot work well in this scenario because they tend to select a large number of non-target samples. In this paper, we formulate this scenario as an open-set AL problem and propose an efficient framework, OpenAL, to address the challenge of querying samples from an unlabeled pool with both target class and non-target class samples. Experiments on fine-grained classification of pathology images show that OpenAL can significantly improve the query quality of target class samples and achieve higher performance than current state-of-the-art AL methods. Code is available at https://github.com/miccaiif/OpenAL.
Authors: Nour Habib, Yunsu Cho, Abhishek Buragohain, Andreas Rausch
One of the many Autonomous Systems (ASs), such as autonomous driving cars, performs various safety-critical functions. Many of these autonomous systems take advantage of Artificial Intelligence (AI) techniques to perceive their environment. But these perceiving components could not be formally verified, since, the accuracy of such AI-based components has a high dependency on the quality of training data. So Machine learning (ML) based anomaly detection, a technique to identify data that does not belong to the training data could be used as a safety measuring indicator during the development and operational time of such AI-based components. Adversarial learning, a sub-field of machine learning has proven its ability to detect anomalies in images and videos with impressive results on simple data sets. Therefore, in this work, we investigate and provide insight into the performance of such techniques on a highly complex driving scenes dataset called Berkeley DeepDrive.
Authors: Zixuan Chen, Lingxiao Yang, Jianhuang Lai, Xiaohua Xie
Sparse-view Computed Tomography (SVCT) reconstruction is an ill-posed inverse problem in imaging that aims to acquire high-quality CT images based on sparsely-sampled measurements. Recent works use Implicit Neural Representations (INRs) to build the coordinate-based mapping between sinograms and CT images. However, these methods have not considered the correlation between adjacent projection views, resulting in aliasing artifacts on SV sinograms. To address this issue, we propose a self-supervised SVCT reconstruction method -- Anti-Aliasing Projection Representation Field (APRF), which can build the continuous representation between adjacent projection views via the spatial constraints. Specifically, APRF only needs SV sinograms for training, which first employs a line-segment sampling module to estimate the distribution of projection views in a local region, and then synthesizes the corresponding sinogram values using center-based line integral module. After training APRF on a single SV sinogram itself, it can synthesize the corresponding dense-view (DV) sinogram with consistent continuity. High-quality CT images can be obtained by applying re-projection techniques on the predicted DV sinograms. Extensive experiments on CT images demonstrate that APRF outperforms state-of-the-art methods, yielding more accurate details and fewer artifacts. Our code will be publicly available soon.
Authors: Shuzhou Sun, Shuaifeng Zhi, Qing Liao, Janne Heikkilä, Li Liu
Despite the impressive performance of recent unbiased Scene Graph Generation (SGG) methods, the current debiasing literature mainly focuses on the long-tailed distribution problem, whereas it overlooks another source of bias, i.e., semantic confusion, which makes the SGG model prone to yield false predictions for similar relationships. In this paper, we explore a debiasing procedure for the SGG task leveraging causal inference. Our central insight is that the Sparse Mechanism Shift (SMS) in causality allows independent intervention on multiple biases, thereby potentially preserving head category performance while pursuing the prediction of high-informative tail relationships. However, the noisy datasets lead to unobserved confounders for the SGG task, and thus the constructed causal models are always causal-insufficient to benefit from SMS. To remedy this, we propose Two-stage Causal Modeling (TsCM) for the SGG task, which takes the long-tailed distribution and semantic confusion as confounders to the Structural Causal Model (SCM) and then decouples the causal intervention into two stages. The first stage is causal representation learning, where we use a novel Population Loss (P-Loss) to intervene in the semantic confusion confounder. The second stage introduces the Adaptive Logit Adjustment (AL-Adjustment) to eliminate the long-tailed distribution confounder to complete causal calibration learning. These two stages are model agnostic and thus can be used in any SGG model that seeks unbiased predictions. Comprehensive experiments conducted on the popular SGG backbones and benchmarks show that our TsCM can achieve state-of-the-art performance in terms of mean recall rate. Furthermore, TsCM can maintain a higher recall rate than other debiasing methods, which indicates that our method can achieve a better tradeoff between head and tail relationships.
Authors: Sushil Sharma, Ganesh Sistu, Lucie Yahiaoui, Arindam Das, Mark Halton, Ciarán Eising
Autonomous vehicles require accurate and reliable short-term trajectory predictions for safe and efficient driving. While most commercial automated vehicles currently use state machine-based algorithms for trajectory forecasting, recent efforts have focused on end-to-end data-driven systems. Often, the design of these models is limited by the availability of datasets, which are typically restricted to generic scenarios. To address this limitation, we have developed a synthetic dataset for short-term trajectory prediction tasks using the CARLA simulator. This dataset is extensive and incorporates what is considered complex scenarios - pedestrians crossing the road, vehicles overtaking - and comprises 6000 perspective view images with corresponding IMU and odometry information for each frame. Furthermore, an end-to-end short-term trajectory prediction model using convolutional neural networks (CNN) and long short-term memory (LSTM) networks has also been developed. This model can handle corner cases, such as slowing down near zebra crossings and stopping when pedestrians cross the road, without the need for explicit encoding of the surrounding environment. In an effort to accelerate this research and assist others, we are releasing our dataset and model to the research community. Our datasets are publicly available on https://github.com/navigatinguncertainty.
Authors: Pengfei Li, Gang Liu, Jinlong He, Zixu Zhao, Shenjun Zhong
Medical visual question answering (VQA) is a challenging task that requires answering clinical questions of a given medical image, by taking consider of both visual and language information. However, due to the small scale of training data for medical VQA, pre-training fine-tuning paradigms have been a commonly used solution to improve model generalization performance. In this paper, we present a novel self-supervised approach that learns unimodal and multimodal feature representations of input images and text using medical image caption datasets, by leveraging both unimodal and multimodal contrastive losses, along with masked language modeling and image text matching as pretraining objectives. The pre-trained model is then transferred to downstream medical VQA tasks. The proposed approach achieves state-of-the-art (SOTA) performance on three publicly available medical VQA datasets with significant accuracy improvements of 2.2%, 14.7%, and 1.7% respectively. Besides, we conduct a comprehensive analysis to validate the effectiveness of different components of the approach and study different pre-training settings. Our codes and models are available at https://github.com/pengfeiliHEU/MUMC.
Authors: Tomaso Fontanini, Claudio Ferrari, Massimo Bertozzi, Andrea Prati
Semantic image synthesis (SIS) refers to the problem of generating realistic imagery given a semantic segmentation mask that defines the spatial layout of object classes. Most of the approaches in the literature, other than the quality of the generated images, put effort in finding solutions to increase the generation diversity in terms of style i.e. texture. However, they all neglect a different feature, which is the possibility of manipulating the layout provided by the mask. Currently, the only way to do so is manually by means of graphical users interfaces. In this paper, we describe a network architecture to address the problem of automatically manipulating or generating the shape of object classes in semantic segmentation masks, with specific focus on human faces. Our proposed model allows embedding the mask class-wise into a latent space where each class embedding can be independently edited. Then, a bi-directional LSTM block and a convolutional decoder output a new, locally manipulated mask. We report quantitative and qualitative results on the CelebMask-HQ dataset, which show our model can both faithfully reconstruct and modify a segmentation mask at the class level. Also, we show our model can be put before a SIS generator, opening the way to a fully automatic generation control of both shape and texture. Code available at https://github.com/TFonta/Semantic-VAE.
Authors: Marc-Antoine Lavoie, Steven Waslander
The long-tailed image classification task remains important in the development of deep neural networks as it explicitly deals with large imbalances in the class frequencies of the training data. While uncommon in engineered datasets, this imbalance is almost always present in real-world data. Previous approaches have shown that combining cross-entropy and contrastive learning can improve performance on the long-tailed task, but they do not explore the tradeoff between head and tail classes. We propose a novel class instance balanced loss (CIBL), which reweights the relative contributions of a cross-entropy and a contrastive loss as a function of the frequency of class instances in the training batch. This balancing favours the contrastive loss for more common classes, leading to a learned classifier with a more balanced performance across all class frequencies. Furthermore, increasing the relative weight on the contrastive head shifts performance from common (head) to rare (tail) classes, allowing the user to skew the performance towards these classes if desired. We also show that changing the linear classifier head with a cosine classifier yields a network that can be trained to similar performance in substantially fewer epochs. We obtain competitive results on both CIFAR-100-LT and ImageNet-LT.
Authors: Michał Szachniewicz, Wojciech Kozłowski, Michał Stypułkowski, Maciej Zięba
Self-supervised methods have been proven effective for learning deep representations of 3D point cloud data. Although recent methods in this domain often rely on random masking of inputs, the results of this approach can be improved. We introduce PointCAM, a novel adversarial method for learning a masking function for point clouds. Our model utilizes a self-distillation framework with an online tokenizer for 3D point clouds. Compared to previous techniques that optimize patch-level and object-level objectives, we postulate applying an auxiliary network that learns how to select masks instead of choosing them randomly. Our results show that the learned masking function achieves state-of-the-art or competitive performance on various downstream tasks. The source code is available at https://github.com/szacho/pointcam.
Authors: Shantanu Ghosh, Ke Yu, Forough Arabshahi, Kayhan Batmanghelich
The current approach to ML model design is either to choose a flexible Blackbox model and explain it post hoc or to start with an interpretable model. Blackbox models are flexible but difficult to explain, whereas interpretable models are designed to be explainable. However, developing interpretable models necessitates extensive ML knowledge, and the resulting models tend to be less flexible, offering potentially subpar performance compared to their Blackbox equivalents. This paper aims to blur the distinction between a post hoc explanation of a BlackBox and constructing interpretable models. We propose beginning with a flexible BlackBox model and gradually \emph{carving out} a mixture of interpretable models and a \emph{residual network}. Our design identifies a subset of samples and \emph{routes} them through the interpretable models. The remaining samples are routed through a flexible residual network. We adopt First Order Logic (FOL) as the interpretable model's backbone, which provides basic reasoning on concepts retrieved from the BlackBox model. On the residual network, we repeat the method until the proportion of data explained by the residual network falls below a desired threshold. Our approach offers several advantages. First, the mixture of interpretable and flexible residual networks results in almost no compromise in performance. Second, the route, interpret, and repeat approach yields a highly flexible interpretable model. Our extensive experiment demonstrates the performance of the model on various datasets. We show that by editing the FOL model, we can fix the shortcut learned by the original BlackBox model. Finally, our method provides a framework for a hybrid symbolic-connectionist network that is simple to train and adaptable to many applications.
Authors: Benny J. Tang, Angie Boggust, Arvind Satyanarayan
Captions that describe or explain charts help improve recall and comprehension of the depicted data and provide a more accessible medium for people with visual disabilities. However, current approaches for automatically generating such captions struggle to articulate the perceptual or cognitive features that are the hallmark of charts (e.g., complex trends and patterns). In response, we introduce VisText: a dataset of 12,441 pairs of charts and captions that describe the charts' construction, report key statistics, and identify perceptual and cognitive phenomena. In VisText, a chart is available as three representations: a rasterized image, a backing data table, and a scene graph -- a hierarchical representation of a chart's visual elements akin to a web page's Document Object Model (DOM). To evaluate the impact of VisText, we fine-tune state-of-the-art language models on our chart captioning task and apply prefix-tuning to produce captions that vary the semantic content they convey. Our models generate coherent, semantically rich captions and perform on par with state-of-the-art chart captioning models across machine translation and text generation metrics. Through qualitative analysis, we identify six broad categories of errors that our models make that can inform future work.
Authors: Lubnaa Abdur Rahman, Ioannis Papathanail, Lorenzo Brigato, Elias K. Spanakis, Stavroula Mougiakakou
Food recognition and nutritional apps are trending technologies that may revolutionise the way people with diabetes manage their diet. Such apps can monitor food intake as a digital diary and even employ artificial intelligence to assess the diet automatically. Although these apps offer a promising solution for managing diabetes, they are rarely used by patients. This chapter aims to provide an in-depth assessment of the current status of apps for food recognition and nutrition, to identify factors that may inhibit or facilitate their use, while it is accompanied by an outline of relevant research and development.
Authors: M. L. Sloan
The human tri-color vision process may be characterized as follows:
1. A requirement of three scalar quantities to fully define a color (for example, intensity, hue, and purity), with
2. These scalar measures linear in the intensity of the incident light, allowing in general any specific color to be duplicated by an additive mixture of light from three standardized (basis) colors,
3. The exception being that the spectral colors are unique, in that they cannot be duplicated by any positive mixture of other colors.
These characteristics strongly suggest that human color vision makes use of Schwartz measures in processing color data. This hypothesis is subject to test. In this brief paper, the results of this hypothesis are shown to be in good agreement with measured data.
Authors: Davood Karimi, Hamza Kebiri, Ali Gholipour
Diffusion-weighted magnetic resonance imaging (dMRI) is widely used to assess the brain white matter. One of the most common computations in dMRI involves cross-subject tract-specific analysis, whereby dMRI-derived biomarkers are compared between cohorts of subjects. The accuracy and reliability of these studies hinges on the ability to compare precisely the same white matter tracts across subjects. This is an intricate and error-prone computation. Existing computational methods such as Tract-Based Spatial Statistics (TBSS) suffer from a host of shortcomings and limitations that can seriously undermine the validity of the results. We present a new computational framework that overcomes the limitations of existing methods via (i) accurate segmentation of the tracts, and (ii) precise registration of data from different subjects/scans. The registration is based on fiber orientation distributions. To further improve the alignment of cross-subject data, we create detailed atlases of white matter tracts. These atlases serve as an unbiased reference space where the data from all subjects is registered for comparison. Extensive evaluations show that, compared with TBSS, our proposed framework offers significantly higher reproducibility and robustness to data perturbations. Our method promises a drastic improvement in accuracy and reproducibility of cross-subject dMRI studies that are routinely used in neuroscience and medical research.
Authors: Atman Mishra, A. Sharath Ram, Kavyashree C
OCR (Optical Character Recognition) is a technology that offers comprehensive alphanumeric recognition of handwritten and printed characters at electronic speed by merely scanning the document. Recently, the understanding of visual data has been termed Intelligent Character Recognition (ICR). Intelligent Character Recognition (ICR) is the OCR module that can convert scans of handwritten or printed characters into ASCII text. ASCII data is the standard format for data encoding in electronic communication. ASCII assigns standard numeric values to letters, numeral, symbols, white-spaces and other characters. In more technical terms, OCR is the process of using an electronic device to transform 2-Dimensional textual information into machine-encoded text. Anything that contains text both machine written or handwritten can be scanned either through a scanner or just simply a picture of the text is enough for the recognition system to distinguish the text. The goal of this papers is to show the results of a Convolutional Neural Network model which has been trained on National Institute of Science and Technology (NIST) dataset containing over a 100,000 images. The network learns from the features extracted from the images and use it to generate the probability of each class to which the picture belongs to. We have achieved an accuracy of 90.54% with a loss of 2.53%.
Authors: Marija Ivanovska, Vitomir Štruc
The detection of malicious Deepfakes is a constantly evolving problem, that requires continuous monitoring of detectors, to ensure they are able to detect image manipulations generated by the latest emerging models. In this paper, we present a preliminary study that investigates the vulnerability of single-image Deepfake detectors to attacks created by a representative of the newest generation of generative methods, i.e. Denoising Diffusion Models (DDMs). Our experiments are run on FaceForensics++, a commonly used benchmark dataset, consisting of Deepfakes generated with various techniques for face swapping and face reenactment. The analysis shows, that reconstructing existing Deepfakes with only one denoising diffusion step significantly decreases the accuracy of all tested detectors, without introducing visually perceptible image changes.
Authors: Johann Lussange, Mulin Yu, Yuliya Tarabalka, Florent Lafarge
Reconstructing urban areas in 3D out of satellite raster images has been a long-standing and challenging goal of both academical and industrial research. The rare methods today achieving this objective at a Level Of Details $2$ rely on procedural approaches based on geometry, and need stereo images and/or LIDAR data as input. We here propose a method for urban 3D reconstruction named KIBS(\textit{Keypoints Inference By Segmentation}), which comprises two novel features: i) a full deep learning approach for the 3D detection of the roof sections, and ii) only one single (non-orthogonal) satellite raster image as model input. This is achieved in two steps: i) by a Mask R-CNN model performing a 2D segmentation of the buildings' roof sections, and after blending these latter segmented pixels within the RGB satellite raster image, ii) by another identical Mask R-CNN model inferring the heights-to-ground of the roof sections' corners via panoptic segmentation, unto full 3D reconstruction of the buildings and city. We demonstrate the potential of the KIBS method by reconstructing different urban areas in a few minutes, with a Jaccard index for the 2D segmentation of individual roof sections of $88.55\%$ and $75.21\%$ on our two data sets resp., and a height's mean error of such correctly segmented pixels for the 3D reconstruction of $1.60$ m and $2.06$ m on our two data sets resp., hence within the LOD2 precision range.
Authors: Evangelos Ntavelis, Aliaksandr Siarohin, Kyle Olszewski, Chaoyang Wang, Luc Van Gool, Sergey Tulyakov
We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core. The 3D autodecoder framework embeds properties learned from the target dataset in the latent space, which can then be decoded into a volumetric representation for rendering view-consistent appearance and geometry. We then identify the appropriate intermediate volumetric latent space, and introduce robust normalization and de-normalization operations to learn a 3D diffusion from 2D images or monocular videos of rigid or articulated objects. Our approach is flexible enough to use either existing camera supervision or no camera information at all -- instead efficiently learning it during training. Our evaluations demonstrate that our generation results outperform state-of-the-art alternatives on various benchmark datasets and metrics, including multi-view image datasets of synthetic objects, real in-the-wild videos of moving people, and a large-scale, real video dataset of static objects.
Authors: Xinyi Bai, Steffi Agino Priyanka, Hsiao-Jung Tung, Yuankai Wang
Due to the low accuracy of object detection and recognition in many intelligent surveillance systems at nighttime, the quality of night images is crucial. Compared with the corresponding daytime image, nighttime image is characterized as low brightness, low contrast and high noise. In this paper, a bio-inspired image enhancement algorithm is proposed to convert a low illuminance image to a brighter and clear one. Different from existing bio-inspired algorithm, the proposed method doesn't use any training sequences, we depend on a novel chain of contrast enhancement and denoising algorithms without using any forms of recursive functions. Our method can largely improve the brightness and contrast of night images, besides, suppress noise. Then we implement on real experiment, and simulation experiment to test our algorithms. Both results show the advantages of proposed algorithm over contrast pair, Meylan and Retinex.
Authors: Yinghao Xu, Wang Yifan, Alexander W. Bergman, Menglei Chai, Bolei Zhou, Gordon Wetzstein
Access to high-quality and diverse 3D articulated digital human assets is crucial in various applications, ranging from virtual reality to social platforms. Generative approaches, such as 3D generative adversarial networks (GANs), are rapidly replacing laborious manual content creation tools. However, existing 3D GAN frameworks typically rely on scene representations that leverage either template meshes, which are fast but offer limited quality, or volumes, which offer high capacity but are slow to render, thereby limiting the 3D fidelity in GAN settings. In this work, we introduce layered surface volumes (LSVs) as a new 3D object representation for articulated digital humans. LSVs represent a human body using multiple textured mesh layers around a conventional template. These layers are rendered using alpha compositing with fast differentiable rasterization, and they can be interpreted as a volumetric representation that allocates its capacity to a manifold of finite thickness around the template. Unlike conventional single-layer templates that struggle with representing fine off-surface details like hair or accessories, our surface volumes naturally capture such details. LSVs can be articulated, and they exhibit exceptional efficiency in GAN settings, where a 2D generator learns to synthesize the RGBA textures for the individual layers. Trained on unstructured, single-view 2D image datasets, our LSV-GAN generates high-quality and view-consistent 3D articulated digital humans without the need for view-inconsistent 2D upsampling networks.
Authors: Shraman Pramanick, Yale Song, Sayan Nag, Kevin Qinghong Lin, Hardik Shah, Mike Zheng Shou, Rama Chellappa, Pengchuan Zhang
Video-language pre-training (VLP) has become increasingly important due to its ability to generalize to various vision and language tasks. However, existing egocentric VLP frameworks utilize separate video and language encoders and learn task-specific cross-modal information only during fine-tuning, limiting the development of a unified system. In this work, we introduce the second generation of egocentric video-language pre-training (EgoVLPv2), a significant improvement from the previous generation, by incorporating cross-modal fusion directly into the video and language backbones. EgoVLPv2 learns strong video-text representation during pre-training and reuses the cross-modal attention modules to support different downstream tasks in a flexible and efficient manner, reducing fine-tuning costs. Moreover, our proposed fusion in the backbone strategy is more lightweight and compute-efficient than stacking additional fusion-specific layers. Extensive experiments on a wide range of VL tasks demonstrate the effectiveness of EgoVLPv2 by achieving consistent state-of-the-art performance over strong baselines across all downstream. Our project page can be found at https://shramanpramanick.github.io/EgoVLPv2/.
Authors: Luchao Qi, Jiaye Wu, Shengze Wang, Soumyadip Sengupta
Our paper presents My3DGen, a practical system for creating a personalized and lightweight 3D generative prior using as few as 10 images. My3DGen can reconstruct multi-view consistent images from an input test image, and generate novel appearances by interpolating between any two images of the same individual. While recent studies have demonstrated the effectiveness of personalized generative priors in producing high-quality 2D portrait reconstructions and syntheses, to the best of our knowledge, we are the first to develop a personalized 3D generative prior. Instead of fine-tuning a large pre-trained generative model with millions of parameters to achieve personalization, we propose a parameter-efficient approach. Our method involves utilizing a pre-trained model with fixed weights as a generic prior, while training a separate personalized prior through low-rank decomposition of the weights in each convolution and fully connected layer. However, parameter-efficient few-shot fine-tuning on its own often leads to overfitting. To address this, we introduce a regularization technique based on symmetry of human faces. This regularization enforces that novel view renderings of a training sample, rendered from symmetric poses, exhibit the same identity. By incorporating this symmetry prior, we enhance the quality of reconstruction and synthesis, particularly for non-frontal (profile) faces. Our final system combines low-rank fine-tuning with symmetry regularization and significantly surpasses the performance of pre-trained models, e.g. EG3D. It introduces only approximately 0.6 million additional parameters per identity compared to 31 million for full finetuning of the original model. As a result, our system achieves a 50-fold reduction in model size without sacrificing the quality of the generated 3D faces. Code will be available at our project page: https://luchaoqi.github.io/my3dgen.
Authors: Roland S. Zimmermann, Thomas Klein, Wieland Brendel
In light of the recent widespread adoption of AI systems, understanding the internal information processing of neural networks has become increasingly critical. Most recently, machine vision has seen remarkable progress by scaling neural networks to unprecedented levels in dataset and model size. We here ask whether this extraordinary increase in scale also positively impacts the field of mechanistic interpretability. In other words, has our understanding of the inner workings of scaled neural networks improved as well? We here use a psychophysical paradigm to quantify mechanistic interpretability for a diverse suite of models and find no scaling effect for interpretability - neither for model nor dataset size. Specifically, none of the nine investigated state-of-the-art models are easier to interpret than the GoogLeNet model from almost a decade ago. Latest-generation vision models appear even less interpretable than older architectures, hinting at a regression rather than improvement, with modern models sacrificing interpretability for accuracy. These results highlight the need for models explicitly designed to be mechanistically interpretable and the need for more helpful interpretability methods to increase our understanding of networks at an atomic level. We release a dataset containing more than 120'000 human responses from our psychophysical evaluation of 767 units across nine models. This dataset is meant to facilitate research on automated instead of human-based interpretability evaluations that can ultimately be leveraged to directly optimize the mechanistic interpretability of models.
Authors: Tom Monnier, Jake Austin, Angjoo Kanazawa, Alexei A. Efros, Mathieu Aubry
Given a set of calibrated images of a scene, we present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives. While many approaches focus on recovering high-fidelity 3D scenes, we focus on parsing a scene into mid-level 3D representations made of a small set of textured primitives. Such representations are interpretable, easy to manipulate and suited for physics-based simulations. Moreover, unlike existing primitive decomposition methods that rely on 3D input data, our approach operates directly on images through differentiable rendering. Specifically, we model primitives as textured superquadric meshes and optimize their parameters from scratch with an image rendering loss. We highlight the importance of modeling transparency for each primitive, which is critical for optimization and also enables handling varying numbers of primitives. We show that the resulting textured primitives faithfully reconstruct the input images and accurately model the visible 3D points, while providing amodal shape completions of unseen object regions. We compare our approach to the state of the art on diverse scenes from DTU, and demonstrate its robustness on real-life captures from BlendedMVS and Nerfstudio. We also showcase how our results can be used to effortlessly edit a scene or perform physical simulations. Code and video results are available at https://www.tmonnier.com/DBW .
Authors: Songyuan Li, Junyi Feng, Xi Li
Recent approaches for fast semantic video segmentation have reduced redundancy by warping feature maps across adjacent frames, greatly speeding up the inference phase. However, the accuracy drops seriously owing to the errors incurred by warping. In this paper, we propose a novel framework and design a simple and effective correction stage after warping. Specifically, we build a non-key-frame CNN, fusing warped context features with current spatial details. Based on the feature fusion, our Context Feature Rectification~(CFR) module learns the model's difference from a per-frame model to correct the warped features. Furthermore, our Residual-Guided Attention~(RGA) module utilizes the residual maps in the compressed domain to help CRF focus on error-prone regions. Results on Cityscapes show that the accuracy significantly increases from $67.3\%$ to $71.6\%$, and the speed edges down from $65.5$ FPS to $61.8$ FPS at a resolution of $1024\times 2048$. For non-rigid categories, e.g., ``human'' and ``object'', the improvements are even higher than 18 percentage points.
Authors: Xiaomeng Dong, Michael Potter, Gaurav Kumar, Yun-Chan Tsai, V. Ratna Saripalli, Theodore Trafalis
It is no secret amongst deep learning researchers that finding the optimal data augmentation strategy during training can mean the difference between state-of-the-art performance and a run-of-the-mill result. To that end, the community has seen many efforts to automate the process of finding the perfect augmentation procedure for any task at hand. Unfortunately, even recent cutting-edge methods bring massive computational overhead, requiring as many as 100 full model trainings to settle on an ideal configuration. We show how to achieve equivalent performance using just 6 trainings with Random Unidimensional Augmentation. Source code is available at https://github.com/fastestimator/RUA/tree/v1.0
Authors: Qihang Yu, Huiyu Wang, Siyuan Qiao, Maxwell Collins, Yukun Zhu, Hartwig Adam, Alan Yuille, Liang-Chieh Chen
The rise of transformers in vision tasks not only advances network backbone designs, but also starts a brand-new page to achieve end-to-end image recognition (e.g., object detection and panoptic segmentation). Originated from Natural Language Processing (NLP), transformer architectures, consisting of self-attention and cross-attention, effectively learn long-range interactions between elements in a sequence. However, we observe that most existing transformer-based vision models simply borrow the idea from NLP, neglecting the crucial difference between languages and images, particularly the extremely large sequence length of spatially flattened pixel features. This subsequently impedes the learning in cross-attention between pixel features and object queries. In this paper, we rethink the relationship between pixels and object queries and propose to reformulate the cross-attention learning as a clustering process. Inspired by the traditional k-means clustering algorithm, we develop a k-means Mask Xformer (kMaX-DeepLab) for segmentation tasks, which not only improves the state-of-the-art, but also enjoys a simple and elegant design. As a result, our kMaX-DeepLab achieves a new state-of-the-art performance on COCO val set with 58.0% PQ, Cityscapes val set with 68.4% PQ, 44.0% AP, and 83.5% mIoU, and ADE20K val set with 50.9% PQ and 55.2% mIoU without test-time augmentation or external dataset. We hope our work can shed some light on designing transformers tailored for vision tasks. TensorFlow code and models are available at https://github.com/google-research/deeplab2 A PyTorch re-implementation is also available at https://github.com/bytedance/kmax-deeplab
Authors: Asha Rani, Pankaj Yadav, Yashaswi Verma
Autism, also known as Autism Spectrum Disorder (or ASD), is a neurological disorder. Its main symptoms include difficulty in (verbal and/or non-verbal) communication, and rigid/repetitive behavior. These symptoms are often indistinguishable from a normal (control) individual, due to which this disorder remains undiagnosed in early childhood leading to delayed treatment. Since the learning curve is steep during the initial age, an early diagnosis of autism could allow to take adequate interventions at the right time, which might positively affect the growth of an autistic child. Further, the traditional methods of autism diagnosis require multiple visits to a specialized psychiatrist, however this process can be time-consuming. In this paper, we present a learning based approach to automate autism diagnosis using simple and small action video clips of subjects. This task is particularly challenging because the amount of annotated data available is small, and the variations among samples from the two categories (ASD and control) are generally indistinguishable. This is also evident from poor performance of a binary classifier learned using the cross-entropy loss on top of a baseline encoder. To address this, we adopt contrastive feature learning in both self supervised and supervised learning frameworks, and show that these can lead to a significant increase in the prediction accuracy of a binary classifier on this task. We further validate this by conducting thorough experimental analyses under different set-ups on two publicly available datasets.
Authors: Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani, Alessandro Bruno
The visual scanpath is a sequence of points through which the human gaze moves while exploring a scene. It represents the fundamental concepts upon which visual attention research is based. As a result, the ability to predict them has emerged as an important task in recent years. In this paper, we propose an inter-observer consistent adversarial training approach for scanpath prediction through a lightweight deep neural network. The adversarial method employs a discriminative neural network as a dynamic loss that is better suited to model the natural stochastic phenomenon while maintaining consistency between the distributions related to the subjective nature of scanpaths traversed by different observers. Through extensive testing, we show the competitiveness of our approach in regard to state-of-the-art methods.
Authors: Yuting Xiao, Yiqun Zhao, Yanyu Xu, Shenghua Gao
We represent the ResNeRF, a novel geometry-guided two-stage framework for indoor scene novel view synthesis. Be aware of that a good geometry would greatly boost the performance of novel view synthesis, and to avoid the geometry ambiguity issue, we propose to characterize the density distribution of the scene based on a base density estimated from scene geometry and a residual density parameterized by the geometry. In the first stage, we focus on geometry reconstruction based on SDF representation, which would lead to a good geometry surface of the scene and also a sharp density. In the second stage, the residual density is learned based on the SDF learned in the first stage for encoding more details about the appearance. In this way, our method can better learn the density distribution with the geometry prior for high-fidelity novel view synthesis while preserving the 3D structures. Experiments on large-scale indoor scenes with many less-observed and textureless areas show that with the good 3D surface, our method achieves state-of-the-art performance for novel view synthesis.
Authors: Rogier van der Sluijs, Nandita Bhaskhar, Daniel Rubin, Curtis Langlotz, Akshay Chaudhari
Image augmentations are quintessential for effective visual representation learning across self-supervised learning techniques. While augmentation strategies for natural imaging have been studied extensively, medical images are vastly different from their natural counterparts. Thus, it is unknown whether common augmentation strategies employed in Siamese representation learning generalize to medical images and to what extent. To address this challenge, in this study, we systematically assess the effect of various augmentations on the quality and robustness of the learned representations. We train and evaluate Siamese Networks for abnormality detection on chest X-Rays across three large datasets (MIMIC-CXR, CheXpert and VinDR-CXR). We investigate the efficacy of the learned representations through experiments involving linear probing, fine-tuning, zero-shot transfer, and data efficiency. Finally, we identify a set of augmentations that yield robust representations that generalize well to both out-of-distribution data and diseases, while outperforming supervised baselines using just zero-shot transfer and linear probes by up to 20%. Our code is available at https://github.com/StanfordMIMI/siaug.
Authors: Wan-Duo Kurt Ma, J.P. Lewis, Avisek Lahiri, Thomas Leung, W. Bastiaan Kleijn
Text-guided diffusion models such as DALLE-2, Imagen, and Stable Diffusion are able to generate an effectively endless variety of images given only a short text prompt describing the desired image content. In many cases the images are of very high quality. However, these models often struggle to compose scenes containing several key objects such as characters in specified positional relationships. The missing capability to "direct" the placement of characters and objects both within and across images is crucial in storytelling, as recognized in the literature on film and animation theory. In this work, we take a particularly straightforward approach to providing the needed direction. Drawing on the observation that the cross-attention maps for prompt words reflect the spatial layout of objects denoted by those words, we introduce an optimization objective that produces ``activation'' at desired positions in these cross-attention maps. The resulting approach is a step toward generalizing the applicability of text-guided diffusion models beyond single images to collections of related images, as in storybooks. To the best of our knowledge, our Directed Diffusion method is the first diffusion technique that provides positional control over multiple objects, while making use of an existing pre-trained model and maintaining a coherent blend between the positioned objects and the background. Moreover, it requires only a few lines to implement.
Authors: Junbin Xiao, Pan Zhou, Angela Yao, Yicong Li, Richang Hong, Shuicheng Yan, Tat-Seng Chua
We propose to perform video question answering (VideoQA) in a Contrastive manner via a Video Graph Transformer model (CoVGT). CoVGT's uniqueness and superiority are three-fold: 1) It proposes a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations and dynamics, for complex spatio-temporal reasoning. 2) It designs separate video and text transformers for contrastive learning between the video and text to perform QA, instead of multi-modal transformer for answer classification. Fine-grained video-text communication is done by additional cross-modal interaction modules. 3) It is optimized by the joint fully- and self-supervised contrastive objectives between the correct and incorrect answers, as well as the relevant and irrelevant questions respectively. With superior video encoding and QA solution, we show that CoVGT can achieve much better performances than previous arts on video reasoning tasks. Its performances even surpass those models that are pretrained with millions of external data. We further show that CoVGT can also benefit from cross-modal pretraining, yet with orders of magnitude smaller data. The results demonstrate the effectiveness and superiority of CoVGT, and additionally reveal its potential for more data-efficient pretraining. We hope our success can advance VideoQA beyond coarse recognition/description towards fine-grained relation reasoning of video contents. Our code is available at https://github.com/doc-doc/CoVGT.
Authors: Chang Liu, Wenzhao Xiang, Yuan He, Hui Xue, Shibao Zheng, Hang Su
Deep neural networks (DNNs) may suffer from significantly degenerated performance when the training and test data are of different underlying distributions. Despite the importance of model generalization to out-of-distribution (OOD) data, the accuracy of state-of-the-art (SOTA) models on OOD data can plummet. Recent work has demonstrated that regular or off-manifold adversarial examples, as a special case of data augmentation, can be used to improve OOD generalization. Inspired by this, we theoretically prove that on-manifold adversarial examples can better benefit OOD generalization. Nevertheless, it is nontrivial to generate on-manifold adversarial examples because the real manifold is generally complex. To address this issue, we proposed a novel method of Augmenting data with Adversarial examples via a Wavelet module (AdvWavAug), an on-manifold adversarial data augmentation technique that is simple to implement. In particular, we project a benign image into a wavelet domain. With the assistance of the sparsity characteristic of wavelet transformation, we can modify an image on the estimated data manifold. We conduct adversarial augmentation based on AdvProp training framework. Extensive experiments on different models and different datasets, including ImageNet and its distorted versions, demonstrate that our method can improve model generalization, especially on OOD data. By integrating AdvWavAug into the training process, we have achieved SOTA results on some recent transformer-based models.
Authors: Jinfeng Wang, Sifan Song, Jionglong Su, S. Kevin Zhou
Self-supervised learning is well known for its remarkable performance in representation learning and various downstream computer vision tasks. Recently, Positive-pair-Only Contrastive Learning (POCL) has achieved reliable performance without the need to construct positive-negative training sets. It reduces memory requirements by lessening the dependency on the batch size. The POCL method typically uses a single loss function to extract the distortion invariant representation (DIR) which describes the proximity of positive-pair representations affected by different distortions. This loss function implicitly enables the model to filter out or ignore the distortion variant representation (DVR) affected by different distortions. However, existing POCL methods do not explicitly enforce the disentanglement and exploitation of the actually valuable DVR. In addition, these POCL methods have been observed to be sensitive to augmentation strategies. To address these limitations, we propose a novel POCL framework named Distortion-Disentangled Contrastive Learning (DDCL) and a Distortion-Disentangled Loss (DDL). Our approach is the first to explicitly disentangle and exploit the DVR inside the model and feature stream to improve the overall representation utilization efficiency, robustness and representation ability. Experiments carried out demonstrate the superiority of our framework to Barlow Twins and Simsiam in terms of convergence, representation quality, and robustness on several benchmark datasets.
Authors: Kangcheng Liu, Aoran Xiao, Xiaoqin Zhang, Shijian Lu, Ling Shao
Contrastive learning has recently demonstrated great potential for unsupervised pre-training in 3D scene understanding tasks. However, most existing work randomly selects point features as anchors while building contrast, leading to a clear bias toward background points that often dominate in 3D scenes. Also, object awareness and foreground-to-background discrimination are neglected, making contrastive learning less effective. To tackle these issues, we propose a general foreground-aware feature contrast (FAC) framework to learn more effective point cloud representations in pre-training. FAC consists of two novel contrast designs to construct more effective and informative contrast pairs. The first is building positive pairs within the same foreground segment where points tend to have the same semantics. The second is that we prevent over-discrimination between 3D segments/objects and encourage foreground-to-background distinctions at the segment level with adaptive feature learning in a Siamese correspondence network, which adaptively learns feature correlations within and across point cloud views effectively. Visualization with point activation maps shows that our contrast pairs capture clear correspondences among foreground regions during pre-training. Quantitative experiments also show that FAC achieves superior knowledge transfer and data efficiency in various downstream 3D semantic segmentation and object detection tasks.
Authors: Yiqun Lin, Zhongjin Luo, Wei Zhao, Xiaomeng Li
Sparse-view cone-beam CT (CBCT) reconstruction is an important direction to reduce radiation dose and benefit clinical applications. Previous voxel-based generation methods represent the CT as discrete voxels, resulting in high memory requirements and limited spatial resolution due to the use of 3D decoders. In this paper, we formulate the CT volume as a continuous intensity field and develop a novel DIF-Net to perform high-quality CBCT reconstruction from extremely sparse (fewer than 10) projection views at an ultrafast speed. The intensity field of a CT can be regarded as a continuous function of 3D spatial points. Therefore, the reconstruction can be reformulated as regressing the intensity value of an arbitrary 3D point from given sparse projections. Specifically, for a point, DIF-Net extracts its view-specific features from different 2D projection views. These features are subsequently aggregated by a fusion module for intensity estimation. Notably, thousands of points can be processed in parallel to improve efficiency during training and testing. In practice, we collect a knee CBCT dataset to train and evaluate DIF-Net. Extensive experiments show that our approach can reconstruct CBCT with high image quality and high spatial resolution from extremely sparse views within 1.6 seconds, significantly outperforming state-of-the-art methods. Our code will be available at https://github.com/xmed-lab/DIF-Net.
Authors: Yijun Yang, Huazhu Fu, Angelica I. Aviles-Rivero, Carola-Bibiane Schönlieb, Lei Zhu
Diffusion Probabilistic Models have recently shown remarkable performance in generative image modeling, attracting significant attention in the computer vision community. However, while a substantial amount of diffusion-based research has focused on generative tasks, few studies have applied diffusion models to general medical image classification. In this paper, we propose the first diffusion-based model (named DiffMIC) to address general medical image classification by eliminating unexpected noise and perturbations in medical images and robustly capturing semantic representation. To achieve this goal, we devise a dual conditional guidance strategy that conditions each diffusion step with multiple granularities to improve step-wise regional attention. Furthermore, we propose learning the mutual information in each granularity by enforcing Maximum-Mean Discrepancy regularization during the diffusion forward process. We evaluate the effectiveness of our DiffMIC on three medical classification tasks with different image modalities, including placental maturity grading on ultrasound images, skin lesion classification using dermatoscopic images, and diabetic retinopathy grading using fundus images. Our experimental results demonstrate that DiffMIC outperforms state-of-the-art methods by a significant margin, indicating the universality and effectiveness of the proposed model. Our code will be publicly available at https://github.com/scott-yjyang/DiffMIC.
Authors: Zixuan Ding, Ao Wang, Hui Chen, Qiang Zhang, Pengzhang Liu, Yongjun Bao, Weipeng Yan, Jungong Han
Multi-label recognition (MLR) with incomplete labels is very challenging. Recent works strive to explore the image-to-label correspondence in the vision-language model, \ie, CLIP, to compensate for insufficient annotations. In spite of promising performance, they generally overlook the valuable prior about the label-to-label correspondence. In this paper, we advocate remedying the deficiency of label supervision for the MLR with incomplete labels by deriving a structured semantic prior about the label-to-label correspondence via a semantic prior prompter. We then present a novel Semantic Correspondence Prompt Network (SCPNet), which can thoroughly explore the structured semantic prior. A Prior-Enhanced Self-Supervised Learning method is further introduced to enhance the use of the prior. Comprehensive experiments and analyses on several widely used benchmark datasets show that our method significantly outperforms existing methods on all datasets, well demonstrating the effectiveness and the superiority of our method. Our code will be available at https://github.com/jameslahm/SCPNet.
Authors: Dongyu Yan, Jianheng Liu, Fengyu Quan, Haoyao Chen, Mengmeng Fu
Actively planning sensor views during object reconstruction is crucial for autonomous mobile robots. An effective method should be able to strike a balance between accuracy and efficiency. In this paper, we propose a seamless integration of the emerging implicit representation with the active reconstruction task. We build an implicit occupancy field as our geometry proxy. While training, the prior object bounding box is utilized as auxiliary information to generate clean and detailed reconstructions. To evaluate view uncertainty, we employ a sampling-based approach that directly extracts entropy from the reconstructed occupancy probability field as our measure of view information gain. This eliminates the need for additional uncertainty maps or learning. Unlike previous methods that compare view uncertainty within a finite set of candidates, we aim to find the next-best-view (NBV) on a continuous manifold. Leveraging the differentiability of the implicit representation, the NBV can be optimized directly by maximizing the view uncertainty using gradient descent. It significantly enhances the method's adaptability to different scenarios. Simulation and real-world experiments demonstrate that our approach effectively improves reconstruction accuracy and efficiency of view planning in active reconstruction tasks. The proposed system will open source at https://github.com/HITSZ-NRSL/ActiveImplicitRecon.git.
Authors: Tejas Srinivasan, Furong Jia, Mohammad Rostami, Jesse Thomason
Adapters present a promising solution to the catastrophic forgetting problem in continual learning. However, training independent Adapter modules for every new task misses an opportunity for cross-task knowledge transfer. We propose Improvise to Initialize (I2I), a continual learning algorithm that initializes Adapters for incoming tasks by distilling knowledge from previously-learned tasks' Adapters. We evaluate I2I on CLiMB, a multimodal continual learning benchmark, by conducting experiments on sequences of visual question answering tasks. Adapters trained with I2I consistently achieve better task accuracy than independently-trained Adapters, demonstrating that our algorithm facilitates knowledge transfer between task Adapters. I2I also results in better cross-task knowledge transfer than the state-of-the-art AdapterFusion without incurring the associated parametric cost.
Authors: Ali Borji
The ability of image and video generation models to create photorealistic images has reached unprecedented heights, making it difficult to distinguish between real and fake images in many cases. However, despite this progress, a gap remains between the quality of generated images and those found in the real world. To address this, we have reviewed a vast body of literature from both academic publications and social media to identify qualitative shortcomings in image generation models, which we have classified into five categories. By understanding these failures, we can identify areas where these models need improvement, as well as develop strategies for detecting deep fakes. The prevalence of deep fakes in today's society is a serious concern, and our findings can help mitigate their negative impact.
Authors: Ji Yu
Despite their superior performance, deep-learning methods often suffer from the disadvantage of needing large-scale well-annotated training data. In response, recent literature has seen a proliferation of efforts aimed at reducing the annotation burden. This paper focuses on a weakly-supervised training setting for single-cell segmentation models, where the only available training label is the rough locations of individual cells. The specific problem is of practical interest due to the widely available nuclei counter-stain data in biomedical literature, from which the cell locations can be derived programmatically. Of more general interest is a proposed self-learning method called collaborative knowledge sharing, which is related to but distinct from the more well-known consistency learning methods. This strategy achieves self-learning by sharing knowledge between a principal model and a very light-weight collaborator model. Importantly, the two models are entirely different in their architectures, capacities, and model outputs: In our case, the principal model approaches the segmentation problem from an object-detection perspective, whereas the collaborator model a sematic segmentation perspective. We assessed the effectiveness of this strategy by conducting experiments on LIVECell, a large single-cell segmentation dataset of bright-field images, and on A431 dataset, a fluorescence image dataset in which the location labels are generated automatically from nuclei counter-stain data. Implementing code is available at https://github.com/jiyuuchc/lacss
Authors: Chiranjibi Sitaula, Sumesh KC, Jagannath Aryal
Very high-resolution (VHR) remote sensing (RS) scene classification is a challenging task due to the higher inter-class similarity and intra-class variability problems. Recently, the existing deep learning (DL)-based methods have shown great promise in VHR RS scene classification. However, they still provide an unstable classification performance. To address such a problem, we, in this letter, propose a novel DL-based approach. For this, we devise an enhanced VHR attention module (EAM), followed by the atrous spatial pyramid pooling (ASPP) and global average pooling (GAP). This procedure imparts the enhanced features from the corresponding level. Then, the multi-level feature fusion is performed. Experimental results on two widely-used VHR RS datasets show that the proposed approach yields a competitive and stable/robust classification performance with the least standard deviation of 0.001. Further, the highest overall accuracies on the AID and the NWPU datasets are 95.39% and 93.04%, respectively.
Authors: Martin Brenner, Napoleon H. Reyes, Teo Susnjak, Andre L.C. Barczak
In the last decade, the computer vision field has seen significant progress in multimodal data fusion and learning, where multiple sensors, including depth, infrared, and visual, are used to capture the environment across diverse spectral ranges. Despite these advancements, there has been no systematic and comprehensive evaluation of fusing RGB-D and thermal modalities to date. While autonomous driving using LiDAR, radar, RGB, and other sensors has garnered substantial research interest, along with the fusion of RGB and depth modalities, the integration of thermal cameras and, specifically, the fusion of RGB-D and thermal data, has received comparatively less attention. This might be partly due to the limited number of publicly available datasets for such applications. This paper provides a comprehensive review of both, state-of-the-art and traditional methods used in fusing RGB-D and thermal camera data for various applications, such as site inspection, human tracking, fault detection, and others. The reviewed literature has been categorised into technical areas, such as 3D reconstruction, segmentation, object detection, available datasets, and other related topics. Following a brief introduction and an overview of the methodology, the study delves into calibration and registration techniques, then examines thermal visualisation and 3D reconstruction, before discussing the application of classic feature-based techniques as well as modern deep learning approaches. The paper concludes with a discourse on current limitations and potential future research directions. It is hoped that this survey will serve as a valuable reference for researchers looking to familiarise themselves with the latest advancements and contribute to the RGB-DT research field.
Authors: Baifeng Shi, Siyu Gai, Trevor Darrell, Xin Wang
Transfer learning involves adapting a pre-trained model to novel downstream tasks. However, we observe that current transfer learning methods often fail to focus on task-relevant features. In this work, we explore refocusing model attention for transfer learning. We introduce Top-Down Attention Steering (TOAST), a novel transfer learning algorithm that keeps the pre-trained backbone frozen, selects task-relevant features in the output, and feeds those features back to the model to steer the attention to the task-specific features. By refocusing the attention only, TOAST achieves state-of-the-art results on a number of transfer learning benchmarks, while having a small number of tunable parameters. Compared to fully fine-tuning, LoRA, and prompt tuning, TOAST substantially improves performance across a range of fine-grained visual classification datasets (e.g., 81.1% -> 86.2% on FGVC). TOAST also outperforms the fully fine-tuned Alpaca and Vicuna models on instruction-following language generation. Code is available at https://github.com/bfshi/TOAST.
Authors: Shantanu Ghosh, Ke Yu, Kayhan Batmanghelich
Building generalizable AI models is one of the primary challenges in the healthcare domain. While radiologists rely on generalizable descriptive rules of abnormality, Neural Network (NN) models suffer even with a slight shift in input distribution (e.g., scanner type). Fine-tuning a model to transfer knowledge from one domain to another requires a significant amount of labeled data in the target domain. In this paper, we develop an interpretable model that can be efficiently fine-tuned to an unseen target domain with minimal computational cost. We assume the interpretable component of NN to be approximately domain-invariant. However, interpretable models typically underperform compared to their Blackbox (BB) variants. We start with a BB in the source domain and distill it into a \emph{mixture} of shallow interpretable models using human-understandable concepts. As each interpretable model covers a subset of data, a mixture of interpretable models achieves comparable performance as BB. Further, we use the pseudo-labeling technique from semi-supervised learning (SSL) to learn the concept classifier in the target domain, followed by fine-tuning the interpretable models in the target domain. We evaluate our model using a real-life large-scale chest-X-ray (CXR) classification dataset. The code is available at: \url{https://github.com/batmanlab/MICCAI-2023-Route-interpret-repeat-CXRs}.
Authors: Zeyue Xue, Guanglu Song, Qiushan Guo, Boxiao Liu, Zhuofan Zong, Yu Liu, Ping Luo
Text-to-image generation has recently witnessed remarkable achievements. We introduce a text-conditional image diffusion model, termed RAPHAEL, to generate highly artistic images, which accurately portray the text prompts, encompassing multiple nouns, adjectives, and verbs. This is achieved by stacking tens of mixture-of-experts (MoEs) layers, i.e., space-MoE and time-MoE layers, enabling billions of diffusion paths (routes) from the network input to the output. Each path intuitively functions as a "painter" for depicting a particular textual concept onto a specified image region at a diffusion timestep. Comprehensive experiments reveal that RAPHAEL outperforms recent cutting-edge models, such as Stable Diffusion, ERNIE-ViLG 2.0, DeepFloyd, and DALL-E 2, in terms of both image quality and aesthetic appeal. Firstly, RAPHAEL exhibits superior performance in switching images across diverse styles, such as Japanese comics, realism, cyberpunk, and ink illustration. Secondly, a single model with three billion parameters, trained on 1,000 A100 GPUs for two months, achieves a state-of-the-art zero-shot FID score of 6.61 on the COCO dataset. Furthermore, RAPHAEL significantly surpasses its counterparts in human evaluation on the ViLG-300 benchmark. We believe that RAPHAEL holds the potential to propel the frontiers of image generation research in both academia and industry, paving the way for future breakthroughs in this rapidly evolving field. More details can be found on a webpage: https://miaohua.sensetime.com/en.
Authors: Xingxing Wei, Shiji Zhao
Adversarial attacks have been proven to be potential threats to Deep Neural Networks (DNNs), and many methods are proposed to defend against adversarial attacks. However, while enhancing the robustness, the clean accuracy will decline to a certain extent, implying a trade-off existed between the accuracy and robustness. In this paper, we firstly empirically find an obvious distinction between standard and robust models in the filters' weight distribution of the same architecture, and then theoretically explain this phenomenon in terms of the gradient regularization, which shows this difference is an intrinsic property for DNNs, and thus a static network architecture is difficult to improve the accuracy and robustness at the same time. Secondly, based on this observation, we propose a sample-wise dynamic network architecture named Adversarial Weight-Varied Network (AW-Net), which focuses on dealing with clean and adversarial examples with a ``divide and rule" weight strategy. The AW-Net dynamically adjusts network's weights based on regulation signals generated by an adversarial detector, which is directly influenced by the input sample. Benefiting from the dynamic network architecture, clean and adversarial examples can be processed with different network weights, which provides the potentiality to enhance the accuracy and robustness simultaneously. A series of experiments demonstrate that our AW-Net is architecture-friendly to handle both clean and adversarial examples and can achieve better trade-off performance than state-of-the-art robust models.
Authors: Mike Laszkiewicz, Jonas Ricker, Johannes Lederer, Asja Fischer
Recent groundbreaking developments on generative modeling have sparked interest in practical single-model attribution. Such methods predict whether a sample was generated by a specific generator or not, for instance, to prove intellectual property theft. However, previous works are either limited to the closed-world setting or require undesirable changes of the generative model. We address these shortcomings by proposing FLIPAD, a new approach for single-model attribution in the open-world setting based on final-layer inversion and anomaly detection. We show that the utilized final-layer inversion can be reduced to a convex lasso optimization problem, making our approach theoretically sound and computationally efficient. The theoretical findings are accompanied by an experimental study demonstrating the effectiveness of our approach, outperforming the existing methods.
Authors: Xuying Zhang, Bowen Yin, Zheng Lin, Qibin Hou, Deng-Ping Fan, Ming-Ming Cheng
We consider the problem of referring camouflaged object detection (Ref-COD), a new task that aims to segment specified camouflaged objects based on a small set of referring images with salient target objects. We first assemble a large-scale dataset, called R2C7K, which consists of 7K images covering 64 object categories in real-world scenarios. Then, we develop a simple but strong dual-branch framework, dubbed R2CNet, with a reference branch embedding the common representations of target objects from referring images and a segmentation branch identifying and segmenting camouflaged objects under the guidance of the common representations. In particular, we design a Referring Mask Generation module to generate pixel-level prior mask and a Referring Feature Enrichment module to enhance the capability of identifying specified camouflaged objects. Extensive experiments show the superiority of our Ref-COD methods over their COD counterparts in segmenting specified camouflaged objects and identifying the main body of target objects. Our code and dataset are publicly available at https://github.com/zhangxuying1004/RefCOD.
Authors: Qingbo Kang, Jun Gao, Kang Li, Qicheng Lao
Masked autoencoder (MAE) has attracted unprecedented attention and achieves remarkable performance in many vision tasks. It reconstructs random masked image patches (known as proxy task) during pretraining and learns meaningful semantic representations that can be transferred to downstream tasks. However, MAE has not been thoroughly explored in ultrasound imaging. In this work, we investigate the potential of MAE for ultrasound image recognition. Motivated by the unique property of ultrasound imaging in high noise-to-signal ratio, we propose a novel deblurring MAE approach that incorporates deblurring into the proxy task during pretraining. The addition of deblurring facilitates the pretraining to better recover the subtle details presented in the ultrasound images, thus improving the performance of the downstream classification task. Our experimental results demonstrate the effectiveness of our deblurring MAE, achieving state-of-the-art performance in ultrasound image classification. Overall, our work highlights the potential of MAE for ultrasound image recognition and presents a novel approach that incorporates deblurring to further improve its effectiveness.
Authors: Gehua Ma, Runhao Jiang, Rui Yan, Huajin Tang
Developing computational models of neural response is crucial for understanding sensory processing and neural computations. Current state-of-the-art neural network methods use temporal filters to handle temporal dependencies, resulting in an unrealistic and inflexible processing flow. Meanwhile, these methods target trial-averaged firing rates and fail to capture important features in spike trains. This work presents the temporal conditioning spiking latent variable models (TeCoS-LVM) to simulate the neural response to natural visual stimuli. We use spiking neurons to produce spike outputs that directly match the recorded trains. This approach helps to avoid losing information embedded in the original spike trains. We exclude the temporal dimension from the model parameter space and introduce a temporal conditioning operation to allow the model to adaptively explore and exploit temporal dependencies in stimuli sequences in a natural paradigm. We show that TeCoS-LVM models can produce more realistic spike activities and accurately fit spike statistics than powerful alternatives. Additionally, learned TeCoS-LVM models can generalize well to longer time scales. Overall, while remaining computationally tractable, our model effectively captures key features of neural coding systems. It thus provides a useful tool for building accurate predictive computational accounts for various sensory perception circuits.
Authors: Shiji Zhao, Xizhe Wang, Xingxing Wei
Adversarial training is a practical approach for improving the robustness of deep neural networks against adversarial attacks. Although bringing reliable robustness, the performance toward clean examples is negatively affected after adversarial training, which means a trade-off exists between accuracy and robustness. Recently, some studies have tried to use knowledge distillation methods in adversarial training, achieving competitive performance in improving the robustness but the accuracy for clean samples is still limited. In this paper, to mitigate the accuracy-robustness trade-off, we introduce the Multi-Teacher Adversarial Robustness Distillation (MTARD) to guide the model's adversarial training process by applying a strong clean teacher and a strong robust teacher to handle the clean examples and adversarial examples, respectively. During the optimization process, to ensure that different teachers show similar knowledge scales, we design the Entropy-Based Balance algorithm to adjust the teacher's temperature and keep the teachers' information entropy consistent. Besides, to ensure that the student has a relatively consistent learning speed from multiple teachers, we propose the Normalization Loss Balance algorithm to adjust the learning weights of different types of knowledge. A series of experiments conducted on public datasets demonstrate that MTARD outperforms the state-of-the-art adversarial training and distillation methods against various adversarial attacks.
Authors: Usman Muhammad, Md Ziaul Hoque, Mourad Oussalah, Jorma Laaksonen
Face presentation attacks (PA), also known as spoofing attacks, pose a substantial threat to biometric systems that rely on facial recognition systems, such as access control systems, mobile payments, and identity verification systems. To mitigate the spoofing risk, several video-based methods have been presented in the literature that analyze facial motion in successive video frames. However, estimating the motion between adjacent frames is a challenging task and requires high computational cost. In this paper, we rephrase the face anti-spoofing task as a motion prediction problem and introduce a deep ensemble learning model with a frame skipping mechanism. In particular, the proposed frame skipping adopts a uniform sampling approach by dividing the original video into video clips of fixed size. By doing so, every nth frame of the clip is selected to ensure that the temporal patterns can easily be perceived during the training of three different recurrent neural networks (RNNs). Motivated by the performance of individual RNNs, a meta-model is developed to improve the overall detection performance by combining the prediction of individual RNNs. Extensive experiments were performed on four datasets, and state-of-the-art performance is reported on MSU-MFSD (3.12%), Replay-Attack (11.19%), and OULU-NPU (12.23%) databases by using half total error rates (HTERs) in the most challenging cross-dataset testing scenario.
Authors: Mokshagna Sai Teja Karanam, Tushar Kataria, Shireen Elhabian
Statistical shape models (SSM) have been well-established as an excellent tool for identifying variations in the morphology of anatomy across the underlying population. Shape models use consistent shape representation across all the samples in a given cohort, which helps to compare shapes and identify the variations that can detect pathologies and help in formulating treatment plans. In medical imaging, computing these shape representations from CT/MRI scans requires time-intensive preprocessing operations, including but not limited to anatomy segmentation annotations, registration, and texture denoising. Deep learning models have demonstrated exceptional capabilities in learning shape representations directly from volumetric images, giving rise to highly effective and efficient Image-to-SSM. Nevertheless, these models are data-hungry and due to the limited availability of medical data, deep learning models tend to overfit. Offline data augmentation techniques, that use kernel density estimation based (KDE) methods for generating shape-augmented samples, have successfully aided Image-to-SSM networks in achieving comparable accuracy to traditional SSM methods. However, these augmentation methods focus on shape augmentation, whereas deep learning models exhibit image-based texture bias results in sub-optimal models. This paper introduces a novel strategy for on-the-fly data augmentation for the Image-to-SSM framework by leveraging data-dependent noise generation or texture augmentation. The proposed framework is trained as an adversary to the Image-to-SSM network, augmenting diverse and challenging noisy samples. Our approach achieves improved accuracy by encouraging the model to focus on the underlying geometry rather than relying solely on pixel values.
Authors: Amirhossein Askari-Farsangi, Ali Sharifi-Zarchi, Mohammad Hossein Rohban
Acute Lymphoblastic Leukemia (ALL) is one of the most common types of childhood blood cancer. The quick start of the treatment process is critical to saving the patient's life, and for this reason, early diagnosis of this disease is essential. Examining the blood smear images of these patients is one of the methods used by expert doctors to diagnose this disease. Deep learning-based methods have numerous applications in medical fields, as they have significantly advanced in recent years. ALL diagnosis is not an exception in this field, and several machine learning-based methods for this problem have been proposed. In previous methods, high diagnostic accuracy was reported, but our work showed that this alone is not sufficient, as it can lead to models taking shortcuts and not making meaningful decisions. This issue arises due to the small size of medical training datasets. To address this, we constrained our model to follow a pipeline inspired by experts' work. We also demonstrated that, since a judgement based on only one image is insufficient, redefining the problem as a multiple-instance learning problem is necessary for achieving a practical result. Our model is the first to provide a solution to this problem in a multiple-instance learning setup. We introduced a novel pipeline for diagnosing ALL that approximates the process used by hematologists, is sensitive to disease biomarkers, and achieves an accuracy of 96.15%, an F1-score of 94.24%, a sensitivity of 97.56%, and a specificity of 90.91% on ALL IDB 1. Our method was further evaluated on an out-of-distribution dataset, which posed a challenging test and had acceptable performance. Notably, our model was trained on a relatively small dataset, highlighting the potential for our approach to be applied to other medical datasets with limited data availability.
Authors: Dan Ruta, Gemma Canet Tarrés, Andrew Gilbert, Eli Shechtman, Nicholas Kolkin, John Collomosse
Neural Style Transfer (NST) is the field of study applying neural techniques to modify the artistic appearance of a content image to match the style of a reference style image. Traditionally, NST methods have focused on texture-based image edits, affecting mostly low level information and keeping most image structures the same. However, style-based deformation of the content is desirable for some styles, especially in cases where the style is abstract or the primary concept of the style is in its deformed rendition of some content. With the recent introduction of diffusion models, such as Stable Diffusion, we can access far more powerful image generation techniques, enabling new possibilities. In our work, we propose using this new class of models to perform style transfer while enabling deformable style transfer, an elusive capability in previous models. We show how leveraging the priors of these models can expose new artistic controls at inference time, and we document our findings in exploring this new direction for the field of style transfer.
Authors: Yuqi Hu, Xiangyu Zhao, Gaowei Qing, Kai Xie, Chenglei Liu, Lichi Zhang
Background: MR-based subchondral bone effectively predicts knee osteoarthritis. However, its clinical application is limited by the cost and time of MR. Purpose: We aim to develop a novel distillation-learning-based method named SRRD for subchondral bone microstructural analysis using easily-acquired CT images, which leverages paired MR images to enhance the CT-based analysis model during training. Materials and Methods: Knee joint images of both CT and MR modalities were collected from October 2020 to May 2021. Firstly, we developed a GAN-based generative model to transform MR images into CT images, which was used to establish the anatomical correspondence between the two modalities. Next, we obtained numerous patches of subchondral bone regions of MR images, together with their trabecular parameters (BV / TV, Tb. Th, Tb. Sp, Tb. N) from the corresponding CT image patches via regression. The distillation-learning technique was used to train the regression model and transfer MR structural information to the CT-based model. The regressed trabecular parameters were further used for knee osteoarthritis classification. Results: A total of 80 participants were evaluated. CT-based regression results of trabecular parameters achieved intra-class correlation coefficients (ICCs) of 0.804, 0.773, 0.711, and 0.622 for BV / TV, Tb. Th, Tb. Sp, and Tb. N, respectively. The use of distillation learning significantly improved the performance of the CT-based knee osteoarthritis classification method using the CNN approach, yielding an AUC score of 0.767 (95% CI, 0.681-0.853) instead of 0.658 (95% CI, 0.574-0.742) (p<.001). Conclusions: The proposed SRRD method showed high reliability and validity in MR-CT registration, regression, and knee osteoarthritis classification, indicating the feasibility of subchondral bone microstructural analysis based on CT images.