Misinformation has become a major challenge in the era of increasing digital information, requiring the development of effective detection methods. We have investigated a novel approach to Out-Of-Context detection (OOCD) that uses synthetic data generation. We created a dataset specifically designed for OOCD and developed an efficient detector for accurate classification. Our experimental findings validate the use of synthetic data generation and demonstrate its efficacy in addressing the data limitations associated with OOCD. The dataset and detector should serve as valuable resources for future research and the development of robust misinformation detection systems.
우리는 세밀한 초분광 토지 피복 이해를 위한 대규모 벤치마크인 HyperImageNet을 제안한다. 이 데이터셋은 224개의 스펙트럼 밴드를 갖춘 26,084개의 항공 초분광 이미지 패치와 138개의 세밀한 토지 피복 카테고리를 포함한다. 기존 데이터셋과 달리, HyperImageNet은 원본 영상, 픽셀 수준의 의미론적 라벨, 객체 수준의 인스턴스 마스크를 제공하여 의미론적 분할(semantic segmentation)과 인스턴스 분할(instance segmentation)을 모두 지원한다. 또한, 대표적인 방법들과 HyperFree 파운데이션 모델(foundation model)을 평가하기 위해 엄격한 공간 분리를 적용한 개방 환경 벤치마크를 구축한다. 실험 결과는 세밀한 초분광 이해와 개방 환경 원격 탐사 연구를 위한 HyperImageNet의 효과를 보여준다.
본 논문에서는 분수 브라운 운동(fractional Brownian motion)으로 구동되는 잔차 동역학(residual dynamics)을 갖는 분수 확률적 신경망(fractional stochastic neural network)을 개발한다. 이 신경망에 대한 이산 확률적 최대 원리(discrete stochastic maximum principle)를 도입하여 이에 대응하는 인접 재귀(adjoint recursion)를 구성한다. 결정론적(deterministic) 신경망 파라미터에 대해, 투영된 샘플별 확률적 경사하강법(projected samplewise stochastic gradient descent)의 평균제곱 수렴(mean square convergence)을 증명한다. 수치 실험에는 닫힌 형태(closed form) 수렴 테스트, 불확실성 정량화(uncertainty quantification)를 포함한 잡음이 있는 회귀(noisy regression), 장기 기억(long memory) 시간 시계열 생성, 그리고 구조화된 섭동(structured perturbation) 하에서의 이미지 분류가 포함된다. 결과는 분수 구동 항(fractional driver)이 브라운 운동 및 결정론적 기준선(baseline) 대비 장기 기억 복원 또는 강건성(robustness)을 개선하는 설정을 식별한다.
Incorporation of prior knowledge about organ shape and location is key to improve performance of image analysis approaches. In particular, priors can be useful in cases where images are corrupted and contain artefacts due to limitations in image acquisition. The highly constrained nature of anatomical objects can be well captured with learning based techniques. However, in most recent and promising techniques such as CNN based segmentation it is not obvious how to incorporate such prior knowledge. State-of-the-art methods operate as pixel-wise classifiers where the training objectives do not incorporate the structure and inter-dependencies of the output. To overcome this limitation, we propose a generic training strategy that incorporates anatomical prior knowledge into CNNs through a new regularisation model, which is trained end-to-end. The new framework encourages models to follow the global anatomical properties of the underlying anatomy (e.g. shape, label structure) via learned non-linear representations of the shape. We show that the proposed approach can be easily adapted to different analysis tasks (e.g. image enhancement, segmentation) and improve the prediction accuracy of the state-of-the-art models. The applicability of our approach is shown on multi-modal cardiac datasets and public benchmarks. Additionally, we demonstrate how the learned deep models of 3D shapes can be interpreted and used as biomarkers for classification of cardiac pathologies.
Deep neural networks (DNNs) have shown vulnerability to adversarial attacks, i.e., carefully perturbed inputs designed to mislead the network at inference time. Recently introduced localized attacks, Localized and Visible Adversarial Noise (LaVAN) and Adversarial patch, pose a new challenge to deep learning security by adding adversarial noise only within a specific region without affecting the salient objects in an image. Driven by the observation that such attacks introduce concentrated high-frequency changes at a particular image location, we have developed an effective method to estimate noise location in gradient domain and transform those high activation regions caused by adversarial noise in image domain while having minimal effect on the salient object that is important for correct classification. Our proposed Local Gradients Smoothing (LGS) scheme achieves this by regularizing gradients in the estimated noisy region before feeding the image to DNN for inference. We have shown the effectiveness of our method in comparison to other defense methods including Digital Watermarking, JPEG compression, Total Variance Minimization (TVM) and Feature squeezing on ImageNet dataset. In addition, we systematically study the robustness of the proposed defense mechanism against Back Pass Differentiable Approximation (BPDA), a state of the art attack recently developed to break defenses that transform an input sample to minimize the adversarial effect. Compared to other defense mechanisms, LGS is by far the most resistant to BPDA in localized adversarial attack setting.
The burgeoning field of camouflaged object detection (COD) seeks to identify objects that blend into their surroundings. Despite the impressive performance of recent models, we have identified a limitation in their robustness, where existing methods may misclassify salient objects as camouflaged ones, despite these two characteristics being contradictory. This limitation may stem from lacking multi-pattern training images, leading to less saliency robustness. To address this issue, we introduce CamDiff, a novel approach inspired by AI-Generated Content (AIGC) that overcomes the scarcity of multi-pattern training images. Specifically, we leverage the latent diffusion model to synthesize salient objects in camouflaged scenes, while using the zero-shot image classification ability of the Contrastive Language-Image Pre-training (CLIP) model to prevent synthesis failures and ensure the synthesized object aligns with the input prompt. Consequently, the synthesized image retains its original camouflage label while incorporating salient objects, yielding camouflage samples with richer characteristics. The results of user studies show that the salient objects in the scenes synthesized by our framework attract the user's attention more; thus, such samples pose a greater challenge to the existing COD models. Our approach enables flexible editing and efficient large-scale dataset generation at a low cost. It significantly enhances COD baselines' training and testing phases, emphasizing robustness across diverse domains. Our newly-generated datasets and source code are available at https://github.com/drlxj/CamDiff.
Contrastive Language-Image Pre-training (CLIP), which excels at abstracting open-world representations across domains and modalities, has become a foundation for a variety of vision and multimodal tasks. However, recent studies reveal that CLIP has severe visual shortcomings, such as which can hardly distinguish orientation, quantity, color, structure, etc. These visual shortcomings also limit the perception capabilities of multimodal large language models (MLLMs) built on CLIP. The main reason could be that the image-text pairs used to train CLIP are inherently biased, due to the lack of the distinctiveness of the text and the diversity of images. In this work, we present a simple post-training approach for CLIP models, which largely overcomes its visual shortcomings via a self-supervised diffusion process. We introduce DIVA, which uses the DIffusion model as a Visual Assistant for CLIP. Specifically, DIVA leverages generative feedback from text-to-image diffusion models to optimize CLIP representations, with only images (without corresponding text). We demonstrate that DIVA improves CLIP's performance on the challenging MMVP-VLM benchmark which assesses fine-grained visual abilities to a large extent (e.g., 3-7%), and enhances the performance of MLLMs and vision models on multimodal understanding and segmentation tasks. Extensive evaluation on 29 image classification and retrieval benchmarks confirms that our framework preserves CLIP's strong zero-shot capabilities. The code is available at https://github.com/baaivision/DIVA.
In this study, a multi-task deep neural network is proposed for skin lesion analysis. The proposed multi-task learning model solves different tasks (e.g., lesion segmentation and two independent binary lesion classifications) at the same time by exploiting commonalities and differences across tasks. This results in improved learning efficiency and potential prediction accuracy for the task-specific models, when compared to training the individual models separately. The proposed multi-task deep learning model is trained and evaluated on the dermoscopic image sets from the International Skin Imaging Collaboration (ISIC) 2017 Challenge - Skin Lesion Analysis towards Melanoma Detection, which consists of 2000 training samples and 150 evaluation samples. The experimental results show that the proposed multi-task deep learning model achieves promising performances on skin lesion segmentation and classification. The average value of Jaccard index for lesion segmentation is 0.724, while the average values of area under the receiver operating characteristic curve (AUC) on two individual lesion classifications are 0.880 and 0.972, respectively.
Global pooling is one of the most significant operations in many machine learning models and tasks, whose implementation, however, is often empirical in practice. In this study, we develop a novel and solid global pooling framework through the lens of optimal transport. We demonstrate that most existing global pooling methods are equivalent to solving some specializations of an unbalanced optimal transport (UOT) problem. Making the parameters of the UOT problem learnable, we unify various global pooling methods in the same framework, and accordingly, propose a generalized global pooling layer called UOT-Pooling (UOTP) for neural networks. Besides implementing the UOTP layer based on the classic Sinkhorn-scaling algorithm, we design a new model architecture based on the Bregman ADMM algorithm, which has better numerical stability and can reproduce existing pooling layers more effectively. We test our UOTP layers in several application scenarios, including multi-instance learning, graph classification, and image classification. Our UOTP layers can either imitate conventional global pooling layers or learn some new pooling mechanisms leading to better performance.
A number of approaches have dealt with statistical assessment of self-similarity, and many of those are based on multiscale concepts. Most rely on certain distributional assumptions which are usually violated by real data traces, often characterized by large temporal or spatial mean level shifts, missing values or extreme observations. A novel, robust approach based on Theil-type weighted regression is proposed for estimating self-similarity in two-dimensional data (images). The method is compared to two traditional estimation techniques that use wavelet decompositions; ordinary least squares (OLS) and Abry-Veitch bias correcting estimator (AV). As an application, the suitability of the self-similarity estimate resulting from the the robust approach is illustrated as a predictive feature in the classification of digitized mammogram images as cancerous or non-cancerous. The diagnostic employed here is based on the properties of image backgrounds, which is typically an unused modality in breast cancer screening. Classification results show nearly 68% accuracy, varying slightly with the choice of wavelet basis, and the range of multiresolution levels used.
The remarkable success of deep learning has prompted interest in its application to medical imaging diagnosis. Even though state-of-the-art deep learning models have achieved human-level accuracy on the classification of different types of medical data, these models are hardly adopted in clinical workflows, mainly due to their lack of interpretability. The black-box-ness of deep learning models has raised the need for devising strategies to explain the decision process of these models, leading to the creation of the topic of eXplainable Artificial Intelligence (XAI). In this context, we provide a thorough survey of XAI applied to medical imaging diagnosis, including visual, textual, example-based and concept-based explanation methods. Moreover, this work reviews the existing medical imaging datasets and the existing metrics for evaluating the quality of the explanations. In addition, we include a performance comparison among a set of report generation-based methods. Finally, the major challenges in applying XAI to medical imaging and the future research directions on the topic are also discussed.
This work presents a new method for unsupervised thermal image classification and semantic segmentation by transferring knowledge from the RGB domain using a multi-domain attention network. Our method does not require any thermal annotations or co-registered RGB-thermal pairs, enabling robots to perform visual tasks at night and in adverse weather conditions without incurring additional costs of data labeling and registration. Current unsupervised domain adaptation methods look to align global images or features across domains. However, when the domain shift is significantly larger for cross-modal data, not all features can be transferred. We solve this problem by using a shared backbone network that promotes generalization, and domain-specific attention that reduces negative transfer by attending to domain-invariant and easily-transferable features. Our approach outperforms the state-of-the-art RGB-to-thermal adaptation method in classification benchmarks, and is successfully applied to thermal river scene segmentation using only synthetic RGB images. Our code is made publicly available at https://github.com/ganlumomo/thermal-uda-attention.
Current deep learning classifiers, carry out supervised learning and store class discriminatory information in a set of shared network weights. These weights cannot be easily altered to incrementally learn additional classes, since the classification weights all require retraining to prevent old class information from being lost and also require the previous training data to be present. We present a novel two stage architecture which couples visual feature learning with probabilistic models to represent each class in the form of a Gaussian Mixture Model. By using these independent class representations within our classifier, we outperform a benchmark of an equivalent network with a Softmax head, obtaining increased accuracy for sample sizes smaller than 12 and increased weighted F1 score for 3 imbalanced class profiles in that sample range. When learning new classes our classifier exhibits no catastrophic forgetting issues and only requires the new classes' training images to be present. This enables a database of growing classes over time which can be visually indexed and reasoned over.
Integrating deep learning with clinical expertise holds great potential for addressing healthcare challenges and empowering medical professionals with improved diagnostic tools. However, the need for annotated medical images is often an obstacle to leveraging the full power of machine learning models. Our research demonstrates that by combining synthetic images, generated using diffusion models, with real images, we can enhance nonalcoholic fatty liver disease (NAFLD) classification performance even in low-data regime settings. We evaluate the quality of the synthetic images by comparing two metrics: Inception Score (IS) and Fr\'{e}chet Inception Distance (FID), computed on diffusion- and generative adversarial network (GAN)-generated images. Our results show superior performance for the diffusion-generated images, with a maximum IS score of $1.90$ compared to $1.67$ for GANs, and a minimum FID score of $69.45$ compared to $100.05$ for GANs. Utilizing a partially frozen CNN backbone (EfficientNet v1), our synthetic augmentation method achieves a maximum image-level ROC AUC of $0.904$ on a NAFLD prediction task.
This paper addresses the critical issue of deforestation by exploring the application of vision transformers (ViTs) for classifying the drivers of deforestation using satellite imagery from Indonesian forests. Motivated by the urgency of this problem, I propose an approach that leverages ViTs and machine learning techniques. The input to my algorithm is a 332x332-pixel satellite image, and I employ a ViT architecture to predict the deforestation driver class; grassland shrubland, other, plantation, or smallholder agriculture. My methodology involves fine-tuning a pre-trained ViT on a dataset from the Stanford ML Group, and I experiment with rotational data augmentation techniques (among others) and embedding of longitudinal data to improve classification accuracy. I also tried training a ViT from scratch. Results indicate a significant improvement over baseline models, achieving a test accuracy of 72.9%. I conduct a comprehensive analysis, including error patterns and metrics, to highlight the strengths and limitations of my approach. This research contributes to the ongoing efforts to address deforestation challenges through advanced computer vision techniques.
We introduce SLIMP (Skin Lesion Image-Metadata Pre-training) for learning rich representations of skin lesions through a novel nested contrastive learning approach that captures complex relationships between images and metadata. Melanoma detection and skin lesion classification based solely on images, pose significant challenges due to large variations in imaging conditions (lighting, color, resolution, distance, etc.) and lack of clinical and phenotypical context. Clinicians typically follow a holistic approach for assessing the risk level of the patient and for deciding which lesions may be malignant and need to be excised, by considering the patient's medical history as well as the appearance of other lesions of the patient. Inspired by this, SLIMP combines the appearance and the metadata of individual skin lesions with patient-level metadata relating to their medical record and other clinically relevant information. By fully exploiting all available data modalities throughout the learning process, the proposed pre-training strategy improves performance compared to other pre-training strategies on downstream skin lesions classification tasks highlighting the learned representations quality.
In the last two decades Computer Aided Diagnostics (CAD) systems were developed to help radiologists analyze screening mammograms. The benefits of current CAD technologies appear to be contradictory and they should be improved to be ultimately considered useful. Since 2012 deep convolutional neural networks (CNN) have been a tremendous success in image recognition, reaching human performance. These methods have greatly surpassed the traditional approaches, which are similar to currently used CAD solutions. Deep CNN-s have the potential to revolutionize medical image analysis. We propose a CAD system based on one of the most successful object detection frameworks, Faster R-CNN. The system detects and classifies malignant or benign lesions on a mammogram without any human intervention. The proposed method sets the state of the art classification performance on the public INbreast database, AUC = 0.95 . The approach described here has achieved the 2nd place in the Digital Mammography DREAM Challenge with AUC = 0.85 . When used as a detector, the system reaches high sensitivity with very few false positive marks per image on the INbreast dataset. Source code, the trained model and an OsiriX plugin are availaible online at https://github.com/riblidezso/frcnn_cad .
Accurate estimation of heading date of paddy rice greatly helps the breeders to understand the adaptability of different crop varieties in a given location. The heading date also plays a vital role in determining grain yield for research experiments. Visual examination of the crop is laborious and time consuming. Therefore, quick and precise estimation of heading date of paddy rice is highly essential. In this work, we propose a simple pipeline to detect regions containing flowering panicles from ground level RGB images of paddy rice. Given a fixed region size for an image, the number of regions containing flowering panicles is directly proportional to the number of flowering panicles present. Consequently, we use the flowering panicle region counts to estimate the heading date of the crop. The method is based on image classification using Convolutional Neural Networks (CNNs). We evaluated the performance of our algorithm on five time series image sequences of three different varieties of rice crops. When compared to the previous work on this dataset, the accuracy and general versatility of the method has been improved and heading date has been estimated with a mean absolute error of less than 1 day.
High-resolution and variable-shape images have not yet been properly addressed by the AI community. The approach of down-sampling data often used with convolutional neural networks is sub-optimal for many tasks, and has too many drawbacks to be considered a sustainable alternative. In sight of the increasing importance of problems that can benefit from exploiting high-resolution (HR) and variable-shape, and with the goal of promoting research in that direction, we introduce a new family of datasets (MetH). The four proposed problems include two image classification, one image regression and one super resolution task. Each of these datasets contains thousands of art pieces captured by HR and variable-shape images, labeled by experts at the Metropolitan Museum of Art. We perform an analysis, which shows how the proposed tasks go well beyond current public alternatives in both pixel size and aspect ratio variance. At the same time, the performance obtained by popular architectures on these tasks shows that there is ample room for improvement. To wrap up the relevance of the contribution we review the fields, both in AI and high-performance computing, that could benefit from the proposed challenges.
Segmenting histology images into diagnostically relevant regions is imperative to support timely and reliable decisions by pathologists. To this end, computer-aided techniques have been proposed to delineate relevant regions in scanned histology slides. However, the techniques necessitate task-specific large datasets of annotated pixels, which is tedious, time-consuming, expensive, and infeasible to acquire for many histology tasks. Thus, weakly-supervised semantic segmentation techniques are proposed to utilize weak supervision that is cheaper and quicker to acquire. In this paper, we propose SegGini, a weakly supervised segmentation method using graphs, that can utilize weak multiplex annotations, i.e. inexact and incomplete annotations, to segment arbitrary and large images, scaling from tissue microarray (TMA) to whole slide image (WSI). Formally, SegGini constructs a tissue-graph representation for an input histology image, where the graph nodes depict tissue regions. Then, it performs weakly-supervised segmentation via node classification by using inexact image-level labels, incomplete scribbles, or both. We evaluated SegGini on two public prostate cancer datasets containing TMAs and WSIs. Our method achieved state-of-the-art segmentation performance on both datasets for various annotation settings while being comparable to a pathologist baseline.