Current deep models provide remarkable object detection in terms of object classification and localization. However, estimating object rotation with respect to other visual objects in the visual context of an input image still lacks deep studies due to the unavailability of object datasets with rotation annotations. This paper tackles these two challenges to solve the rotation estimation of a parked bike with respect to its parking area. First, we leverage the power of 3D graphics to build a camera-agnostic well-annotated Synthetic Bike Rotation Dataset (SynthBRSet). Then, we propose an object-to-spot rotation estimator (OSRE) by extending the object detection task to further regress the bike rotations in two axes. Since our model is purely trained on synthetic data, we adopt image smoothing techniques when deploying it on real-world images. The proposed OSRE is evaluated on synthetic and real-world data providing promising results. Our data and code are available at \href{https://github.com/saghiralfasly/OSRE-Project}{https://github.com/saghiralfasly/OSRE-Project}.
In this study, we demonstrate the application of a hybrid Vision Transformer (ViT) model, pretrained on ImageNet, on an electroencephalogram (EEG) regression task. Despite being originally trained for image classification tasks, when fine-tuned on EEG data, this model shows a notable increase in performance compared to other models, including an identical architecture ViT trained without the ImageNet weights. This discovery challenges the traditional understanding of model generalization, suggesting that Transformer models pretrained on seemingly unrelated image data can provide valuable priors for EEG regression tasks with an appropriate fine-tuning pipeline. The success of this approach suggests that the features extracted by ViT models in the context of visual tasks can be readily transformed for the purpose of EEG predictive modeling. We recommend utilizing this methodology not only in neuroscience and related fields, but generally for any task where data collection is limited by practical, financial, or ethical constraints. Our results illuminate the potential of pretrained models on tasks that are clearly distinct from their original purpose.
Instruction-tuned large language models (LLMs) have demonstrated promising zero-shot generalization capabilities across various downstream tasks. Recent research has introduced multimodal capabilities to LLMs by integrating independently pretrained vision encoders through model grafting. These multimodal variants undergo instruction tuning, similar to LLMs, enabling effective zero-shot generalization for multimodal tasks. This study conducts a comparative analysis of different multimodal instruction tuning approaches and evaluates their performance across a range of tasks, including complex reasoning, conversation, image captioning, multiple-choice questions (MCQs), and binary classification. Through rigorous benchmarking and ablation experiments, we reveal key insights for guiding architectural choices when incorporating multimodal capabilities into LLMs. However, current approaches have limitations; they do not sufficiently address the need for a diverse multimodal instruction dataset, which is crucial for enhancing task generalization. Additionally, they overlook issues related to truthfulness and factuality when generating responses. These findings illuminate current methodological constraints in adapting language models for image comprehension and provide valuable guidance for researchers and practitioners seeking to harness multimodal versions of LLMs.
Medical report generation from X-ray images is a challenging task, particularly in an unpaired setting where paired image-report data is unavailable for training. To address this challenge, we propose a novel model that leverages the available information in two distinct datasets, one comprising reports and the other consisting of images. The core idea of our model revolves around the notion that combining auto-encoding report generation with multi-modal (report-image) alignment can offer a solution. However, the challenge persists regarding how to achieve this alignment when pair correspondence is absent. Our proposed solution involves the use of auxiliary tasks, particularly contrastive learning and classification, to position related images and reports in close proximity to each other. This approach differs from previous methods that rely on pre-processing steps, such as using external information stored in a knowledge graph. Our model, named MedRAT, surpasses previous state-of-the-art methods, demonstrating the feasibility of generating comprehensive medical reports without the need for paired data or external tools.
Self-Attention Mechanism (SAM) is good at capturing the internal connections of features and greatly improves the performance of machine learning models, espeacially requiring efficient characterization and feature extraction of high-dimensional data. A novel Quantum Self-Attention Network (QSAN) is proposed for image classification tasks on near-term quantum devices. First, a Quantum Self-Attention Mechanism (QSAM) including Quantum Logic Similarity (QLS) and Quantum Bit Self-Attention Score Matrix (QBSASM) is explored as the theoretical basis of QSAN to enhance the data representation of SAM. QLS is employed to prevent measurements from obtaining inner products to allow QSAN to be fully implemented on quantum computers, and QBSASM as a result of the evolution of QSAN to produce a density matrix that effectively reflects the attention distribution of the output. Then, the framework for one-step realization and quantum circuits of QSAN are designed for fully considering the compression of the measurement times to acquire QBSASM in the intermediate process, in which a quantum coordinate prototype is introduced as well in the quantum circuit for describing the mathematical relation between the output and control bits to facilitate programming. Ultimately, the method comparision and binary classification experiments on MNIST with the pennylane platform demonstrate that QSAN converges about 1.7x and 2.3x faster than hardware-efficient ansatz and QAOA ansatz respevtively with similar parameter configurations and 100% prediction accuracy, which indicates it has a better learning capability. QSAN is quite suitable for fast and in-depth analysis of the primary and secondary relationships of image and other data, which has great potential for applications of quantum computer vision from the perspective of enhancing the information extraction ability of models.
The fusion of vision and language has brought about a transformative shift in computer vision through the emergence of Vision-Language Models (VLMs). However, the resource-intensive nature of existing VLMs poses a significant challenge. We need an accessible method for developing the next generation of VLMs. To address this issue, we propose Zoom-shot, a novel method for transferring the zero-shot capabilities of CLIP to any pre-trained vision encoder. We do this by exploiting the multimodal information (i.e. text and image) present in the CLIP latent space through the use of specifically designed multimodal loss functions. These loss functions are (1) cycle-consistency loss and (2) our novel prompt-guided knowledge distillation loss (PG-KD). PG-KD combines the concept of knowledge distillation with CLIP's zero-shot classification, to capture the interactions between text and image features. With our multimodal losses, we train a $\textbf{linear mapping}$ between the CLIP latent space and the latent space of a pre-trained vision encoder, for only a $\textbf{single epoch}$. Furthermore, Zoom-shot is entirely unsupervised and is trained using $\textbf{unpaired}$ data. We test the zero-shot capabilities of a range of vision encoders augmented as new VLMs, on coarse and fine-grained classification datasets, outperforming the previous state-of-the-art in this problem domain. In our ablations, we find Zoom-shot allows for a trade-off between data and compute during training; and our state-of-the-art results can be obtained by reducing training from 20% to 1% of the ImageNet training data with 20 epochs. All code and models are available on GitHub.
Distracted driving is a critical safety issue that leads to numerous fatalities and injuries worldwide. This study addresses the urgent need for efficient and real-time machine learning models to detect distracted driving behaviors. Leveraging the Pretrained YOLOv8 (P-YOLOv8) model, a real-time object detection system is introduced, optimized for both speed and accuracy. This approach addresses the computational constraints and latency limitations commonly associated with conventional detection models. The study demonstrates P-YOLOv8 versatility in both object detection and image classification tasks using the Distracted Driver Detection dataset from State Farm, which includes 22,424 images across ten behavior categories. Our research explores the application of P-YOLOv8 for image classification, evaluating its performance compared to deep learning models such as VGG16, VGG19, and ResNet. Some traditional models often struggle with low accuracy, while others achieve high accuracy but come with high computational costs and slow detection speeds, making them unsuitable for real-time applications. P-YOLOv8 addresses these issues by achieving competitive accuracy with significant computational cost and efficiency advantages. In particular, P-YOLOv8 generates a lightweight model with a size of only 2.84 MB and a lower number of parameters, totaling 1,451,098, due to its innovative architecture. It achieves a high accuracy of 99.46 percent with this small model size, opening new directions for deployment on inexpensive and small embedded devices using Tiny Machine Learning (TinyML). The experimental results show robust performance, making P-YOLOv8 a cost-effective solution for real-time deployment. This study provides a detailed analysis of P-YOLOv8's architecture, training, and performance benchmarks, highlighting its potential for real-time use in detecting distracted driving.
3D engineering of matter has opened up new avenues for designing systems that can perform various computational tasks through light-matter interaction. Here, we demonstrate the design of optical networks in the form of multiple diffractive layers that are trained using deep learning to transform and encode the spatial information of objects into the power spectrum of the diffracted light, which are used to perform optical classification of objects with a single-pixel spectroscopic detector. Using a time-domain spectroscopy setup with a plasmonic nanoantenna-based detector, we experimentally validated this machine vision framework at terahertz spectrum to optically classify the images of handwritten digits by detecting the spectral power of the diffracted light at ten distinct wavelengths, each representing one class/digit. We also report the coupling of this spectral encoding achieved through a diffractive optical network with a shallow electronic neural network, separately trained to reconstruct the images of handwritten digits based on solely the spectral information encoded in these ten distinct wavelengths within the diffracted light. These reconstructed images demonstrate task-specific image decompression and can also be cycled back as new inputs to the same diffractive network to improve its optical object classification. This unique machine vision framework merges the power of deep learning with the spatial and spectral processing capabilities of diffractive networks, and can also be extended to other spectral-domain measurement systems to enable new 3D imaging and sensing modalities integrated with spectrally encoded classification tasks performed through diffractive optical networks.
Defects are unavoidable in casting production owing to the complexity of the casting process. While conventional human-visual inspection of casting products is slow and unproductive in mass productions, an automatic and reliable defect detection not just enhances the quality control process but positively improves productivity. However, casting defect detection is a challenging task due to diversity and variation in defects' appearance. Convolutional neural networks (CNNs) have been widely applied in both image classification and defect detection tasks. Howbeit, CNNs with frequentist inference require a massive amount of data to train on and still fall short in reporting beneficial estimates of their predictive uncertainty. Accordingly, leveraging the transfer learning paradigm, we first apply four powerful CNN-based models (VGG16, ResNet50, DenseNet121, and InceptionResNetV2) on a small dataset to extract meaningful features. Extracted features are then processed by various machine learning algorithms to perform the classification task. Simulation results demonstrate that linear support vector machine (SVM) and multi-layer perceptron (MLP) show the finest performance in defect detection of casting images. Secondly, to achieve a reliable classification and to measure epistemic uncertainty, we employ an uncertainty quantification (UQ) technique (ensemble of MLP models) using features extracted from four pre-trained CNNs. UQ confusion matrix and uncertainty accuracy metric are also utilized to evaluate the predictive uncertainty estimates. Comprehensive comparisons reveal that UQ method based on VGG16 outperforms others to fetch uncertainty. We believe an uncertainty-aware automatic defect detection solution will reinforce casting productions quality assurance.
Visual question answering (VQA) in surgery is largely unexplored. Expert surgeons are scarce and are often overloaded with clinical and academic workloads. This overload often limits their time answering questionnaires from patients, medical students or junior residents related to surgical procedures. At times, students and junior residents also refrain from asking too many questions during classes to reduce disruption. While computer-aided simulators and recording of past surgical procedures have been made available for them to observe and improve their skills, they still hugely rely on medical experts to answer their questions. Having a Surgical-VQA system as a reliable 'second opinion' could act as a backup and ease the load on the medical experts in answering these questions. The lack of annotated medical data and the presence of domain-specific terms has limited the exploration of VQA for surgical procedures. In this work, we design a Surgical-VQA task that answers questionnaires on surgical procedures based on the surgical scene. Extending the MICCAI endoscopic vision challenge 2018 dataset and workflow recognition dataset further, we introduce two Surgical-VQA datasets with classification and sentence-based answers. To perform Surgical-VQA, we employ vision-text transformers models. We further introduce a residual MLP-based VisualBert encoder model that enforces interaction between visual and text tokens, improving performance in classification-based answering. Furthermore, we study the influence of the number of input image patches and temporal visual features on the model performance in both classification and sentence-based answering.
Time series data has been demonstrated to be crucial in various research fields. The management of large quantities of time series data presents challenges in terms of deep learning tasks, particularly for training a deep neural network. Recently, a technique named \textit{Dataset Condensation} has emerged as a solution to this problem. This technique generates a smaller synthetic dataset that has comparable performance to the full real dataset in downstream tasks such as classification. However, previous methods are primarily designed for image and graph datasets, and directly adapting them to the time series dataset leads to suboptimal performance due to their inability to effectively leverage the rich information inherent in time series data, particularly in the frequency domain. In this paper, we propose a novel framework named Dataset \textit{\textbf{Cond}}ensation for \textit{\textbf{T}}ime \textit{\textbf{S}}eries \textit{\textbf{C}}lassification via Dual Domain Matching (\textbf{CondTSC}) which focuses on the time series classification dataset condensation task. Different from previous methods, our proposed framework aims to generate a condensed dataset that matches the surrogate objectives in both the time and frequency domains. Specifically, CondTSC incorporates multi-view data augmentation, dual domain training, and dual surrogate objectives to enhance the dataset condensation process in the time and frequency domains. Through extensive experiments, we demonstrate the effectiveness of our proposed framework, which outperforms other baselines and learns a condensed synthetic dataset that exhibits desirable characteristics such as conforming to the distribution of the original data.
Object detection in unmanned aerial vehicle (UAV) remote sensing images poses significant challenges due to unstable image quality, small object sizes, complex backgrounds, and environmental occlusions. Small objects, in particular, occupy small portions of images, making their accurate detection highly difficult. Existing multi-scale feature fusion methods address these challenges to some extent by aggregating features across different resolutions. However, they often fail to effectively balance the classification and localization performance for small objects, primarily due to insufficient feature representation and imbalanced network information flow. In this paper, we propose a novel feature fusion framework specifically designed for UAV object detection tasks to enhance both localization accuracy and classification performance. The proposed framework integrates hybrid upsampling and downsampling modules, enabling feature maps from different network depths to be flexibly adjusted to arbitrary resolutions. This design facilitates cross-layer connections and multi-scale feature fusion, ensuring improved representation of small objects. Our approach leverages hybrid downsampling to enhance fine-grained feature representation, improving spatial localization of small targets, even under complex conditions. Simultaneously, the upsampling module aggregates global contextual information, optimizing feature consistency across scales and enhancing classification robustness in cluttered scenes. Experimental results on two public UAV datasets demonstrate the effectiveness of the proposed framework. Integrated into the YOLO-v10 model, our method achieves a 2% improvement in average precision (AP) compared to the baseline YOLO-v10 model, while maintaining the same number of parameters. These results highlight the potential of our framework for accurate and efficient UAV object detection.
We propose a deep clustering architecture alongside image segmentation for medical image analysis. The main idea is based on unsupervised learning to cluster images on severity of the disease in the subject's sample, and this image is then segmented to highlight and outline regions of interest. We start with training an autoencoder on the images for segmentation. The encoder part from the autoencoder branches out to a clustering node and segmentation node. Deep clustering using Kmeans clustering is performed at the clustering branch and a lightweight model is used for segmentation. Each of the branches use extracted features from the autoencoder. We demonstrate our results on ISIC 2018 Skin Lesion Analysis Towards Melanoma Detection and Cityscapes datasets for segmentation and clustering. The proposed architecture beats UNet and DeepLab results on the two datasets, and has less than half the number of parameters. We use the deep clustering branch for clustering images into four clusters. Our approach can be applied to work with high complexity datasets of medical imaging for analyzing survival prediction for severe diseases or customizing treatment based on how far the disease has propagated. Clustering patients can help understand how binning should be done on real valued features to reduce feature sparsity and improve accuracy on classification tasks. The proposed architecture can provide an early diagnosis and reduce human intervention on labeling as it can become quite costly as the datasets grow larger. The main idea is to propose a one shot approach to segmentation with deep clustering.
With the popularization of AI solutions for image based problems, there has been a growing concern for both data privacy and acquisition. In a large number of cases, information is located on separate data silos and it can be difficult for a developer to consolidate all of it in a fashion that is appropriate for machine learning model development. Alongside this, a portion of these localized data regions may not have access to a labelled ground truth. This indicates that they have the capacity to reach conclusions numerically, but are not able to assign classifications amid a lack of pertinent information. Such a determination is often negligible, especially when attempting to develop image based solutions that often necessitate this capability. With this being the case, we propose an innovative vertical federated learning (VFL) model architecture that can operate under this common set of conditions. This is the first (and currently the only) implementation of a system that can work under the constraints of a VFL environment and perform image segmentation while maintaining nominal accuracies. We achieved this by utilizing an FCN that boasts the ability to operate on federates that lack labelled data and privately share the respective weights with a central server, that of which hosts the necessary features for classification. Tests were conducted on the CamVid dataset in order to determine the impact of heavy feature compression required for the transfer of information between federates, as well as to reach nominal conclusions about the overall performance metrics when working under such constraints.
Recent advancements in medical image analysis have predominantly relied on Convolutional Neural Networks (CNNs), achieving impressive performance in chest X-ray classification tasks, such as the 92% AUC reported by AutoThorax-Net and the 88% AUC achieved by ChexNet in classifcation tasks. However, in the medical field, even small improvements in accuracy can have significant clinical implications. This study explores the application of Vision Transformers (ViT), a state-of-the-art architecture in machine learning, to chest X-ray analysis, aiming to push the boundaries of diagnostic accuracy. I present a comparative analysis of two ViT-based approaches: one utilizing full chest X-ray images and another focusing on segmented lung regions. Experiments demonstrate that both methods surpass the performance of traditional CNN-based models, with the full-image ViT achieving up to 97.83% accuracy and the lung-segmented ViT reaching 96.58% accuracy in classifcation of diseases on three label and AUC of 94.54% when label numbers are increased to eight. Notably, the full-image approach showed superior performance across all metrics, including precision, recall, F1 score, and AUC-ROC. These findings suggest that Vision Transformers can effectively capture relevant features from chest X-rays without the need for explicit lung segmentation, potentially simplifying the preprocessing pipeline while maintaining high accuracy. This research contributes to the growing body of evidence supporting the efficacy of transformer-based architectures in medical image analysis and highlights their potential to enhance diagnostic precision in clinical settings.
세분화된 시각적 표현(fine-grained visual representation)은 특히 진단과 관련된 단서가 미세하고 공간적으로 국소화되어 있을 때 의료 영상 분석에 필수적입니다. 따라서 최신 트랜스포머(transformer) 기반 의료 비전 인코더는 임상적으로 유의미하면서도 공간적으로 일관된 패치 수준 표현을 학습해야 합니다. 이러한 특성이 결여될 경우, 대규모 비전-언어 모델(LVLM)은 모호한 시각적 기반 위에서 동작하게 되어 임상적으로 신뢰할 수 있고 공간적으로 그라운딩(grounding)된 응답을 생성하는 능력이 제한됩니다. 그러나 의료 비전 인코더를 위한 기존 학습(training) 전략은 두 가지 목표를 동시에 달성하는 경우가 드뭅니다. 이미지-텍스트 정렬은 주로 이미지 수준에서 임상적으로 유의미한 지도(supervision)를 제공하므로, 진단 단서의 공간적 국소화에 대한 제약이 약하게 남습니다. 반면, 자기지도학습(self-supervised learning)은 공간적 일관성을 촉진하지만, 시각적으로 유사하면서도 임상적으로는 상이한 영역을 구별하는 데 필요한 의미론적 지도가 부족합니다. 이러한 간극을 해결하기 위해, 위치 인식 세분화 표현 학습을 기반으로 구축된 의료 비전 파운데이션 모델인 LoFi를 제시합니다. LoFi는 그라운딩 및 그라운디드 캡셔닝(grounded captioning) 목표 하에서 경량 대규모 언어 모델(LLM)과 함께 비전 인코더를 학습시킵니다. 이러한 목표는 임상 텍스트로부터 위치를 예측하거나 그 반대의 과정을 요구하기 때문에, 명시적인 패치 수준 정규화(regularization) 없이도 공간적 일관성이 자연스럽게 발현됩니다. 대규모 학습을 가능하게 하기 위해, 7개 양상(modality)에 걸친 84개 데이터셋(dataset)에서 큐레이션한 448만 개의 이미지-텍스트-박스 삼중쌍으로 구성된 대규모 의료 그라운딩 데이터셋인 MedG를 구축했습니다. 구문 그라운딩(phrase grounding), 시각적 질의응답(VQA), 섭동 하의 영역 기반 장기 분류(classification) 전반에 걸쳐, LoFi는 범용 및 의료 비전 파운데이션 모델뿐만 아니라 최신 최고 성능의 LVLM을 일관되게 능가합니다. 코드는 https://github.com/myeongkyunkang/lofi-medg 에서 확인할 수 있습니다.
Visual patterns represent the discernible regularity in the visual world. They capture the essential nature of visual objects or scenes. Understanding and modeling visual patterns is a fundamental problem in visual recognition that has wide ranging applications. In this paper, we study the problem of visual pattern mining and propose a novel deep neural network architecture called PatternNet for discovering these patterns that are both discriminative and representative. The proposed PatternNet leverages the filters in the last convolution layer of a convolutional neural network to find locally consistent visual patches, and by combining these filters we can effectively discover unique visual patterns. In addition, PatternNet can discover visual patterns efficiently without performing expensive image patch sampling, and this advantage provides an order of magnitude speedup compared to most other approaches. We evaluate the proposed PatternNet subjectively by showing randomly selected visual patterns which are discovered by our method and quantitatively by performing image classification with the identified visual patterns and comparing our performance with the current state-of-the-art. We also directly evaluate the quality of the discovered visual patterns by leveraging the identified patterns as proposed objects in an image and compare with other relevant methods. Our proposed network and procedure, PatterNet, is able to outperform competing methods for the tasks described.
Single-sample face recognition is one of the most challenging problems in face recognition. We propose a novel algorithm to address this problem based on a sparse representation based classification (SRC) framework. The new algorithm is robust to image misalignment and pixel corruption, and is able to reduce required gallery images to one sample per class. To compensate for the missing illumination information traditionally provided by multiple gallery images, a sparse illumination learning and transfer (SILT) technique is introduced. The illumination in SILT is learned by fitting illumination examples of auxiliary face images from one or more additional subjects with a sparsely-used illumination dictionary. By enforcing a sparse representation of the query image in the illumination dictionary, the SILT can effectively recover and transfer the illumination and pose information from the alignment stage to the recognition stage. Our extensive experiments have demonstrated that the new algorithms significantly outperform the state of the art in the single-sample regime and with less restrictions. In particular, the single-sample face alignment accuracy is comparable to that of the well-known Deformable SRC algorithm using multiple gallery images per class. Furthermore, the face recognition accuracy exceeds those of the SRC and Extended SRC algorithms using hand labeled alignment initialization.
With increasing amounts of visual data being created in the form of videos and images, visual data selection and summarization are becoming ever increasing problems. We present Vis-DSS, an open-source toolkit for Visual Data Selection and Summarization. Vis-DSS implements a framework of models for summarization and data subset selection using submodular functions, which are becoming increasingly popular today for these problems. We present several classes of models, capturing notions of diversity, coverage, representation and importance, along with optimization/inference and learning algorithms. Vis-DSS is the first open source toolkit for several Data selection and summarization tasks including Image Collection Summarization, Video Summarization, Training Data selection for Classification and Diversified Active Learning. We demonstrate state-of-the art performance on all these tasks, and also show how we can scale to large problems. Vis-DSS allows easy integration for applications to be built on it, also can serve as a general skeleton that can be extended to several use cases, including video and image sharing platforms for creating GIFs, image montage creation, or as a component to surveillance systems and we demonstrate this by providing a graphical user-interface (GUI) desktop app built over Qt framework. Vis-DSS is available at https://github.com/rishabhk108/vis-dss
Anomaly detection in X-ray images has been an active and lasting research area in the last decades, especially in the domain of medical X-ray images. For this work, we created a real-world labeled anomaly dataset, consisting of 16-bit X-ray image data of fuel cell electrodes coated with a platinum catalyst solution and perform anomaly detection on the dataset using a deep learning approach. The dataset contains a diverse set of anomalies with 11 identified common anomalies where the electrodes contain e.g. scratches, bubbles, smudges etc. We experiment with 16-bit image to 8-bit image conversion methods to utilize pre-trained Convolutional Neural Networks as feature extractors (transfer learning) and find that we achieve the best performance by maximizing the contrasts globally across the dataset during the 16-bit to 8-bit conversion, through histogram equalization. We group the fuel cell electrodes with anomalies into a single class called abnormal and the normal fuel cell electrodes into a class called normal, thereby abstracting the anomaly detection problem into a binary classification problem. We achieve a balanced accuracy of 85.18\%. The anomaly detection is used by the company, Serenergy, for optimizing the time spend on the quality control of the fuel cell electrodes