In traffic sign recognition tasks, recognition of road signs by observing synthetic reference images is a human-like ability that can be performed by one-shot learning algorithms. One-shot object recognition is a challenging task for deep neural networks in which a deep model classifies query examples based on support images. It becomes more difficult when there is a domain shift between support and query samples. The generalization of a deep model on an unknown domain with different distributions is another problematic task in on-shot recognition. This work introduces a novel deep network named SeqNet to overcome the aforementioned problems. To the best of our knowledge, this work outperforms all state-of-the-art models in one-shot traffic sign recognition and one-shot logo identification by superior results. Our proposed SeqNet model generalizes to unseen domains without further model fine-tuning on the test data. Also, we show how using transferred knowledge from an irrelevant but large domain could reduce the network parameters that result in model size reduction. By utilizing the power of transferred knowledge from a large deep model the SeqNet becomes smaller and has about 6X fewer parameters than its competitors. The smaller size of the SeqNet architecture enables it to be used in resource-constrained devices in many applications such as smart vehicles. The experimental results depict that our proposed SeqNet performance is ameliorated by large margins, with up to 20% accuracy for one-shot classification and 30% area under the curve (AUC) for image retrieval tasks.
Object recognition and detection are well-studied problems with a developed set of almost standard solutions. Identity documents recognition, classification, detection, and localization are the tasks required in a number of applications, particularly, in physical access control security systems at critical infrastructure premises. In this paper, we propose the new original architecture of a model based on an artificial convolutional neural network and semantic segmentation approach for the recognition and detection of identity documents in images. The challenge with the processing of such images is the limited computational performance and the limited amount of memory when such an application is running on industrial oneboard microcomputer hardware. The aim of this research is to prove the feasibility of the proposed technique and to obtain quality metrics. The methodology of the research is to evaluate the deep learning detection model trained on the mobile identity document video dataset. The dataset contains five hundred video clips for fifty different identity document types. The numerical results from simulations are used to evaluate the quality metrics. We present the results as accuracy versus threshold of the intersection over union value. The paper reports an accuracy above 0.75 for the intersection over union (IoU) threshold value of 0.8. Besides, we assessed the size of the model and proved the feasibility of running the model on an industrial one-board microcomputer or smartphone hardware.
Extracting tables from documents is a critical task across various industries, especially on business documents like invoices and reports. Existing systems based on DEtection TRansformer (DETR) such as TAble TRansformer (TATR), offer solutions for Table Detection (TD) and Table Structure Recognition (TSR) but face challenges with diverse table formats and common errors like incorrect area detection and overlapping columns. This research introduces RAPTOR, a modular post-processing system designed to enhance state-of-the-art models for improved table extraction, particularly for product tables. RAPTOR addresses recurrent TD and TSR issues, improving both precision and structural predictions. For TD, we use DETR (trained on ICDAR 2019) and TATR (trained on PubTables-1M and FinTabNet), while TSR only relies on TATR. A Genetic Algorithm is incorporated to optimize RAPTOR's module parameters, using a private dataset of product tables to align with industrial needs. We evaluate our method on two private datasets of product tables, the public DOCILE dataset (which contains tables similar to our target product tables), and the ICDAR 2013 and ICDAR 2019 datasets. The results demonstrate that while our approach excels at product tables, it also maintains reasonable performance across diverse table formats. An ablation study further validates the contribution of each module in our system.
Infrared sensing is a core method for supporting unmanned systems, such as autonomous vehicles and drones. Recently, infrared sensors have been widely deployed on mobile and stationary platforms for detection and classification of objects from long distances and in wide field of views. Given its success in the vision image analysis domain, deep learning has also been applied for object recognition in infrared images. However, techniques that have proven successful in visible light perception face new challenges in the infrared domain. These challenges include extremely low signal-to-noise ratios in infrared images, very small and blurred objects of interest, and limited availability of labeled/unlabeled training data due to the specialized nature of infrared sensors. Numerous methods have been proposed in the literature for the detection and classification of small objects in infrared images achieving varied levels of success. There is a need for a survey paper that critically analyzes existing techniques in this domain, identifies unsolved challenges and provides future research directions. This paper fills the gap and offers a concise and insightful review of deep learning-based methods. It also identifies the challenges faced by existing infrared object segmentation methods and provides a structured review of existing infrared perception methods from the perspective of these challenges and highlights the motivations behind the various approaches. Finally, this review suggests promising future directions based on recent advancements within this domain.
Recent open-world representation learning approaches have leveraged CLIP to enable zero-shot 3D object recognition. However, performance on real point clouds with occlusions still falls short due to the unrealistic pretraining settings. Additionally, these methods incur high inference costs because they rely on Transformer's attention modules. In this paper, we make two contributions to address these limitations. First, we propose occlusion-aware text-image-point cloud pretraining to reduce the training-testing domain gap. From 52K synthetic 3D objects, our framework generates nearly 630K partial point clouds for pretraining, consistently improving real-world recognition performances of existing popular 3D networks. Second, to reduce computational requirements, we introduce DuoMamba, a two-stream linear state space model tailored for point clouds. By integrating two space-filling curves with 1D convolutions, DuoMamba effectively models spatial dependencies between point tokens, offering a powerful alternative to Transformer. When pretrained with our framework, DuoMamba surpasses current state-of-the-art methods while reducing latency and FLOPs, highlighting the potential of our approach for real-world applications. We will release our data and code to facilitate future research.
Deep neural networks (DNNs) often exhibit biases toward certain categories during object recognition, even under balanced training data conditions. The intrinsic mechanisms underlying these biases remain unclear. Inspired by the human visual system, which decouples object manifolds through hierarchical processing to achieve object recognition, we propose a geometric analysis framework linking the geometric complexity of class-specific perceptual manifolds in DNNs to model bias. Our findings reveal that differences in geometric complexity can lead to varying recognition capabilities across categories, introducing biases. To support this analysis, we present the Perceptual-Manifold-Geometry library, designed for calculating the geometric properties of perceptual manifolds.
The evaluation of factual accuracy in large vision language models (LVLMs) has lagged behind their rapid development, making it challenging to fully reflect these models' knowledge capacity and reliability. In this paper, we introduce the first factuality-based visual question-answering benchmark in Chinese, named ChineseSimpleVQA, aimed at assessing the visual factuality of LVLMs across 8 major topics and 56 subtopics. The key features of this benchmark include a focus on the Chinese language, diverse knowledge types, a multi-hop question construction, high-quality data, static consistency, and easy-to-evaluate through short answers. Moreover, we contribute a rigorous data construction pipeline and decouple the visual factuality into two parts: seeing the world (i.e., object recognition) and discovering knowledge. This decoupling allows us to analyze the capability boundaries and execution mechanisms of LVLMs. Subsequently, we evaluate 34 advanced open-source and closed-source models, revealing critical performance gaps within this field.
Although large multimodal models (LMMs) have demonstrated remarkable capabilities in visual scene interpretation and reasoning, their capacity for complex and precise 3-dimensional spatial reasoning remains uncertain. Existing benchmarks focus predominantly on 2D spatial understanding and lack a framework to comprehensively evaluate 6D spatial reasoning across varying complexities. To address this limitation, we present Spatial457, a scalable and unbiased synthetic dataset designed with 4 key capability for spatial reasoning: multi-object recognition, 2D location, 3D location, and 3D orientation. We develop a cascading evaluation structure, constructing 7 question types across 5 difficulty levels that range from basic single object recognition to our new proposed complex 6D spatial reasoning tasks. We evaluated various large multimodal models (LMMs) on PulseCheck457, observing a general decline in performance as task complexity increases, particularly in 3D reasoning and 6D spatial tasks. To quantify these challenges, we introduce the Relative Performance Dropping Rate (RPDR), highlighting key weaknesses in 3D reasoning capabilities. Leveraging the unbiased attribute design of our dataset, we also uncover prediction biases across different attributes, with similar patterns observed in real-world image settings. The code and data are released in https://github.com/XingruiWang/Spatial457.
White blood cells (WBC) are important parts of our immune system, and they protect our body against infections by eliminating viruses, bacteria, parasites and fungi. The number of WBC types and the total number of WBCs provide important information about our health status. A traditional method, convolutional neural networks (CNN), a deep learning architecture, can classify the blood cell from a part of an object and perform object recognition. Various CNN models exhibit potential; however, their development often involves ad-hoc processes that neglect unnecessary layers, leading to issues with unbalanced datasets and insufficient data augmentation. To address these challenges, we propose a novel ensemble approach that integrates three CNN architectures, each uniquely configured with different dropout and max-pooling layer settings to enhance feature learning. This ensemble model, named DCENWCNet, effectively balances the bias-variance trade-off. When evaluated on the widely recognized Rabbin-WBC dataset, our model outperforms existing state-of-the-art networks, achieving highest mean accuracy. Additionally, it demonstrates superior performance in precision, recall, F1-score, and Area Under the ROC Curve (AUC) across all categories. To delve deeper into the interpretability of classifiers, we employ reliable post-hoc explanation techniques, including Local Interpretable Model-Agnostic Explanations (LIME). These methods approximate the behavior of a black-box model by elucidating the relationships between feature values and predictions. Interpretable results enable users to comprehend and validate the model's predictions, thereby increasing their confidence in the automated diagnosis.
Computer vision for real-world applications faces data acquisition challenges, including accessibility, high costs, difficulty in obtaining diversity in scenarios or environmental conditions. Synthetic data usage has surged as a solution to these obstacles. Leveraging game engines for synthetic dataset creation effectively enriches training datasets with increased diversity and richness. The choice of the game engine, pivotal for generating photorealistic simulations, may influence synthetic data quality. This study compares Unity Engine’s and Unreal Engine’s capabilities in generating synthetic maritime datasets to support ship recognition applications. To this end, the realworld maritime dataset ShipSG has been replicated in the corresponding game engines to create the same scenarios. The performance of the generated synthetic datasets is benchmarked against the real-world ShipSG dataset using the object recognition model YOLOv8. Furthermore, the comparison evaluates various photorealistic parameters found in the dataset images to determine the optimal configuration for improving performance with YOLOv8. The datasets generated using the Unity Engine, with all photorealistic effects present and the one with no lens distortion, achieved the highest accuracy in ship recognition with a mAP of 72.3%. Both configurations of the synthetic datasets were utilised to augment the ShipSG dataset to train YOLOv8. The configuration with all photorealistic parameters in place provides the highest mAP increase, of 0.4% compared with YOLOv8 performance on ShipSG when no synthetic data is used. This evidence underscores that utilising game engines can effectively support and enhance ship recognition tasks.
Fiducial markers are widely used in various robotics tasks, facilitating enhanced navigation, object recognition, and scene understanding. Despite their advantages for robots and Augmented Reality (AR) applications, they often disrupt the visual aesthetics of environments because they are visible to humans, making them unsuitable for non-intrusive use cases. To address this gap, this paper presents "iMarkers"-innovative, unobtrusive fiducial markers detectable exclusively by robots equipped with specialized sensors. These markers offer high flexibility in production, allowing customization of their visibility range and encoding algorithms to suit various demands. The paper also introduces the hardware designs and software algorithms developed for detecting iMarkers, highlighting their adaptability and robustness in the detection and recognition stages. Various evaluations have demonstrated the effectiveness of iMarkers compared to conventional (printed) and blended fiducial markers and confirmed their applicability in diverse robotics scenarios.
Despite their impressive performance on multi-modal tasks, large vision-language models (LVLMs) tend to suffer from hallucinations. An important type is object hallucination, where LVLMs generate objects that are inconsistent with the images shown to the model. Existing works typically attempt to quantify object hallucinations by detecting and measuring the fraction of hallucinated objects in generated captions. Additionally, more recent work also measures object hallucinations by directly querying the LVLM with binary questions about the presence of likely hallucinated objects based on object statistics like top-k frequent objects and top-k co-occurring objects. In this paper, we present Context-Aware Object Similarities (CAOS), a novel approach for evaluating object hallucination in LVLMs using object statistics as well as the generated captions. CAOS uniquely integrates object statistics with semantic relationships between objects in captions and ground-truth data. Moreover, existing approaches usually only detect and measure hallucinations belonging to a predetermined set of in-domain objects (typically the set of all ground-truth objects for the training dataset) and ignore generated objects that are not part of this set, leading to under-evaluation. To address this, we further employ language model--based object recognition to detect potentially out-of-domain hallucinated objects and use an ensemble of LVLMs for verifying the presence of such objects in the query image. CAOS also examines the sequential dynamics of object generation, shedding light on how the order of object appearance influences hallucinations, and employs word embedding models to analyze the semantic reasons behind hallucinations. CAOS aims to offer a nuanced understanding of the hallucination tendencies of LVLMs by providing a systematic framework to identify and interpret object hallucinations.
As an indispensable sensor for Remote sensing, Synthetic Aperture Radar (SAR) has a unique capability for all-day imaging. Nevertheless, in a data-driven era, the scarcity of large-scale datasets poses a significant bottleneck to advancing SAR automatic target recognition (ATR) technology. This paper introduces NUDT4MSTAR, a large-scale SAR dataset for remote sensing target recognition in the wild, including 40 vehicle target types and various imaging conditions across 5 realistic scenes. NUDT4MSTAR represents a significant leap forward in dataset scale, containing over 190,000 images-tenfold the size of its predecessors. We meticulously annotate each image with detailed target information and imaging conditions. Besides, data in both processed magnitude images and original complex formats are provided. Then, we construct a comprehensive benchmark consisting of 7 experiments with 15 recognition methods focusing on the stable and effective ATR issues. Besides, we conduct transfer learning experiments utilizing various models training on NUDT4MSTAR and apply them to three other target datasets, demonstrating its substantial potential for the broader field of ground objects ATR. Finally, we discuss this dataset's application value and ATR's significant challenges. To the best of our knowledge, this work marks the first-ever endeavor to create a large-scale dataset benchmark for fine-grained SAR recognition in the wild, featuring an extensive collection of exhaustively annotated vehicle images. We expect that the open source of NUDT4MSTAR will facilitate the development of SAR ATR and attract a wider community of researchers.
Video encoders optimize compression for human perception by minimizing reconstruction error under bit-rate constraints. In many modern applications such as autonomous driving, an overwhelming majority of videos serve as input for AI systems performing tasks like object recognition or segmentation, rather than being watched by humans. It is therefore useful to optimize the encoder for a downstream task instead of for perceptual image quality. However, a major challenge is how to combine such downstream optimization with existing standard video encoders, which are highly efficient and popular. Here, we address this challenge by controlling the Quantization Parameters (QPs) at the macro-block level to optimize the downstream task. This granular control allows us to prioritize encoding for task-relevant regions within each frame. We formulate this optimization problem as a Reinforcement Learning (RL) task, where the agent learns to balance long-term implications of choosing QPs on both task performance and bit-rate constraints. Notably, our policy does not require the downstream task as an input during inference, making it suitable for streaming applications and edge devices such as vehicles. We demonstrate significant improvements in two tasks, car detection, and ROI (saliency) encoding. Our approach improves task performance for a given bit rate compared to traditional task agnostic encoding methods, paving the way for more efficient task-aware video compression.
In the current era of Machine Learning, Transformers have become the de facto approach across a variety of domains, such as computer vision and natural language processing. Transformer-based solutions are the backbone of current state-of-the-art methods for language generation, image and video classification, segmentation, action and object recognition, among many others. Interestingly enough, while these state-of-the-art methods produce impressive results in their respective domains, the problem of understanding the relationship between vision and language is still beyond our reach. In this work, we propose a common ground between vision and language based on events in space and time in an explainable and programmatic way, to connect learning-based vision and language state of the art models and provide a solution to the long standing problem of describing videos in natural language. We validate that our algorithmic approach is able to generate coherent, rich and relevant textual descriptions on videos collected from a variety of datasets, using both standard metrics (e.g. Bleu, ROUGE) and the modern LLM-as-a-Jury approach.
Localizing object parts precisely is essential for tasks such as object recognition and robotic manipulation. Recent part segmentation methods require extensive training data and labor-intensive annotations. Segment-Anything Model (SAM) has demonstrated good performance on a wide range of segmentation problems, but requires (manual) positional prompts to guide it where to segment. Furthermore, since it has been trained on full objects instead of object parts, it is prone to over-segmentation of parts. To address this, we propose a novel approach that guides SAM towards the relevant object parts. Our method learns positional prompts from coarse patch annotations that are easier and cheaper to acquire. We train classifiers on image patches to identify part classes and aggregate patches into regions of interest (ROIs) with positional prompts. SAM is conditioned on these ROIs and prompts. This approach, termed `Guided SAM', enhances efficiency and reduces manual effort, allowing effective part segmentation with minimal labeled data. We demonstrate the efficacy of Guided SAM on a dataset of car parts, improving the average IoU on state of the art models from 0.37 to 0.49 with annotations that are on average five times more efficient to acquire.
Superpixel segmentation is a foundation for many higher-level computer vision tasks, such as image segmentation, object recognition, and scene understanding. Existing graph-based superpixel segmentation methods typically concentrate on the relationships between a given pixel and its directly adjacent pixels while overlooking the influence of non-adjacent pixels. These approaches do not fully leverage the global information in the graph, leading to suboptimal segmentation quality. To address this limitation, we present SIT-HSS, a hierarchical superpixel segmentation method based on structural information theory. Specifically, we first design a novel graph construction strategy that incrementally explores the pixel neighborhood to add edges based on 1-dimensional structural entropy (1D SE). This strategy maximizes the retention of graph information while avoiding an overly complex graph structure. Then, we design a new 2D SE-guided hierarchical graph partitioning method, which iteratively merges pixel clusters layer by layer to reduce the graph's 2D SE until a predefined segmentation scale is achieved. Experimental results on three benchmark datasets demonstrate that the SIT-HSS performs better than state-of-the-art unsupervised superpixel segmentation algorithms. The source code is available at \url{https://github.com/SELGroup/SIT-HSS}.
Visual impairment affects the ability of people to live a life like normal people. Such people face challenges in performing activities of daily living, such as reading, writing, traveling and participating in social gatherings. Many traditional approaches are available to help visually impaired people; however, these are limited in obtaining contextually rich environmental information necessary for independent living. In order to overcome this limitation, this paper introduces a novel wearable vision assistance system that has a hat-mounted camera connected to a Raspberry Pi 4 Model B (8GB RAM) with artificial intelligence (AI) technology to deliver real-time feedback to a user through a sound beep mechanism. The key features of this system include a user-friendly procedure for the recognition of new people or objects through a one-click process that allows users to add data on new individuals and objects for later detection, enhancing the accuracy of the recognition over time. The system provides detailed descriptions of objects in the user's environment using a large vision language model (LVLM). In addition, it incorporates a distance sensor that activates a beeping sound using a buzzer as soon as the user is about to collide with an object, helping to ensure safety while navigating their environment. A comprehensive evaluation is carried out to evaluate the proposed AI-based solution against traditional support techniques. Comparative analysis shows that the proposed solution with its innovative combination of hardware and AI (including LVLMs with IoT), is a significant advancement in assistive technology that aims to solve the major issues faced by the community of visually impaired people
Multimodal large language models (MLLMs), such as GPT-4o, Gemini, LLaVA, and Flamingo, have made significant progress in integrating visual and textual modalities, excelling in tasks like visual question answering (VQA), image captioning, and content retrieval. They can generate coherent and contextually relevant descriptions of images. However, they still face challenges in accurately identifying and counting objects and determining their spatial locations, particularly in complex scenes with overlapping or small objects. To address these limitations, we propose a novel framework based on multimodal retrieval-augmented generation (RAG), which introduces structured scene graphs to enhance object recognition, relationship identification, and spatial understanding within images. Our framework improves the MLLM's capacity to handle tasks requiring precise visual descriptions, especially in scenarios with challenging perspectives, such as aerial views or scenes with dense object arrangements. Finally, we conduct extensive experiments on the VG-150 dataset that focuses on first-person visual understanding and the AUG dataset that involves aerial imagery. The results show that our approach consistently outperforms existing MLLMs in VQA tasks, which stands out in recognizing, localizing, and quantifying objects in different spatial contexts and provides more accurate visual descriptions.
Face recognition has witnessed remarkable advancements in recent years, thanks to the development of deep learning techniques.However, an off-the-shelf face recognition model as a commercial service could be stolen by model stealing attacks, posing great threats to the rights of the model owner.Model fingerprinting, as a model stealing detection method, aims to verify whether a suspect model is stolen from the victim model, gaining more and more attention nowadays.Previous methods always utilize transferable adversarial examples as the model fingerprint, but this method is known to be sensitive to adversarial defense and transfer learning techniques.To address this issue, we consider the pairwise relationship between samples instead and propose a novel yet simple model stealing detection method based on SAmple Correlation (SAC).Specifically, we present SAC-JC that selects JPEG compressed samples as model inputs and calculates the correlation matrix among their model outputs.Extensive results validate that SAC successfully defends against various model stealing attacks in deep face recognition, encompassing face verification and face emotion recognition, exhibiting the highest performance in terms of AUC, p-value and F1 score.Furthermore, we extend our evaluation of SAC-JC to object recognition datasets including Tiny-ImageNet and CIFAR10, which also demonstrates the superior performance of SAC-JC to previous methods.The code will be available at \url{https://github.com/guanjiyang/SAC_JC}.