In recent years, deep learning techniques have been used to develop sign language recognition systems, potentially serving as a communication tool for millions of hearing-impaired individuals worldwide. However, there are inherent challenges in creating such systems. Firstly, it is important to consider as many linguistic parameters as possible in gesture execution to avoid ambiguity between words. Moreover, to facilitate the real-world adoption of the created solution, it is essential to ensure that the chosen technology is realistic, avoiding expensive, intrusive, or low-mobility sensors, as well as very complex deep learning architectures that impose high computational requirements. Based on this, our work aims to propose an efficient sign language recognition system that utilizes low-cost sensors and techniques. To this end, an object detection model was trained specifically for detecting the interpreter's face and hands, ensuring focus on the most relevant regions of the image and generating inputs with higher semantic value for the classifier. Additionally, we introduced a novel approach to obtain features representing hand location and movement by leveraging spatial information derived from centroid positions of bounding boxes, thereby enhancing sign discrimination. The results demonstrate the efficiency of our handcrafted features, increasing accuracy by 7.96% on the AUTSL dataset, while adding fewer than 700 thousand parameters and incurring less than 10 milliseconds of additional inference time. These findings highlight the potential of our technique to strike a favorable balance between computational cost and accuracy, making it a promising approach for practical sign language recognition applications.
Workplace accidents due to personal protective equipment (PPE) non-compliance raise serious safety concerns and lead to legal liabilities, financial penalties, and reputational damage. While object detection models have shown the capability to address this issue by identifying safety items, most existing models, such as YOLO, Faster R-CNN, and SSD, are limited in verifying the fine-grained attributes of PPE across diverse workplace scenarios. Vision language models (VLMs) are gaining traction for detection tasks by leveraging the synergy between visual and textual information, offering a promising solution to traditional object detection limitations in PPE recognition. Nonetheless, VLMs face challenges in consistently verifying PPE attributes due to the complexity and variability of workplace environments, requiring them to interpret context-specific language and visual cues simultaneously. We introduce Clip2Safety, an interpretable detection framework for diverse workplace safety compliance, which comprises four main modules: scene recognition, the visual prompt, safety items detection, and fine-grained verification. The scene recognition identifies the current scenario to determine the necessary safety gear. The visual prompt formulates the specific visual prompts needed for the detection process. The safety items detection identifies whether the required safety gear is being worn according to the specified scenario. Lastly, the fine-grained verification assesses whether the worn safety equipment meets the fine-grained attribute requirements. We conduct real-world case studies across six different scenarios. The results show that Clip2Safety not only demonstrates an accuracy improvement over state-of-the-art question-answering based VLMs but also achieves inference times two hundred times faster.
This thesis presents and evaluates the Dilated Convolution with Learnable Spacings (DCLS) method. Through various supervised learning experiments in the fields of computer vision, audio, and speech processing, the DCLS method proves to outperform both standard and advanced convolution techniques. The research is organized into several steps, starting with an analysis of the literature and existing convolution techniques that preceded the development of the DCLS method. We were particularly interested in the methods that are closely related to our own and that remain essential to capture the nuances and uniqueness of our approach. The cornerstone of our study is the introduction and application of the DCLS method to convolutional neural networks (CNNs), as well as to hybrid architectures that rely on both convolutional and visual attention approaches. DCLS is shown to be particularly effective in tasks such as classification, semantic segmentation, and object detection. Initially using bilinear interpolation, the study also explores other interpolation methods, finding that Gaussian interpolation slightly improves performance. The DCLS method is further applied to spiking neural networks (SNNs) to enable synaptic delay learning within a neural network that could eventually be transferred to so-called neuromorphic chips. The results show that the DCLS method stands out as a new state-of-the-art technique in SNN audio classification for certain benchmark tasks in this field. These tasks involve datasets with a high temporal component. In addition, we show that DCLS can significantly improve the accuracy of artificial neural networks for the multi-label audio classification task. We conclude with a discussion of the chosen experimental setup, its limitations, the limitations of our method, and our results.
3D perception tasks, such as 3D object detection and Bird's-Eye-View (BEV) segmentation using multi-camera images, have drawn significant attention recently. Despite the fact that accurately estimating both semantic and 3D scene layouts are crucial for this task, existing techniques often neglect the synergistic effects of semantic and depth cues, leading to the occurrence of classification and position estimation errors. Additionally, the input-independent nature of initial queries also limits the learning capacity of Transformer-based models. To tackle these challenges, we propose an input-aware Transformer framework that leverages Semantics and Depth as priors (named SDTR). Our approach involves the use of an S-D Encoder that explicitly models semantic and depth priors, thereby disentangling the learning process of object categorization and position estimation. Moreover, we introduce a Prior-guided Query Builder that incorporates the semantic prior into the initial queries of the Transformer, resulting in more effective input-aware queries. Extensive experiments on the nuScenes and Lyft benchmarks demonstrate the state-of-the-art performance of our method in both 3D object detection and BEV segmentation tasks.
Object detection is an important part in the field of computer vision, and the effect of object detection is directly determined by the regression accuracy of the prediction box. As the key to model training, IoU (Intersection over Union) greatly shows the difference between the current prediction box and the Ground Truth box. Subsequent researchers have continuously added more considerations to IoU, such as center distance, aspect ratio, and so on. However, there is an upper limit to just refining the geometric differences; And there is a potential connection between the new consideration index and the IoU itself, and the direct addition or subtraction between the two may lead to the problem of "over-consideration". Based on this, we propose a new IoU loss function, called Unified-IoU (UIoU), which is more concerned with the weight assignment between different quality prediction boxes. Specifically, the loss function dynamically shifts the model's attention from low-quality prediction boxes to high-quality prediction boxes in a novel way to enhance the model's detection performance on high-precision or intensive datasets and achieve a balance in training speed. Our proposed method achieves better performance on multiple datasets, especially at a high IoU threshold, UIoU has a more significant improvement effect compared with other improved IoU losses. Our code is publicly available at: https://github.com/lxj-drifter/UIOU_files.
We introduce a novel MV-DETR pipeline which is effective while efficient transformer based detection method. Given input RGBD data, we notice that there are super strong pretraining weights for RGB data while less effective works for depth related data. First and foremost , we argue that geometry and texture cues are both of vital importance while could be encoded separately. Secondly, we find that visual texture feature is relatively hard to extract compared with geometry feature in 3d space. Unfortunately, single RGBD dataset with thousands of data is not enough for training an discriminating filter for visual texture feature extraction. Last but certainly not the least, we designed a lightweight VG module consists of a visual textual encoder, a geometry encoder and a VG connector. Compared with previous state of the art works like V-DETR, gains from pretrained visual encoder could be seen. Extensive experiments on ScanNetV2 dataset shows the effectiveness of our method. It is worth mentioned that our method achieve 78\% AP which create new state of the art on ScanNetv2 benchmark.
With the ever-growing variety of object detection approaches, this study explores a series of experiments that combine reinforcement learning (RL)-based visual attention methods with saliency ranking techniques to investigate transparent and sustainable solutions. By integrating saliency ranking for initial bounding box prediction and subsequently applying RL techniques to refine these predictions through a finite set of actions over multiple time steps, this study aims to enhance RL object detection accuracy. Presented as a series of experiments, this research investigates the use of various image feature extraction methods and explores diverse Deep Q-Network (DQN) architectural variations for deep reinforcement learning-based localisation agent training. Additionally, we focus on optimising the detection pipeline at every step by prioritising lightweight and faster models, while also incorporating the capability to classify detected objects, a feature absent in previous RL approaches. We show that by evaluating the performance of these trained agents using the Pascal VOC 2007 dataset, faster and more optimised models were developed. Notably, the best mean Average Precision (mAP) achieved in this study was 51.4, surpassing benchmarks set by RL-based single object detectors in the literature.
The rapid evolution of deep learning and its integration with autonomous driving systems have led to substantial advancements in 3D perception using multimodal sensors. Notably, radar sensors show greater robustness compared to cameras and lidar under adverse weather and varying illumination conditions. This study delves into the often-overlooked yet crucial issue of domain shift in 4D radar-based object detection, examining how varying environmental conditions, such as different weather patterns and road types, impact 3D object detection performance. Our findings highlight distinct domain shifts across various weather scenarios, revealing unique dataset sensitivities that underscore the critical role of radar point cloud generation. Additionally, we demonstrate that transitioning between different road types, especially from highways to urban settings, introduces notable domain shifts, emphasizing the necessity for diverse data collection across varied road environments. To the best of our knowledge, this is the first comprehensive analysis of domain shift effects on 4D radar-based object detection. We believe this empirical study contributes to understanding the complex nature of domain shifts in radar data and suggests paths forward for data collection strategy in the face of environmental variability.
Many learning-based low-light image enhancement (LLIE) algorithms are based on the Retinex theory. However, the Retinex-based decomposition techniques in such models introduce corruptions which limit their enhancement performance. In this paper, we propose a Latent Disentangle-based Enhancement Network (LDE-Net) for low light vision tasks. The latent disentanglement module disentangles the input image in latent space such that no corruption remains in the disentangled Content and Illumination components. For LLIE task, we design a Content-Aware Embedding (CAE) module that utilizes Content features to direct the enhancement of the Illumination component. For downstream tasks (e.g. nighttime UAV tracking and low-light object detection), we develop an effective light-weight enhancer based on the latent disentanglement framework. Comprehensive quantitative and qualitative experiments demonstrate that our LDE-Net significantly outperforms state-of-the-art methods on various LLIE benchmarks. In addition, the great results obtained by applying our framework on the downstream tasks also demonstrate the usefulness of our latent disentanglement design.
The safe operation of automated vehicles depends on their ability to perceive the environment comprehensively. However, occlusion, sensor range, and environmental factors limit their perception capabilities. To overcome these limitations, collective perception enables vehicles to exchange information. However, fusing this exchanged information is a challenging task. Early fusion approaches require large amounts of bandwidth, while intermediate fusion approaches face interchangeability issues. Late fusion of shared detections is currently the only feasible approach. However, it often results in inferior performance due to information loss. To address this issue, we propose MR3D-Net, a dynamic multi-resolution 3D sparse voxel grid fusion backbone architecture for LiDAR-based collective perception. We show that sparse voxel grids at varying resolutions provide a meaningful and compact environment representation that can adapt to the communication bandwidth. MR3D-Net achieves state-of-the-art performance on the OPV2V 3D object detection benchmark while reducing the required bandwidth by up to 94% compared to early fusion. Code is available at https://github.com/ekut-es/MR3D-Net
Infrared-visible object detection aims to achieve robust object detection by leveraging the complementary information of infrared and visible image pairs. However, the commonly existing modality misalignment problem presents two challenges: fusing misalignment complementary features is difficult, and current methods cannot accurately locate objects in both modalities under misalignment conditions. In this paper, we propose a Decoupled Position Detection Transformer (DPDETR) to address these problems. Specifically, we explicitly formulate the object category, visible modality position, and infrared modality position to enable the network to learn the intrinsic relationships and output accurate positions of objects in both modalities. To fuse misaligned object features accurately, we propose a Decoupled Position Multispectral Cross-attention module that adaptively samples and aggregates multispectral complementary features with the constraint of infrared and visible reference positions. Additionally, we design a query-decoupled Multispectral Decoder structure to address the optimization gap among the three kinds of object information in our task and propose a Decoupled Position Contrastive DeNosing Training strategy to enhance the DPDETR's ability to learn decoupled positions. Experiments on DroneVehicle and KAIST datasets demonstrate significant improvements compared to other state-of-the-art methods. The code will be released at https://github.com/gjj45/DPDETR.
The groundbreaking performance of transformers in Natural Language Processing (NLP) tasks has led to their replacement of traditional Convolutional Neural Networks (CNNs), owing to the efficiency and accuracy achieved through the self-attention mechanism. This success has inspired researchers to explore the use of transformers in computer vision tasks to attain enhanced long-term semantic awareness. Vision transformers (ViTs) have excelled in various computer vision tasks due to their superior ability to capture long-distance dependencies using the self-attention mechanism. Contemporary ViTs like Data Efficient Transformers (DeiT) can effectively learn both global semantic information and local texture information from images, achieving performance comparable to traditional CNNs. However, their impressive performance comes with a high computational cost due to very large number of parameters, hindering their deployment on devices with limited resources like smartphones, cameras, drones etc. Additionally, ViTs require a large amount of data for training to achieve performance comparable to benchmark CNN models. Therefore, we identified two key challenges in deploying ViTs on smaller form factor devices: the high computational requirements of large models and the need for extensive training data. As a solution to these challenges, we propose compressing large ViT models using Knowledge Distillation (KD), which is implemented data-free to circumvent limitations related to data availability. Additionally, we conducted experiments on object detection within the same environment in addition to classification tasks. Based on our analysis, we found that datafree knowledge distillation is an effective method to overcome both issues, enabling the deployment of ViTs on less resourceconstrained devices.
The rise of autonomous vehicles has significantly increased the demand for robust 3D object detection systems. While cameras and LiDAR sensors each offer unique advantages--cameras provide rich texture information and LiDAR offers precise 3D spatial data--relying on a single modality often leads to performance limitations. This paper introduces MV2DFusion, a multi-modal detection framework that integrates the strengths of both worlds through an advanced query-based fusion mechanism. By introducing an image query generator to align with image-specific attributes and a point cloud query generator, MV2DFusion effectively combines modality-specific object semantics without biasing toward one single modality. Then the sparse fusion process can be accomplished based on the valuable object semantics, ensuring efficient and accurate object detection across various scenarios. Our framework's flexibility allows it to integrate with any image and point cloud-based detectors, showcasing its adaptability and potential for future advancements. Extensive evaluations on the nuScenes and Argoverse2 datasets demonstrate that MV2DFusion achieves state-of-the-art performance, particularly excelling in long-range detection scenarios.
Foundational vision models, such as the Segment Anything Model (SAM), have achieved significant breakthroughs through extensive pre-training on large-scale visual datasets. Despite their general success, these models may fall short in specialized tasks with limited data, and fine-tuning such large-scale models is often not feasible. Current strategies involve incorporating adaptors into the pre-trained SAM to facilitate downstream task performance with minimal model adjustment. However, these strategies can be hampered by suboptimal learning approaches for the adaptors. In this paper, we introduce a novel Multi-scale Contrastive Adaptor learning method named MCA-SAM, which enhances adaptor performance through a meticulously designed contrastive learning framework at both token and sample levels. Our Token-level Contrastive adaptor (TC-adaptor) focuses on refining local representations by improving the discriminability of patch tokens, while the Sample-level Contrastive adaptor (SC-adaptor) amplifies global understanding across different samples. Together, these adaptors synergistically enhance feature comparison within and across samples, bolstering the model's representational strength and its ability to adapt to new tasks. Empirical results demonstrate that MCA-SAM sets new benchmarks, outperforming existing methods in three challenging domains: camouflage object detection, shadow segmentation, and polyp segmentation. Specifically, MCA-SAM exhibits substantial relative performance enhancements, achieving a 20.0% improvement in MAE on the COD10K dataset, a 6.0% improvement in MAE on the CAMO dataset, a 15.4% improvement in BER on the ISTD dataset, and a 7.9% improvement in mDice on the Kvasir-SEG dataset.
Underwater object detection has higher requirements of running speed and deployment efficiency for the detector due to its specific environmental challenges. NMS of two- or one-stage object detectors and transformer architecture of query-based end-to-end object detectors are not conducive to deployment on underwater embedded devices with limited processing power. As for the detrimental effect of underwater color cast noise, recent underwater object detectors make network architecture or training complex, which also hinders their application and deployment on underwater vehicle platforms. In this paper, we propose the Underwater DECO with improved deNoising training (U-DECN), the query-based end-to-end object detector (with ConvNet encoder-decoder architecture) for underwater color cast noise that addresses the above problems. We integrate advanced technologies from DETR variants into DECO and design optimization methods specifically for the ConvNet architecture, including Separate Contrastive DeNoising Forward and Deformable Convolution in SIM. To address the underwater color cast noise issue, we propose an underwater color denoising query to improve the generalization of the model for the biased object feature information by different color cast noise. Our U-DECN, with ResNet-50 backbone, achieves 61.4 AP (50 epochs), 63.3 AP (72 epochs), 64.0 AP (100 epochs) on DUO, and 21 FPS (5 times faster than Deformable DETR and DINO 4 FPS) on NVIDIA AGX Orin by TensorRT FP16, outperforming the other state-of-the-art query-based end-to-end object detectors. The code is available at https://github.com/LEFTeyex/U-DECN.
Falling objects from buildings can cause severe injuries to pedestrians due to the great impact force they exert. Although surveillance cameras are installed around some buildings, it is challenging for humans to capture such events in surveillance videos due to the small size and fast motion of falling objects, as well as the complex background. Therefore, it is necessary to develop methods to automatically detect falling objects around buildings in surveillance videos. To facilitate the investigation of falling object detection, we propose a large, diverse video dataset called FADE (FAlling Object DEtection around Buildings) for the first time. FADE contains 1,881 videos from 18 scenes, featuring 8 falling object categories, 4 weather conditions, and 4 video resolutions. Additionally, we develop a new object detection method called FADE-Net, which effectively leverages motion information and produces small-sized but high-quality proposals for detecting falling objects around buildings. Importantly, our method is extensively evaluated and analyzed by comparing it with the previous approaches used for generic object detection, video object detection, and moving object detection on the FADE dataset. Experimental results show that the proposed FADE-Net significantly outperforms other methods, providing an effective baseline for future research. The dataset and code are publicly available at https://fadedataset.github.io/FADE.github.io/.
This paper investigates image denoising, comparing traditional non-learning-based techniques, represented by Block-Matching 3D (BM3D), with modern learning-based methods, exemplified by NBNet. We assess these approaches across diverse datasets, including CURE-OR, CURE-TSR, SSID+, Set-12, and Chest-Xray, each presenting unique noise challenges. Our analysis employs seven Image Quality Assessment (IQA) metrics and examines the impact on object detection performance. We find that while BM3D excels in scenarios like blur challenges, NBNet is more effective in complex noise environments such as under-exposure and over-exposure. The study reveals the strengths and limitations of each method, providing insights into the effectiveness of different denoising strategies in varied real-world applications.
In recent years, Few-Shot Object Detection (FSOD) has gained widespread attention and made significant progress due to its ability to build models with a good generalization power using extremely limited annotated data. The fine-tuning based paradigm is currently dominating this field, where detectors are initially pre-trained on base classes with sufficient samples and then fine-tuned on novel ones with few samples, but the scarcity of labeled samples of novel classes greatly interferes precisely fitting their data distribution, thus hampering the performance. To address this issue, we propose a new framework for FSOD, namely Prototype-based Soft-labels and Test-Time Learning (PS-TTL). Specifically, we design a Test-Time Learning (TTL) module that employs a mean-teacher network for self-training to discover novel instances from test data, allowing detectors to learn better representations and classifiers for novel classes. Furthermore, we notice that even though relatively low-confidence pseudo-labels exhibit classification confusion, they still tend to recall foreground. We thus develop a Prototype-based Soft-labels (PS) strategy through assessing similarities between low-confidence pseudo-labels and category prototypes as soft-labels to unleash their potential, which substantially mitigates the constraints posed by few-shot samples. Extensive experiments on both the VOC and COCO benchmarks show that PS-TTL achieves the state-of-the-art, highlighting its effectiveness. The code and model are available at https://github.com/gaoyingjay/PS-TTL.
Road infrastructure maintenance in developing countries faces unique challenges due to resource constraints and diverse environmental factors. This study addresses the critical need for efficient, accurate, and locally-relevant pavement distress detection methods in these regions. We present a novel deep learning approach combining YOLO (You Only Look Once) object detection models with a Convolutional Block Attention Module (CBAM) to simultaneously detect and classify multiple pavement distress types. The model demonstrates robust performance in detecting and classifying potholes, longitudinal cracks, alligator cracks, and raveling, with confidence scores ranging from 0.46 to 0.93. While some misclassifications occur in complex scenarios, these provide insights into unique challenges of pavement assessment in developing countries. Additionally, we developed a web-based application for real-time distress detection from images and videos. This research advances automated pavement distress detection and provides a tailored solution for developing countries, potentially improving road safety, optimizing maintenance strategies, and contributing to sustainable transportation infrastructure development.
Object detection is crucial in various cutting-edge applications, such as autonomous vehicles and advanced robotics systems, primarily relying on data from conventional frame-based RGB sensors. However, these sensors often struggle with issues like motion blur and poor performance in challenging lighting conditions. In response to these challenges, event-based cameras have emerged as an innovative paradigm. These cameras, mimicking the human eye, demonstrate superior performance in environments with fast motion and extreme lighting conditions while consuming less power. This study introduces ReYOLOv8, an advanced object detection framework that enhances a leading frame-based detection system with spatiotemporal modeling capabilities. We implemented a low-latency, memory-efficient method for encoding event data to boost the system's performance. We also developed a novel data augmentation technique tailored to leverage the unique attributes of event data, thus improving detection accuracy. Our models outperformed all comparable approaches in the GEN1 dataset, focusing on automotive applications, achieving mean Average Precision (mAP) improvements of 5%, 2.8%, and 2.5% across nano, small, and medium scales, respectively.These enhancements were achieved while reducing the number of trainable parameters by an average of 4.43% and maintaining real-time processing speeds between 9.2ms and 15.5ms. On the PEDRo dataset, which targets robotics applications, our models showed mAP improvements ranging from 9% to 18%, with 14.5x and 3.8x smaller models and an average speed enhancement of 1.67x.