Related papers: Modification method for single-stage object detect…

3D object detection is one of the most important components in any Self-Driving stack, but current state-of-the-art (SOTA) lidar object detectors require costly & slow manual annotation of 3D bounding boxes to perform well. Recently,…

Recent research on real-time object detectors (e.g., YOLO series) has demonstrated the effectiveness of attention mechanisms for elevating model performance. Nevertheless, existing methods neglect to unifiedly deploy hierarchical attention…

We introduce AnytimeYOLO, a family of variants of the YOLO architecture that enables anytime object detection. Our AnytimeYOLO networks allow for interruptible inference, i.e., they provide a prediction at any point in time, a property…

The rapid progress in machine learning models has significantly boosted the potential for real-world applications such as autonomous vehicles, disease diagnoses, and recognition of emergencies. The performance of many machine learning…

Monitoring animal populations is crucial for assessing the health of ecosystems. Traditional methods, which require extensive fieldwork, are increasingly being supplemented by time-lapse camera-trap imagery combined with an automatic…

A critical object detection task is finetuning an existing model to detect novel objects, but the standard workflow requires bounding box annotations which are time-consuming and expensive to collect. Weakly supervised object detection…

Despite the breakthrough deep learning performances achieved for automatic object detection, small target detection is still a challenging problem, especially when looking at fast and accurate solutions suitable for mobile or edge…

Single Domain Generalization (SDG) tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. While this has been well studied for image classification, the literature on SDG object…

Following recent breakthroughs in convolutional neural networks and monolithic model architectures, state-of-the-art object detection models can reliably and accurately scale into the realm of up to thousands of classes. Things quickly…

One-stage object detectors such as the YOLO family achieve state-of-the-art performance in real-time vision applications but remain heavily reliant on large-scale labeled datasets for training. In this work, we present a systematic study of…

The You Only Look Once (YOLO) architecture is crucial for real-time object detection. However, deploying it in resource-constrained environments such as unmanned aerial vehicles (UAVs) requires efficient transfer learning. Although layer…

Now a days, UAVs such as drones are greatly used for various purposes like that of capturing and target detection from ariel imagery etc. Easy access of these small ariel vehicles to public can cause serious security threats. For instance,…

Non-violent street robberies (snatch-and-run) are difficult to detect automatically because they are brief, subtle, and often indistinguishable from benign human interactions in unconstrained surveillance footage. This paper presents a…

Efficient and accurate annotation of datasets remains a significant challenge for deploying object detection models such as You Only Look Once (YOLO) in real-world applications, particularly in agriculture where rapid decision-making is…

Predominant methods for image-based drone detection frequently rely on employing generic object detection algorithms like YOLOv5. While proficient in identifying drones against homogeneous backgrounds, these algorithms often struggle in…

For realizing safe autonomous driving, the end-to-end delays of real-time object detection systems should be thoroughly analyzed and minimized. However, despite recent development of neural networks with minimized inference delays,…

The recent COCO object detection dataset presents several new challenges for object detection. In particular, it contains objects at a broad range of scales, less prototypical images, and requires more precise localization. To address these…

In this paper, we propose the methods to handle temporal errors during multi-object tracking. Temporal error occurs when objects are occluded or noisy detections appear near the object. In those situations, tracking may fail and various…

Object detection is one of the most important areas in computer vision, which plays a key role in various practical scenarios. Due to limitation of hardware, it is often necessary to sacrifice accuracy to ensure the infer speed of the…

Underwater object detection is critical for oceanic research and industrial safety inspections. However, the complex optical environment and the limited resources of underwater equipment pose significant challenges to achieving high…