Related papers: Rank-DETR for High Quality Object Detection

Automatic Vehicle Detection (AVD) in diverse driving environments presents unique challenges due to varying lighting conditions, road types, and vehicle types. Traditional methods, such as YOLO and Faster R-CNN, often struggle to cope with…

Object detection is a central downstream task used to test if pre-trained network parameters confer benefits, such as improved accuracy or training speed. The complexity of object detection methods can make this benchmarking non-trivial…

Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable…

In the majority of object detection frameworks, the confidence of instance classification is used as the quality criterion of predicted bounding boxes, like the confidence-based ranking in non-maximum suppression (NMS). However, the quality…

3D object detection is a significant task for autonomous driving. Recently with the progress of vision transformers, the 2D object detection problem is being treated with the set-to-set loss. Inspired by these approaches on 2D object…

To achieve accurate 3D object detection at a low cost for autonomous driving, many multi-camera methods have been proposed and solved the occlusion problem of monocular approaches. However, due to the lack of accurate estimated depth,…

Predictive uncertainty estimation is an essential next step for the reliable deployment of deep object detectors in safety-critical tasks. In this work, we focus on estimating predictive distributions for bounding box regression output with…

In real-world applications where confidence is key, like autonomous driving, the accurate detection and appropriate handling of classes differing from those used during training are crucial. Despite the proposal of various unknown object…

Detection identifies objects as axis-aligned boxes in an image. Most successful object detectors enumerate a nearly exhaustive list of potential object locations and classify each. This is wasteful, inefficient, and requires additional…

We propose the task Future Object Detection, in which the goal is to predict the bounding boxes for all visible objects in a future video frame. While this task involves recognizing temporal and kinematic patterns, in addition to the…

In the recent years, we have witnessed a paradigm shift in the field of Computer Vision, with the forthcoming of the transformer architecture. Detection Transformers has become a state of the art solution to object detection and is a…

Rotated object detection is a challenging issue of computer vision field. Loss of spatial information and confusion of parametric order have been the bottleneck for rotated detection accuracy. In this paper, we propose an…

This paper presents a Convolutional Neural Network (CNN) approach for counting and locating objects in high-density imagery. To the best of our knowledge, this is the first object counting and locating method based on a feature map…

Tiny object detection plays a vital role in drone surveillance, remote sensing, and autonomous systems, enabling the identification of small targets across vast landscapes. However, existing methods suffer from inefficient feature leverage…

Modern CNN-based object detectors rely on bounding box regression and non-maximum suppression to localize objects. While the probabilities for class labels naturally reflect classification confidence, localization confidence is absent. This…

Classical Transformer-based line segment detection methods have delivered impressive results. However, we observe that some accurately detected line segments are assigned low confidence scores during prediction, causing them to be ranked…

In object detection with deep neural networks, the box-wise objectness score tends to be overconfident, sometimes even indicating high confidence in presence of inaccurate predictions. Hence, the reliability of the prediction and therefore…

We propose Rank & Sort (RS) Loss, a ranking-based loss function to train deep object detection and instance segmentation methods (i.e. visual detectors). RS Loss supervises the classifier, a sub-network of these methods, to rank each…

Most current detection methods have adopted anchor boxes as regression references. However, the detection performance is sensitive to the setting of the anchor boxes. A proper setting of anchor boxes may vary significantly across different…

Object detection in autonomous driving consists in perceiving and locating instances of objects in multi-dimensional data, such as images or lidar scans. Very recently, multiple works are proposing to evaluate object detectors by measuring…