Related papers: Extending One-Stage Detection with Open-World Prop…

Modern object detectors have achieved impressive progress under the close-set setup. However, open-set object detection (OSOD) remains challenging since objects of unknown categories are often misclassified to existing known classes. In…

Almost all of the current top-performing object detection networks employ region proposals to guide the search for object instances. State-of-the-art region proposal methods usually need several thousand proposals to get high recall, thus…

We tackle the problem of novel class discovery and localization (NCDL). In this setting, we assume a source dataset with supervision for only some object classes. Instances of other classes need to be discovered, classified, and localized…

Weakly supervised object detection(WSOD) task uses only image-level annotations to train object detection task. WSOD does not require time-consuming instance-level annotations, so the study of this task has attracted more and more…

Open World Object Detection (OWOD) is a novel computer vision task with a considerable challenge, bridging the gap between classic object detection (OD) benchmarks and real-world object detection. In addition to detecting and classifying…

Classical object detectors are incapable of detecting novel class objects that are not encountered before. Regarding this issue, Open-Vocabulary Object Detection (OVOD) is proposed, which aims to detect the objects in the candidate class…

We present AVOD, an Aggregate View Object Detection network for autonomous driving scenarios. The proposed neural network architecture uses LIDAR point clouds and RGB images to generate features that are shared by two subnetworks: a region…

Object detection is a fundamental and challenging problem in aerial and satellite image analysis. More recently, a two-stage detector Faster R-CNN is proposed and demonstrated to be a promising tool for object detection in optical remote…

Conventional training of deep neural networks requires a large number of the annotated image which is a laborious and time-consuming task, particularly for rare objects. Few-shot object detection (FSOD) methods offer a remedy by realizing…

Despite weakly supervised object detection (WSOD) being a promising step toward evading strong instance-level annotations, its capability is confined to closed-set categories within a single training dataset. In this paper, we propose a…

Unsupervised 3D object detection leverages heuristic algorithms to discover potential objects, offering a promising route to reduce annotation costs in autonomous driving. Existing approaches mainly generate pseudo labels and refine them…

A desirable open world recognition (OWR) system requires performing three tasks: (1) Open set recognition (OSR), i.e., classifying the known (classes seen during training) and rejecting the unknown (unseen$/$novel classes) online; (2)…

Accurate 6D object pose estimation is vital for robotics, augmented reality, and scene understanding. For seen objects, high accuracy is often attainable via per-object fine-tuning but generalizing to unseen objects remains a challenge. To…

Deep region-based object detector consists of a region proposal step and a deep object recognition step. In this paper, we make significant improvements on both of the two steps. For region proposal we propose a novel lightweight cascade…

Object proposal algorithms have shown great promise as a first step for object recognition and detection. Good object proposal generation algorithms require high object recall rate as well as low computational cost, because generating…

Object detection has advanced significantly in the closed-set setting, but real-world deployment remains limited by two challenges: poor generalization to unseen categories and insufficient robustness under adverse conditions. Prior…

Open vocabulary object detection (OVD) aims at seeking an optimal object detector capable of recognizing objects from both base and novel categories. Recent advances leverage knowledge distillation to transfer insightful knowledge from…

Open-set object detection (OSOD) aims to detect the known categories and reject unknown objects in a dynamic world, which has achieved significant attention. However, previous approaches only consider this problem in data-abundant…

Referring Expression Comprehension (REC) has become one of the most important tasks in visual reasoning, since it is an essential step for many vision-and-language tasks such as visual question answering. However, it has not been widely…

We address the task of open-world class-agnostic object detection, i.e., detecting every object in an image by learning from a limited number of base object classes. State-of-the-art RGB-based models suffer from overfitting the training…