Related papers: ObjectBox: From Centers to Boxes for Anchor-Free O…

We present FoveaBox, an accurate, flexible, and completely anchor-free framework for object detection. While almost all state-of-the-art object detectors utilize predefined anchors to enumerate possible locations, scales and aspect ratios…

Object detection generally requires sliding-window classifiers in tradition or anchor box based predictions in modern deep learning approaches. However, either of these approaches requires tedious configurations in boxes. In this paper, we…

A recent approach for object detection and human pose estimation is to regress bounding boxes or human keypoints from a central point on the object or person. While this center-point regression is simple and efficient, we argue that the…

In this paper, we propose a general approach to optimize anchor boxes for object detection. Nowadays, anchor boxes are widely adopted in state-of-the-art detection frameworks. However, these frameworks usually pre-define anchor box shapes…

In computer vision, object detection is one of most important tasks, which underpins a few instance-level recognition tasks and many downstream applications. Recently one-stage methods have gained much attention over two-stage approaches…

Anchor-based Siamese trackers have achieved remarkable advancements in accuracy, yet the further improvement is restricted by the lagged tracking robustness. We find the underlying reason is that the regression network in anchor-based…

A novel object detection method is presented that handles freely rotated objects of arbitrary sizes, including tiny objects as small as $2\times 2$ pixels. Such tiny objects appear frequently in remotely sensed images, and present a…

Object detection models perform well at localizing and classifying objects that they are shown during training. However, due to the difficulty and cost associated with creating and annotating detection datasets, trained models detect a…

Existing anchor-based and anchor-free object detectors in multi-stage or one-stage pipelines have achieved very promising detection performance. However, they still encounter the design difficulty in hand-crafted 2D anchor definition and…

Modern object detectors rely heavily on rectangular bounding boxes, such as anchors, proposals and the final predictions, to represent objects at various recognition stages. The bounding box is convenient to use but provides only a coarse…

Accurate and fast 3D object detection from point clouds is a key task in autonomous driving. Existing one-stage 3D object detection methods can achieve real-time performance, however, they are dominated by anchor-based detectors which are…

Blackbox transfer attacks for image classifiers have been extensively studied in recent years. In contrast, little progress has been made on transfer attacks for object detectors. Object detectors take a holistic view of the image and the…

Determining positive/negative samples for object detection is known as label assignment. Here we present an anchor-free detector named AutoAssign. It requires little human knowledge and achieves appearance-aware through a fully…

We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3,…

Most of the existing single-stage and two-stage 3D object detectors are anchor-based methods, while the efficient but challenging anchor-free single-stage 3D object detection is not well investigated. Recent studies on 2D object detection…

With the recent development of Semi-Supervised Object Detection (SS-OD) techniques, object detectors can be improved by using a limited amount of labeled data and abundant unlabeled data. However, there are still two challenges that are not…

Most state-of-the-art instance-level human parsing models adopt two-stage anchor-based detectors and, therefore, cannot avoid the heuristic anchor box design and the lack of analysis on a pixel level. To address these two issues, we have…

Anchor-based detectors have been continuously developed for object detection. However, the individual anchor box makes it difficult to predict the boundary's offset accurately. Instead of taking each bounding box as a closed individual, we…

Despite the remarkable accuracy of deep neural networks in object detection, they are costly to train and scale due to supervision requirements. Particularly, learning more object categories typically requires proportionally more bounding…

Oriented object detection in aerial images is a challenging task as the objects in aerial images are displayed in arbitrary directions and are usually densely packed. Current oriented object detection methods mainly rely on two-stage…