Related papers: DCDet: Dynamic Cross-based 3D Object Detector
Anchor-free detectors basically formulate object detection as dense classification and regression. For popular anchor-free detectors, it is common to introduce an individual prediction branch to estimate the quality of localization. The…
Label assignment plays a significant role in modern object detection models. Detection models may yield totally different performances with different label assignment strategies. For anchor-based detection models, the IoU (Intersection over…
Rotation detection serves as a fundamental building block in many visual applications involving aerial image, scene text, and face etc. Differing from the dominant regression-based approaches for orientation estimation, this paper explores…
Label assignment has been widely studied in general object detection because of its great impact on detectors' performance. However, none of these works focus on label assignment in dense pedestrian detection. In this paper, we propose a…
Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection. While effective, existing DA methods suffer from a substantial drop in performance…
Detecting arbitrarily oriented tiny objects poses intense challenges to existing detectors, especially for label assignment. Despite the exploration of adaptive label assignment in recent oriented object detectors, the extreme geometry…
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…
Object detection has made tremendous strides in computer vision. Small object detection with appearance degradation is a prominent challenge, especially for aerial observations. To collect sufficient positive/negative samples for heuristic…
Although two-stage object detectors have continuously advanced the state-of-the-art performance in recent years, the training process itself is far from crystal. In this work, we first point out the inconsistency problem between the fixed…
Arbitrary-oriented objects widely appear in natural scenes, aerial photographs, remote sensing images, etc., thus arbitrary-oriented object detection has received considerable attention. Many current rotation detectors use plenty of anchors…
The ambiguous appearance, tiny scale, and fine-grained classes of objects in remote sensing imagery inevitably lead to the noisy annotations in category labels of detection dataset. However, the effects and treatments of the label noises…
Arbitrary-oriented object detection is a relatively emerging but challenging task. Although remarkable progress has been made, there still remain many unsolved issues due to the large diversity of patterns in orientation, scale, aspect…
Supervised 3D Object Detection models have been displaying increasingly better performance in single-domain cases where the training data comes from the same environment and sensor as the testing data. However, in real-world scenarios data…
Detecting tiny objects is one of the main obstacles hindering the development of object detection. The performance of generic object detectors tends to drastically deteriorate on tiny object detection tasks. In this paper, we point out that…
Despite its significant success, object detection in traffic and transportation scenarios requires time-consuming and laborious efforts in acquiring high-quality labeled data. Therefore, Unsupervised Domain Adaptation (UDA) for object…
Object detection is a typical multi-task learning application, which optimizes classification and regression simultaneously. However, classification loss always dominates the multi-task loss in anchor-based methods, hampering the consistent…
Despite the promising results, existing oriented object detection methods usually involve heuristically designed rules, e.g., RRoI generation, rotated NMS. In this paper, we propose an end-to-end framework for oriented object detection,…
Cross-domain object detection is more challenging than object classification since multiple objects exist in an image and the location of each object is unknown in the unlabeled target domain. As a result, when we adapt features of…
While existing semi-supervised object detection (SSOD) methods perform well in general scenes, they encounter challenges in handling oriented objects in aerial images. We experimentally find three gaps between general and oriented object…
Various deep learning models have been developed to segment anatomical structures from medical images, but they typically have poor performance when tested on another target domain with different data distribution. Recently, unsupervised…