Related papers: Revisiting Feature Alignment for One-stage Object …
Recent works on two-stage cross-domain detection have widely explored the local feature patterns to achieve more accurate adaptation results. These methods heavily rely on the region proposal mechanisms and ROI-based instance-level features…
One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This…
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…
Oriented object detection in aerial images poses a significant challenge due to their varying sizes and orientations. Current state-of-the-art detectors typically rely on either two-stage or one-stage approaches, often employing…
There have been two streams in the 3D detection from point clouds: single-stage methods and two-stage methods. While the former is more computationally efficient, the latter usually provides better detection accuracy. By carefully examining…
Recent researches attempt to improve the detection performance by adopting the idea of cascade for single-stage detectors. In this paper, we analyze and discover that inconsistency is the major factor limiting the performance. The refined…
Objects for detection usually have distinct characteristics in different sub-regions and different aspect ratios. However, in prevalent two-stage object detection methods, Region-of-Interest (RoI) features are extracted by RoI pooling with…
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…
Previous state-of-the-art real-time object detectors have been reported on GPUs which are extremely expensive for processing massive data and in resource-restricted scenarios. Therefore, high efficiency object detectors on CPU-only devices…
Recent advances in camera equipped drone applications and their widespread use increased the demand on vision based object detection algorithms for aerial images. Object detection process is inherently a challenging task as a generic…
Recent one-stage object detectors follow a per-pixel prediction approach that predicts both the object category scores and boundary positions from every single grid location. However, the most suitable positions for inferring different…
Person search aims to simultaneously localize and identify a query person from realistic, uncropped images. To achieve this goal, state-of-the-art models typically add a re-id branch upon two-stage detectors like Faster R-CNN. Owing to the…
Two-stage methods have dominated Human-Object Interaction (HOI) detection for several years. Recently, one-stage HOI detection methods have become popular. In this paper, we aim to explore the essential pros and cons of two-stage and…
Transformer and its variants have shown great potential for various vision tasks in recent years, including image classification, object detection and segmentation. Meanwhile, recent studies also reveal that with proper architecture design,…
In this paper, we propose a Monocular 3D Single Stage object Detector (M3DSSD) with feature alignment and asymmetric non-local attention. Current anchor-based monocular 3D object detection methods suffer from feature mismatching. To…
Object detection in aerial images is an active yet challenging task in computer vision because of the birdview perspective, the highly complex backgrounds, and the variant appearances of objects. Especially when detecting densely packed…
We present a simple yet effective prediction module for a one-stage detector. The main process is conducted in a coarse-to-fine manner. First, the module roughly adjusts the default boxes to well capture the extent of target objects in an…
Recently, object detection in aerial images has gained much attention in computer vision. Different from objects in natural images, aerial objects are often distributed with arbitrary orientation. Therefore, the detector requires more…
Object detection has made substantial progress in the last decade, due to the capability of convolution in extracting local context of objects. However, the scales of objects are diverse and current convolution can only process single-scale…
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…