Non-maximum suppression (NMS) is an essential post-processing module in many 3D object detection frameworks to remove overlapping candidate bounding boxes. However, an overreliance on classification scores and difficu...
详细信息
Non-maximum suppression (NMS) is an essential post-processing module in many 3D object detection frameworks to remove overlapping candidate bounding boxes. However, an overreliance on classification scores and difficulties in determining appropriate thresholds can affect the resulting accuracy directly. To address these issues, we introduce fuzzy learning into NMS and propose a novel generalized Fuzzy-NMS module to achieve finer candidate bounding box filtering. The proposed Fuzzy-NMS module combines the volume and clustering density of candidate bounding boxes, refining them with a fuzzy classification method and optimizing the appropriate suppression thresholds to reduce uncertainty in the NMS process. Adequate validation experiments use the mainstream KITTI and large-scale Waymo 3D object detection benchmarks. The results of these tests demonstrate the proposed Fuzzy-NMS module can improve the accuracy of numerous recently NMS-based detectors significantly, including PointPillars, PV-RCNN, and IA-SSD, etc. This effect is particularly evident for small objects such as pedestrians and bicycles. As a plug-and-play module, Fuzzy-NMS does not need to be retrained and produces no obvious increases in inference time. IEEE
Existing unsupervised domain adaptation approaches primarily focus on reducing the data distribution gap between the source and target domains,often neglecting the influence of class information,leading to inaccurate ...
详细信息
Existing unsupervised domain adaptation approaches primarily focus on reducing the data distribution gap between the source and target domains,often neglecting the influence of class information,leading to inaccurate alignment *** by this observation,this paper proposes an adaptive inter-intra-domain discrepancy method to quantify the intra-class and inter-class discrepancies between the source and target ***,an adaptive factor is introduced to dynamically assess their relative *** upon the proposed adaptive inter-intradomain discrepancy approach,we develop an inter-intradomain alignment network with a class-aware sampling strategy(IDAN-CSS)to distill the feature *** classaware sampling strategy,integrated within IDAN-CSS,facilitates more efficient *** multiple transfer diagnosis cases,we comprehensively demonstrate the feasibility and effectiveness of the proposed IDAN-CSS model.
Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many ...
INTRODUCTION Accurate environment perception is a critical topic in autonomous driving and intelligent *** environmental perception methods mostly rely on on-board ***,limited by the installation height,thereare probl...
INTRODUCTION Accurate environment perception is a critical topic in autonomous driving and intelligent *** environmental perception methods mostly rely on on-board ***,limited by the installation height,thereare problems such as blind spots and unstable long-range perception in vehicle perceptual ***,with the rapid improvement of intelligent infrastructure,it has become possible to use roadside cameras for traffic environment *** from the increased height when compared with on-boardsensors,roadside cameras can obtain a larger perceptual field of view and realize long-range observation.
Sign language (SL) is a mode of communication that, in most cases, relies on visual perception exclusively and uses the visual-gestural modality. The advent of machine learning techniques has expanded the range of pot...
详细信息
This paper introduces a novel approach integrating Differential Evolution (DE) with multi-objective optimization techniques for enhancing Type-1 Takagi-Sugeno-Kang (TSK) fuzzy rule-based systems to attain both fair pr...
详细信息
Learning from Demonstration (LfD) stands out as a powerful tool for swiftly deploying tasks in robotics, distinguished by its capacity to effectively leverage the task expertise of experts. However, contemporary robot...
详细信息
In the past few decades, the demand for assistive robots in the field of healthcare has steadily increased. We conducted research on an autonomous robot system based on imitation learning to assist in liver scans guid...
详细信息
Optogenetics technology has greatly promoted the development of neuroscience. Flexible gene manipulation tools and sensitive light activation methods have provided convenience for neural function research. However, th...
详细信息
Various training-based spatial filtering methods have been proposed to classify steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs). However, many overlook the temporal instability of S...
详细信息
暂无评论