CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud

• URL: http://arxiv.org/abs/2012.03015v1
• Date: Sat, 5 Dec 2020 12:00:08 GMT
• Title: CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud
• Authors: Wu Zheng, Weiliang Tang, Sijin Chen, Li Jiang, Chi-Wing Fu
• Abstract summary: We present a new single-stage detector named the Confident IoU-Aware Single-Stage object Detector (CIA-SSD) CIA-SSD adaptively fuses high-level abstract semantic features and low-level spatial features for accurate predictions of bounding boxes and classification confidence. It attains top performance in terms of the official ranking metric and above 32 FPS inference speed.
• Score: 40.871850077528485
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing single-stage detectors for locating objects in point clouds often treat object localization and category classification as separate tasks, so the localization accuracy and classification confidence may not well align. To address this issue, we present a new single-stage detector named the Confident IoU-Aware Single-Stage object Detector (CIA-SSD). First, we design the lightweight Spatial-Semantic Feature Aggregation module to adaptively fuse high-level abstract semantic features and low-level spatial features for accurate predictions of bounding boxes and classification confidence. Also, the predicted confidence is further rectified with our designed IoU-aware confidence rectification module to make the confidence more consistent with the localization accuracy. Based on the rectified confidence, we further formulate the Distance-variant IoU-weighted NMS to obtain smoother regressions and avoid redundant predictions. We experiment CIA-SSD on 3D car detection in the KITTI test set and show that it attains top performance in terms of the official ranking metric (moderate AP 80.28%) and above 32 FPS inference speed, outperforming all prior single-stage detectors. The code is available at https://github.com/Vegeta2020/CIA-SSD.

Related papers

• NIV-SSD: Neighbor IoU-Voting Single-Stage Object Detector From Point Cloud [17.134983202997034]
  Previous single-stage detectors typically suffer the misalignment between localization accuracy and classification confidence. We introduce a novel rectification method named neighbor IoU-voting (NIV) strategy. To alleviate the imbalance of detection accuracy for complete objects with dense points, we propose a new data augmentation scheme named object resampling.
  arXiv  Detail & Related papers  (2024-01-23T02:25:23Z)
• ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing [32.679280923208715]
  Unsupervised Domain Adaptation (UDA) for object detection aims to adapt a model trained on a source domain to detect instances from a new target domain for which annotations are not available. We propose ConfMix, the first method that introduces a sample mixing strategy based on region-level detection confidence for adaptive object detector learning.
  arXiv  Detail & Related papers  (2022-10-20T19:16:39Z)
• AGO-Net: Association-Guided 3D Point Cloud Object Detection Network [86.10213302724085]
  We propose a novel 3D detection framework that associates intact features for objects via domain adaptation. We achieve new state-of-the-art performance on the KITTI 3D detection benchmark in both accuracy and speed.
  arXiv  Detail & Related papers  (2022-08-24T16:54:38Z)
• Decoupled IoU Regression for Object Detection [31.9114940121939]
  Non-maximum suppression (NMS) is widely used in object detection pipelines for removing duplicated bounding boxes. Inconsistency between the confidence for NMS and the real localization confidence seriously affects detection performance. We propose a novel Decoupled IoU Regression model to handle these problems.
  arXiv  Detail & Related papers  (2022-02-02T04:01:11Z)
• CertainNet: Sampling-free Uncertainty Estimation for Object Detection [65.28989536741658]
  Estimating the uncertainty of a neural network plays a fundamental role in safety-critical settings. In this work, we propose a novel sampling-free uncertainty estimation method for object detection. We call it CertainNet, and it is the first to provide separate uncertainties for each output signal: objectness, class, location and size.
  arXiv  Detail & Related papers  (2021-10-04T17:59:31Z)
• Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections [50.096540945099704]
  We propose a novel ensemble called the Probabilistic Ranking Aware Ensemble (PRAE) that refines the confidence of bounding boxes from detectors. We also introduce a bandit approach to address the confidence imbalance problem caused by the need to deal with different numbers of boxes.
  arXiv  Detail & Related papers  (2021-05-07T09:37:06Z)
• Uncertainty-Aware Deep Calibrated Salient Object Detection [74.58153220370527]
  Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy. These methods overlook the gap between network accuracy and prediction confidence, known as the confidence uncalibration problem. We introduce an uncertaintyaware deep SOD network, and propose two strategies to prevent deep SOD networks from being overconfident.
  arXiv  Detail & Related papers  (2020-12-10T23:28:36Z)
• 3D IoU-Net: IoU Guided 3D Object Detector for Point Clouds [68.44740333471792]
  We add a 3D IoU prediction branch to the regular classification and regression branches. We propose a 3D IoU-Net with IoU sensitive feature learning and an IoU alignment operation. The experimental results on the KITTI car detection benchmark show that 3D IoU-Net with IoU perception achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-04-10T09:24:29Z)
• Seeing without Looking: Contextual Rescoring of Object Detections for AP Maximization [4.346179456029563]
  We propose to incorporate context in object detection by post-processing the output of an arbitrary detector. Rescoring is done by conditioning on contextual information from the entire set of detections. We show that AP can be improved by simply reassigning the detection confidence values.
  arXiv  Detail & Related papers  (2019-12-27T18:56:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.