SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud

• URL: http://arxiv.org/abs/2104.09804v1
• Date: Tue, 20 Apr 2021 07:33:03 GMT
• Title: SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud
• Authors: Wu Zheng, Weiliang Tang, Li Jiang, Chi-Wing Fu
• Abstract summary: We present Self-Ensembling Single-Stage object Detector (SE-SSD) for accurate and efficient 3D object detection in point clouds. Our key focus is on exploiting both soft and hard targets with our formulated constraints. Our SE-SSD attains top performance compared with all prior published works.
• Score: 44.009023567586446
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Self-Ensembling Single-Stage object Detector (SE-SSD) for accurate and efficient 3D object detection in outdoor point clouds. Our key focus is on exploiting both soft and hard targets with our formulated constraints to jointly optimize the model, without introducing extra computation in the inference. Specifically, SE-SSD contains a pair of teacher and student SSDs, in which we design an effective IoU-based matching strategy to filter soft targets from the teacher and formulate a consistency loss to align student predictions with them. Also, to maximize the distilled knowledge for ensembling the teacher, we design a new augmentation scheme to produce shape-aware augmented samples to train the student, aiming to encourage it to infer complete object shapes. Lastly, to better exploit hard targets, we design an ODIoU loss to supervise the student with constraints on the predicted box centers and orientations. Our SE-SSD attains top performance compared with all prior published works. Also, it attains top precisions for car detection in the KITTI benchmark (ranked 1st and 2nd on the BEV and 3D leaderboards, respectively) with an ultra-high inference speed. The code is available at https://github.com/Vegeta2020/SE-SSD.

Related papers

• Cross-Architecture Auxiliary Feature Space Translation for Efficient Few-Shot Personalized Object Detection [28.06000586370357]
  We propose an instance-level personalized object detection strategy called AuXFT. We show that AuXFT reaches a performance of 80% its upper bound at just 32% of the inference time. We validate AuXFT on three publicly available datasets and one in-house benchmark designed for the IPOD task.
  arXiv  Detail & Related papers  (2024-07-01T11:33:53Z)
• Follow the Soldiers with Optimized Single-Shot Multibox Detection and Reinforcement Learning [0.0]
  We build an autonomous system using DeepRacer which will follow a specific person (for our project, a soldier) when they will be moving in any direction. Two main components to accomplish this project is an optimized Single-Shot Multibox Detection (SSD) object detection model and a Reinforcement Learning (RL) model. Experimental results show that SSD Lite gives better performance among these three techniques and exhibits a considerable boost in inference speed (2-3 times) without compromising accuracy.
  arXiv  Detail & Related papers  (2023-08-02T19:08:57Z)
• SOOD: Towards Semi-Supervised Oriented Object Detection [57.05141794402972]
  This paper proposes a novel Semi-supervised Oriented Object Detection model, termed SOOD, built upon the mainstream pseudo-labeling framework. Our experiments show that when trained with the two proposed losses, SOOD surpasses the state-of-the-art SSOD methods under various settings on the DOTA-v1.5 benchmark.
  arXiv  Detail & Related papers  (2023-04-10T11:10:42Z)
• Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection [90.32180043449263]
  State-of-the-art 3D object detectors are usually trained on large-scale datasets with high-quality 3D annotations. A natural remedy is to adopt semi-supervised learning (SSL) by leveraging a limited amount of labeled samples and abundant unlabeled samples. This paper introduces a novel approach of Hierarchical Supervision and Shuffle Data Augmentation (HSSDA), which is a simple yet effective teacher-student framework.
  arXiv  Detail & Related papers  (2023-04-04T02:09:32Z)
• Focus on Your Target: A Dual Teacher-Student Framework for Domain-adaptive Semantic Segmentation [210.46684938698485]
  We study unsupervised domain adaptation (UDA) for semantic segmentation. We find that, by decreasing/increasing the proportion of training samples from the target domain, the 'learning ability' is strengthened/weakened. We propose a novel dual teacher-student (DTS) framework and equip it with a bidirectional learning strategy.
  arXiv  Detail & Related papers  (2023-03-16T05:04:10Z)
• Attention-Based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object Detection [10.84784828447741]
  ADD is an Attention-based Depth knowledge Distillation framework with 3D-aware positional encoding. Credit to our teacher design, our framework is seamless, domain-gap free, easily implementable, and is compatible with object-wise ground-truth depth. We implement our framework on three representative monocular detectors, and we achieve state-of-the-art performance with no additional inference computational cost.
  arXiv  Detail & Related papers  (2022-11-30T06:39:25Z)
• Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding [62.17020485045456]
  It is commonly assumed in semi-supervised learning (SSL) that the unlabeled data are drawn from the same distribution as that of the labeled ones. We propose to selectively utilize unlabeled data through sample weighting, so that only conducive unlabeled data would be prioritized.
  arXiv  Detail & Related papers  (2022-05-02T16:09:17Z)
• Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds [29.762645632148097]
  We propose a highly-efficient single-stage point-based 3D detector called IA-SSD. We exploit two learnable, task-oriented, instance-aware downsampling strategies to hierarchically select the foreground points. Experiments conducted on several large-scale detection benchmarks demonstrate the competitive performance of our IA-SSD.
  arXiv  Detail & Related papers  (2022-03-21T17:14:02Z)
• CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud [40.871850077528485]
  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.
  arXiv  Detail & Related papers  (2020-12-05T12:00:08Z)
• SESS: Self-Ensembling Semi-Supervised 3D Object Detection [138.80825169240302]
  We propose SESS, a self-ensembling semi-supervised 3D object detection framework. Specifically, we design a thorough perturbation scheme to enhance generalization of the network on unlabeled and new unseen data. Our SESS achieves competitive performance compared to the state-of-the-art fully-supervised method by using only 50% labeled data.
  arXiv  Detail & Related papers  (2019-12-26T08:48:04Z)

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.