End-to-End Object Detection with Fully Convolutional Network
- URL: http://arxiv.org/abs/2012.03544v3
- Date: Fri, 26 Mar 2021 03:38:55 GMT
- Title: End-to-End Object Detection with Fully Convolutional Network
- Authors: Jianfeng Wang, Lin Song, Zeming Li, Hongbin Sun, Jian Sun, Nanning
Zheng
- Abstract summary: We introduce a Prediction-aware One-To-One (POTO) label assignment for classification to enable end-to-end detection.
A simple 3D Max Filtering (3DMF) is proposed to utilize the multi-scale features and improve the discriminability of convolutions in the local region.
Our end-to-end framework achieves competitive performance against many state-of-the-art detectors with NMS on COCO and CrowdHuman datasets.
- Score: 71.56728221604158
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Mainstream object detectors based on the fully convolutional network has
achieved impressive performance. While most of them still need a hand-designed
non-maximum suppression (NMS) post-processing, which impedes fully end-to-end
training. In this paper, we give the analysis of discarding NMS, where the
results reveal that a proper label assignment plays a crucial role. To this
end, for fully convolutional detectors, we introduce a Prediction-aware
One-To-One (POTO) label assignment for classification to enable end-to-end
detection, which obtains comparable performance with NMS. Besides, a simple 3D
Max Filtering (3DMF) is proposed to utilize the multi-scale features and
improve the discriminability of convolutions in the local region. With these
techniques, our end-to-end framework achieves competitive performance against
many state-of-the-art detectors with NMS on COCO and CrowdHuman datasets. The
code is available at https://github.com/Megvii-BaseDetection/DeFCN .
Related papers
- Fuzzy-NMS: Improving 3D Object Detection with Fuzzy Classification in
NMS [19.452760776980472]
Non-maximum suppression (NMS) is an essential post-processing module used in many 3D object detection frameworks.
We introduce fuzzy learning into NMS and propose a novel generalized Fuzzy-NMS module to achieve finer candidate bounding box filtering.
arXiv Detail & Related papers (2023-10-21T09:09:03Z) - SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from
Point Cloud [125.9472454212909]
We present a novel Semi-Supervised Domain Adaptation method for 3D object detection (SSDA3D)
SSDA3D includes an Inter-domain Adaptation stage and an Intra-domain Generalization stage.
Experiments show that, with only 10% labeled target data, our SSDA3D can surpass the fully-supervised oracle model with 100% target label.
arXiv Detail & Related papers (2022-12-06T09:32:44Z) - Implicit and Efficient Point Cloud Completion for 3D Single Object
Tracking [9.372859423951349]
We introduce two novel modules, i.e., Adaptive Refine Prediction (ARP) and Target Knowledge Transfer (TKT)
Our model achieves state-of-the-art performance while maintaining a lower computational consumption.
arXiv Detail & Related papers (2022-09-01T15:11:06Z) - Omni-supervised Point Cloud Segmentation via Gradual Receptive Field
Component Reasoning [41.83979510282989]
We bring the first omni-scale supervision method to point cloud segmentation via the proposed gradual Receptive Field Component Reasoning (RFCR)
Our method brings new state-of-the-art performances for S3DIS as well as Semantic3D and ranks the 1st in the ScanNet benchmark among all the point-based methods.
arXiv Detail & Related papers (2021-05-21T08:32:02Z) - Object Detection Made Simpler by Eliminating Heuristic NMS [70.93004137521946]
We show a simple NMS-free, end-to-end object detection framework.
We attain on par or even improved detection accuracy compared with the original one-stage detector.
arXiv Detail & Related papers (2021-01-28T02:38:29Z) - PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object
Detection [57.49788100647103]
LiDAR-based 3D object detection is an important task for autonomous driving.
Current approaches suffer from sparse and partial point clouds of distant and occluded objects.
In this paper, we propose a novel two-stage approach, namely PC-RGNN, dealing with such challenges by two specific solutions.
arXiv Detail & Related papers (2020-12-18T18:06:43Z) - Visibility Guided NMS: Efficient Boosting of Amodal Object Detection in
Crowded Traffic Scenes [7.998326245039892]
Modern 2D object detection frameworks predict multiple bounding boxes per object that are refined using Non-Maximum-Suppression (NMS) to suppress all but one bounding box.
Our novel Visibility Guided NMS (vg-NMS) leverages both pixel-based as well as amodal object detection paradigms and improves the detection performance especially for highly occluded objects with little computational overhead.
We evaluate vg-NMS using KITTI, VIPER as well as the Synscapes dataset and show that it outperforms current state-of-the-art NMS.
arXiv Detail & Related papers (2020-06-15T17:03:23Z) - siaNMS: Non-Maximum Suppression with Siamese Networks for Multi-Camera
3D Object Detection [65.03384167873564]
A siamese network is integrated into the pipeline of a well-known 3D object detector approach.
associations are exploited to enhance the 3D box regression of the object.
The experimental evaluation on the nuScenes dataset shows that the proposed method outperforms traditional NMS approaches.
arXiv Detail & Related papers (2020-02-19T15:32:38Z) - 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.