Corpus ID: 236428836

AA3DNet: Attention Augmented Real Time 3D Object Detection

@article{Sagar2021AA3DNetAA,
  title={AA3DNet: Attention Augmented Real Time 3D Object Detection},
  author={Abhinav Sagar},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.12137}
}
In this work, we address the problem of 3D object detection from point cloud data in real time. For autonomous vehicles to work, it is very important for the perception component to detect the real world objects with both high accuracy and fast inference. We propose a novel neural network architecture along with the training and optimization details for detecting 3D objects using point cloud data. We present anchor design along with custom loss functions used in this work. A combination of… Expand
AASeg: Attention Aware Network for Real Time Semantic Segmentation
TLDR
A new network named Attention Aware Network (AASeg) for real time semantic image segmentation that incorporates spatial and channel information using Spatial Attention and Channel Attention modules respectively and also uses dense local multi-scale context information using Multi Scale Context (MSC) module. Expand
DMSANet: Dual Multi Scale Attention Network
TLDR
A new attention module is proposed that not only achieves the best performance but also has lesser parameters compared to most existing models and can easily be integrated with other convolutional neural networks because of its lightweight nature. Expand

References

SHOWING 1-10 OF 44 REFERENCES
Center-based 3D Object Detection and Tracking
TLDR
This paper uses a keypoint detector to find centers of objects and simply regress to other attributes, including 3D size, 3D orientation, and velocity, in a center-based framework to represent, detect, and track 3D objects as points. Expand
DMSANet: Dual Multi Scale Attention Network
TLDR
A new attention module is proposed that not only achieves the best performance but also has lesser parameters compared to most existing models and can easily be integrated with other convolutional neural networks because of its lightweight nature. Expand
Delving into Localization Errors for Monocular 3D Object Detection
TLDR
This work quantifies the impact introduced by each sub-task and found the ‘localization error’ is the vital factor in restricting monocular 3D detection, and investigates the underlying reasons behind localization errors. Expand
From Points to Parts: 3D Object Detection From Point Cloud With Part-Aware and Part-Aggregation Network
TLDR
This paper extends the preliminary work PointRCNN to a novel and strong point-cloud-based 3D object detection framework, the part-aware and aggregation neural network, which outperforms all existing 3D detection methods and achieves new state-of-the-art on KITTI 3D objects detection dataset by utilizing only the LiDAR point cloud data. Expand
Lidar Point Cloud Guided Monocular 3D Object Detection
TLDR
This paper proposes a general, simple yet effective framework for monocular methods that uses LiDAR point clouds to directly guide the training of monocular 3D detectors, allowing them to learn desired objectives meanwhile eliminating the extra annotation cost. Expand
MonoGRNet: A General Framework for Monocular 3D Object Detection
  • Zengyi Qin, Jinglu Wang, Yan Lu
  • Computer Science, Medicine
  • IEEE transactions on pattern analysis and machine intelligence
  • 2021
TLDR
The task decomposition significantly facilitates the monocular 3D object detection, allowing the target 3D bounding boxes to be efficiently predicted in a single forward pass, without using object proposals, post-processing or the computationally expensive pixel-level depth estimation utilized by previous methods. Expand
Objects are Different: Flexible Monocular 3D Object Detection
TLDR
A flexible framework for monocular 3D object detection which explicitly decouples the truncated objects and adaptively combines multiple approaches for object depth estimation, which outperforms the state-of-the-art method. Expand
AFDet: Anchor Free One Stage 3D Object Detection
TLDR
This work proposes an anchor free and Non-Maximum Suppression free one stage detector called AFDet that can be processed efficiently on a CNN accelerator or a GPU with the simplified post-processing. Expand
DSGN: Deep Stereo Geometry Network for 3D Object Detection
TLDR
The Deep Stereo Geometry Network (DSGN), for the first time, provides a simple and effective one-stage stereo-based 3D detection pipeline that jointly estimates the depth and detects 3D objects in an end-to-end learning manner. Expand
EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection
TLDR
A novel fusion module is proposed to enhance the point features with semantic image features in a point-wise manner without any image annotations to address two critical issues in the 3D detection task, including the exploitation of multiple sensors~ and the inconsistency between the localization and classification confidence. Expand
...
1
2
3
4
5
...