Detecting Rotated Objects as Gaussian Distributions and Its 3-D
Generalization
- URL: http://arxiv.org/abs/2209.10839v1
- Date: Thu, 22 Sep 2022 07:50:48 GMT
- Title: Detecting Rotated Objects as Gaussian Distributions and Its 3-D
Generalization
- Authors: Xue Yang, Gefan Zhang, Xiaojiang Yang, Yue Zhou, Wentao Wang, Jin
Tang, Tao He, Junchi Yan
- Abstract summary: Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects.
We argue that such a mechanism has fundamental limitations in building an effective regression loss for rotation detection.
We propose to model the rotated objects as Gaussian distributions.
We extend our approach from 2-D to 3-D with a tailored algorithm design to handle the heading estimation.
- Score: 81.29406957201458
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Existing detection methods commonly use a parameterized bounding box (BBox)
to model and detect (horizontal) objects and an additional rotation angle
parameter is used for rotated objects. We argue that such a mechanism has
fundamental limitations in building an effective regression loss for rotation
detection, especially for high-precision detection with high IoU (e.g. 0.75).
Instead, we propose to model the rotated objects as Gaussian distributions. A
direct advantage is that our new regression loss regarding the distance between
two Gaussians e.g. Kullback-Leibler Divergence (KLD), can well align the actual
detection performance metric, which is not well addressed in existing methods.
Moreover, the two bottlenecks i.e. boundary discontinuity and square-like
problem also disappear. We also propose an efficient Gaussian metric-based
label assignment strategy to further boost the performance. Interestingly, by
analyzing the BBox parameters' gradients under our Gaussian-based KLD loss, we
show that these parameters are dynamically updated with interpretable physical
meaning, which help explain the effectiveness of our approach, especially for
high-precision detection. We extend our approach from 2-D to 3-D with a
tailored algorithm design to handle the heading estimation, and experimental
results on twelve public datasets (2-D/3-D, aerial/text/face images) with
various base detectors show its superiority.
Related papers
- R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection [12.207437451118036]
3D anomaly detection plays a crucial role in monitoring parts for localized inherent defects in precision manufacturing.
Embedding-based and reconstruction-based approaches are among the most popular and successful methods.
We propose R3D-AD, reconstructing anomalous point clouds by diffusion model for precise 3D anomaly detection.
arXiv Detail & Related papers (2024-07-15T16:10:58Z) - DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detection [42.07920565812081]
We propose a novel post-training weight pruning scheme for 3D object detection.
It determines redundant parameters in the pretrained model that lead to minimal distortion in both locality and confidence.
This framework aims to minimize detection distortion of network output to maximally maintain detection precision.
arXiv Detail & Related papers (2024-07-02T09:33:32Z) - Edge Based Oriented Object Detection [8.075609633483248]
We propose a unique loss function based on edge gradients to enhance the detection accuracy of oriented objects.
We achieve a mAP increase of 1.3% on the DOTA dataset.
arXiv Detail & Related papers (2023-09-15T09:19:38Z) - The KFIoU Loss for Rotated Object Detection [115.334070064346]
In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss.
Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU.
The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
arXiv Detail & Related papers (2022-01-29T10:54:57Z) - Learning High-Precision Bounding Box for Rotated Object Detection via
Kullback-Leibler Divergence [100.6913091147422]
Existing rotated object detectors are mostly inherited from the horizontal detection paradigm.
In this paper, we are motivated to change the design of rotation regression loss from induction paradigm to deduction methodology.
arXiv Detail & Related papers (2021-06-03T14:29:19Z) - Rethinking Rotated Object Detection with Gaussian Wasserstein Distance
Loss [111.8807588392563]
Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design.
We propose a novel regression loss based on Gaussian Wasserstein distance as a fundamental approach to solve the problem.
arXiv Detail & Related papers (2021-01-28T12:04:35Z) - Reinforced Axial Refinement Network for Monocular 3D Object Detection [160.34246529816085]
Monocular 3D object detection aims to extract the 3D position and properties of objects from a 2D input image.
Conventional approaches sample 3D bounding boxes from the space and infer the relationship between the target object and each of them, however, the probability of effective samples is relatively small in the 3D space.
We propose to start with an initial prediction and refine it gradually towards the ground truth, with only one 3d parameter changed in each step.
This requires designing a policy which gets a reward after several steps, and thus we adopt reinforcement learning to optimize it.
arXiv Detail & Related papers (2020-08-31T17:10:48Z) - Robust 6D Object Pose Estimation by Learning RGB-D Features [59.580366107770764]
We propose a novel discrete-continuous formulation for rotation regression to resolve this local-optimum problem.
We uniformly sample rotation anchors in SO(3), and predict a constrained deviation from each anchor to the target, as well as uncertainty scores for selecting the best prediction.
Experiments on two benchmarks: LINEMOD and YCB-Video, show that the proposed method outperforms state-of-the-art approaches.
arXiv Detail & Related papers (2020-02-29T06:24:55Z)
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.