Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection

• URL: http://arxiv.org/abs/2106.06072v1
• Date: Thu, 10 Jun 2021 22:24:31 GMT
• Title: Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection
• Authors: Jeffri M. Llerena, Luis Felipe Zeni, Lucas N. Kristen, Claudio Jung
• Abstract summary: We present a fuzzy representation of object regions using Gaussian distributions, which provides an implicit binary representation as (potentially rotated) ellipses. We also present a similarity measure for the Gaussian distributions based on the Hellinger Distance, which can be viewed as a Probabilistic Intersection-over-Union (ProbIoU)
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most object detection methods use bounding boxes to encode and represent the object shape and location. In this work, we explore a fuzzy representation of object regions using Gaussian distributions, which provides an implicit binary representation as (potentially rotated) ellipses. We also present a similarity measure for the Gaussian distributions based on the Hellinger Distance, which can be viewed as a Probabilistic Intersection-over-Union (ProbIoU). Our experimental results show that the proposed Gaussian representations are closer to annotated segmentation masks in publicly available datasets, and that loss functions based on ProbIoU can be successfully used to regress the parameters of the Gaussian representation. Furthermore, we present a simple mapping scheme from traditional (or rotated) bounding boxes to Gaussian representations, allowing the proposed ProbIoU-based losses to be seamlessly integrated into any object detector.

Related papers

• GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction [55.60972844777044]
  3D semantic occupancy prediction is an important task for robust vision-centric autonomous driving. Most existing methods leverage dense grid-based scene representations, overlooking the spatial sparsity of the driving scenes. We propose a probabilistic Gaussian superposition model which interprets each Gaussian as a probability distribution of its neighborhood being occupied.
  arXiv  Detail & Related papers  (2024-12-05T17:59:58Z)
• Differentiability and Approximation of Probability Functions under Gaussian Mixture Models: A Bayesian Approach [0.0]
  We study probability functions associated with Gaussian mixture models. We use conditional probability distribution to represent the probability function as an integral over the Euclidean sphere. We approximate the probability function using random sampling over the parameter space and the Euclidean sphere.
  arXiv  Detail & Related papers  (2024-11-05T01:36:27Z)
• PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views [116.10577967146762]
  PixelGaussian is an efficient framework for learning generalizable 3D Gaussian reconstruction from arbitrary views. Our method achieves state-of-the-art performance with good generalization to various numbers of views.
  arXiv  Detail & Related papers  (2024-10-24T17:59:58Z)
• GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction [70.65250036489128]
  3D semantic occupancy prediction aims to obtain 3D fine-grained geometry and semantics of the surrounding scene. We propose an object-centric representation to describe 3D scenes with sparse 3D semantic Gaussians. GaussianFormer achieves comparable performance with state-of-the-art methods with only 17.8% - 24.8% of their memory consumption.
  arXiv  Detail & Related papers  (2024-05-27T17:59:51Z)
• Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization [81.29406957201458]
  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.
  arXiv  Detail & Related papers  (2022-09-22T07:50:48Z)
• Generalized Probabilistic U-Net for medical image segementation [3.398241562010881]
  We propose the Generalized Probabilistic U-Net, which extends the Probabilistic U-Net by allowing more general forms of the Gaussian distribution. We study the effect the choice of latent space distribution has on capturing the uncertainty in the reference segmentations using the LIDC-IDRI dataset.
  arXiv  Detail & Related papers  (2022-07-26T13:03:37Z)
• G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection [13.112764410519981]
  We propose a unified Gaussian representation called G-Rep to construct Gaussian distributions for OBB, QBB, and PointSet. G-Rep achieves a unified solution to various representations and problems.
  arXiv  Detail & Related papers  (2022-05-24T05:28:08Z)
• Random Ferns for Semantic Segmentation of PolSAR Images [0.0]
  This paper extends the Random Fern framework to the semantic segmentation of polarimetric synthetic aperture radar images. Two distinct optimization strategies are proposed. Experiments show that results can be achieved that are similar to a more complex Random Forest model.
  arXiv  Detail & Related papers  (2022-02-07T20:22:57Z)
• Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation [72.40827239394565]
  We propose to compute features only at sparsely sampled locations. We then densely reconstruct the feature map with an efficient procedure. The presented network is experimentally shown to save substantial computation while maintaining accuracy over a variety of computer vision tasks.
  arXiv  Detail & Related papers  (2020-03-19T15:36:31Z)
• Block-Approximated Exponential Random Graphs [77.4792558024487]
  An important challenge in the field of exponential random graphs (ERGs) is the fitting of non-trivial ERGs on large graphs. We propose an approximative framework to such non-trivial ERGs that result in dyadic independence (i.e., edge independent) distributions. Our methods are scalable to sparse graphs consisting of millions of nodes.
  arXiv  Detail & Related papers  (2020-02-14T11:42:16Z)

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.