Intersection over Union with smoothing for bounding box regression

• URL: http://arxiv.org/abs/2303.15067v2
• Date: Tue, 28 Mar 2023 10:21:45 GMT
• Title: Intersection over Union with smoothing for bounding box regression
• Authors: Petra \v{S}tevuli\'akov\'a, Petr Hurtik
• Abstract summary: We focus on the construction of a loss function for the bounding box regression. The Intersection over Union (IoU) metric is improved to converge faster. We experimentally show that the proposed loss function is robust with respect to the noise in the dimension of ground truth bounding boxes.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We focus on the construction of a loss function for the bounding box regression. The Intersection over Union (IoU) metric is improved to converge faster, to make the surface of the loss function smooth and continuous over the whole searched space, and to reach a more precise approximation of the labels. The main principle is adding a smoothing part to the original IoU, where the smoothing part is given by a linear space with values that increases from the ground truth bounding box to the border of the input image, and thus covers the whole spatial search space. We show the motivation and formalism behind this loss function and experimentally prove that it outperforms IoU, DIoU, CIoU, and SIoU by a large margin. We experimentally show that the proposed loss function is robust with respect to the noise in the dimension of ground truth bounding boxes. The reference implementation is available at gitlab.com/irafm-ai/smoothing-iou.

Related papers

• Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Box [10.03001043843768]
  We propose Inner-IoU loss, which calculates IoU loss through auxiliary bounding boxes. For different datasets and detectors, we introduce a scaling factor ratio to control the scale size of the auxiliary bounding boxes. Finally, integrate Inner-IoU into the existing IoU-based loss functions for simulation and comparative experiments.
  arXiv  Detail & Related papers  (2023-11-06T05:14:24Z)
• 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)
• MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression [0.0]
  We propose a novel bounding box similarity comparison metric MPDIoU. The MPDIoU loss function is applied to state-of-the-art instance segmentation (e.g., YOLACT) and object detection (e.g., YOLOv7) model trained on PASCAL VOC, MS COCO, and IIIT5k.
  arXiv  Detail & Related papers  (2023-07-14T23:54:49Z)
• The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks [53.95175206863992]
  We study the type of solutions to which gradient descent converges when used to train a single hidden-layer multivariate ReLU network with the quadratic loss. We prove that although shallow ReLU networks are universal approximators, stable shallow networks are not.
  arXiv  Detail & Related papers  (2023-06-30T09:17:39Z)
• SIoU Loss: More Powerful Learning for Bounding Box Regression [0.0]
  Loss function SIoU was suggested, where penalty metrics were redefined considering the angle of the vector between the desired regression. Applied to conventional Neural Networks and datasets it is shown that SIoU improves both the speed of training and the accuracy of the inference.
  arXiv  Detail & Related papers  (2022-05-25T12:46:21Z)
• Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation [56.44946660061753]
  This paper proposes a universal regularization technique called maximum spatial perturbation consistency (MSPC) MSPC enforces a spatial perturbation function (T ) and the translation operator (G) to be commutative (i.e., TG = GT ) Our method outperforms the state-of-the-art methods on most I2I benchmarks.
  arXiv  Detail & Related papers  (2022-03-23T19:59:04Z)
• Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields [53.31927549039624]
  We show that a piecewise discretization preserves better contrast from existing discretization problems. We apply this theory to the problem of matching two images.
  arXiv  Detail & Related papers  (2021-07-13T12:31:06Z)
• GBHT: Gradient Boosting Histogram Transform for Density Estimation [73.94900378709023]
  We propose a density estimation algorithm called textitGradient Boosting Histogram Transform (GBHT) We make the first attempt to theoretically explain why boosting can enhance the performance of its base learners for density estimation problems.
  arXiv  Detail & Related papers  (2021-06-10T13:40:28Z)
• SCALoss: Side and Corner Aligned Loss for Bounding Box Regression [29.275260127860783]
  We propose Side Overlap (SO) loss by maximizing the side overlap of two bounding boxes, which puts more penalty for low overlapping bounding box cases. To speed up the convergence, the Corner Distance (CD) is added into the objective function. We get a new regression objective function, Side and Corner Align Loss (SCALoss)
  arXiv  Detail & Related papers  (2021-04-01T13:46:35Z)
• Federated Functional Gradient Boosting [75.06942944563572]
  We study functional minimization in Federated Learning. For both FFGB.C and FFGB.L, the radii of convergence shrink to zero as the feature distributions become more homogeneous.
  arXiv  Detail & Related papers  (2021-03-11T21:49:19Z)
• 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)

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.