Related papers: Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression

Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression

URL: http://arxiv.org/abs/2110.13675v1
Date: Tue, 26 Oct 2021 13:09:20 GMT
Title: Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression
Authors: Jiabo He, Sarah Erfani, Xingjun Ma, James Bailey, Ying Chi, Xian-Sheng Hua
Abstract summary: We generalize existing IoU-based losses to a new family of power IoU losses that have a power IoU term and an additional power regularization term. Experiments on multiple object detection benchmarks and models demonstrate that $alpha$-IoU losses can surpass existing IoU-based losses by a noticeable performance margin.
Score: 59.72580239998315
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Bounding box (bbox) regression is a fundamental task in computer vision. So far, the most commonly used loss functions for bbox regression are the Intersection over Union (IoU) loss and its variants. In this paper, we generalize existing IoU-based losses to a new family of power IoU losses that have a power IoU term and an additional power regularization term with a single power parameter $\alpha$. We call this new family of losses the $\alpha$-IoU losses and analyze properties such as order preservingness and loss/gradient reweighting. Experiments on multiple object detection benchmarks and models demonstrate that $\alpha$-IoU losses, 1) can surpass existing IoU-based losses by a noticeable performance margin; 2) offer detectors more flexibility in achieving different levels of bbox regression accuracy by modulating $\alpha$; and 3) are more robust to small datasets and noisy bboxes.

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)
Rethinking IoU-based Optimization for Single-stage 3D Object Detection [103.83141677242871]
We propose a Rotation-Decoupled IoU (RDIoU) method that can mitigate the rotation-sensitivity issue. Our RDIoU simplifies the complex interactions of regression parameters by decoupling the rotation variable as an independent term.
arXiv Detail & Related papers (2022-07-19T15:35:23Z)
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)
A Systematic IoU-Related Method: Beyond Simplified Regression for Better Localization [9.036025934093965]
We propose a new metric, the extended IoU, which is well-defined when two boxes are not overlapping and reduced to the standard IoU when overlapping. Thirdly, we propose a steady optimization technique (SOT) to make the fractional EIoU loss approaching the minimum more steadily and smoothly.
arXiv Detail & Related papers (2021-12-03T09:00:55Z)
Towards an Understanding of Benign Overfitting in Neural Networks [104.2956323934544]
Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss. We examine how these benign overfitting phenomena occur in a two-layer neural network setting. We show that it is possible for the two-layer ReLU network interpolator to achieve a near minimax-optimal learning rate.
arXiv Detail & Related papers (2021-06-06T19:08:53Z)
Focal and Efficient IOU Loss for Accurate Bounding Box Regression [63.14659624634066]
In object detection, bounding box regression (BBR) is a crucial step that determines the object localization performance. Most previous loss functions for BBR have two main drawbacks: (i) Both $ell_n$-norm and IOU-based loss functions are inefficient to depict the objective of BBR, which leads to slow convergence and inaccurate regression results.
arXiv Detail & Related papers (2021-01-20T14:33:58Z)
Adaptive Weighted Discriminator for Training Generative Adversarial Networks [11.68198403603969]
We introduce a new family of discriminator loss functions that adopts a weighted sum of real and fake parts. Our method can be potentially applied to any discriminator model with a loss that is a sum of the real and fake parts.
arXiv Detail & Related papers (2020-12-05T23:55:42Z)
$\sigma^2$R Loss: a Weighted Loss by Multiplicative Factors using Sigmoidal Functions [0.9569316316728905]
We introduce a new loss function called squared reduction loss ($sigma2$R loss), which is regulated by a sigmoid function to inflate/deflate the error per instance. Our loss has clear intuition and geometric interpretation, we demonstrate by experiments the effectiveness of our proposal.
arXiv Detail & Related papers (2020-09-18T12:34:40Z)
Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation [91.12575065731883]
We propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression (NMS) The training of deep models using CIoU loss results in consistent AP and AR improvements in comparison to widely adopted $ell_n$-norm loss and IoU-based loss. Cluster-NMS is very efficient due to its pure GPU implementation, and geometric factors can be incorporated to improve both AP and AR.
arXiv Detail & Related papers (2020-05-07T16:00:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.