A Systematic IoU-Related Method: Beyond Simplified Regression for Better Localization

• URL: http://arxiv.org/abs/2112.01793v1
• Date: Fri, 3 Dec 2021 09:00:55 GMT
• Title: A Systematic IoU-Related Method: Beyond Simplified Regression for Better Localization
• Authors: Hanyang Peng and Shiqi Yu
• Abstract summary: 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.
• Score: 9.036025934093965
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Four-variable-independent-regression localization losses, such as Smooth-$\ell_1$ Loss, are used by default in modern detectors. Nevertheless, this kind of loss is oversimplified so that it is inconsistent with the final evaluation metric, intersection over union (IoU). Directly employing the standard IoU is also not infeasible, since the constant-zero plateau in the case of non-overlapping boxes and the non-zero gradient at the minimum may make it not trainable. Accordingly, we propose a systematic method to address these problems. Firstly, we propose a new metric, the extended IoU (EIoU), which is well-defined when two boxes are not overlapping and reduced to the standard IoU when overlapping. Secondly, we present the convexification technique (CT) to construct a loss on the basis of EIoU, which can guarantee the gradient at the minimum to be zero. Thirdly, we propose a steady optimization technique (SOT) to make the fractional EIoU loss approaching the minimum more steadily and smoothly. Fourthly, to fully exploit the capability of the EIoU based loss, we introduce an interrelated IoU-predicting head to further boost localization accuracy. With the proposed contributions, the new method incorporated into Faster R-CNN with ResNet50+FPN as the backbone yields \textbf{4.2 mAP} gain on VOC2007 and \textbf{2.3 mAP} gain on COCO2017 over the baseline Smooth-$\ell_1$ Loss, at almost \textbf{no training and inferencing computational cost}. Specifically, the stricter the metric is, the more notable the gain is, improving \textbf{8.2 mAP} on VOC2007 and \textbf{5.4 mAP} on COCO2017 at metric $AP_{90}$.

Related papers

• Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes [29.466981306355066]
  We show that gradient descent with a fixed learning rate $eta$ can only find local minima that represent smooth functions. We also prove a nearly-optimal MSE bound of $widetildeO(n-4/5)$ within the strict interior of the support of the $n$ data points.
  arXiv  Detail & Related papers  (2024-06-10T22:57:27Z)
• 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)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Directly Optimizing IoU for Bounding Box Localization [5.018156030818881]
  This paper presents a novel method to maximize the detection of bounding boxes for the bounding boxes. The Smooth IoU method has shown performance gains over the standard Huber loss. It has been evaluated on the Oxford IIIT, Udacity self-driving car, PA Pets Union, and VWFS Car Damage datasets.
  arXiv  Detail & Related papers  (2023-04-14T17:08:12Z)
• Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism [7.645166402471877]
  We propose an IoU-based loss with a dynamic non-monotonic FM named Wise-IoU (WIoU) This strategy reduces the competitiveness of high-quality anchor boxes while also reducing the harmful gradient generated by low-quality examples. When WIoU is applied to the state-of-the-art real-time detector YOLOv7, the AP-75 on the MS-COCO dataset is improved from 53.03% to 54.50%.
  arXiv  Detail & Related papers  (2023-01-24T14:50:40Z)
• 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)
• Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis [121.9821494461427]
  We show how to significantly reduce the number of neurons required for two-layer ReLU networks. We also prove new lower bounds that improve upon prior work, and that under certain assumptions, are best possible.
  arXiv  Detail & Related papers  (2022-06-26T06:51:31Z)
• Decoupled IoU Regression for Object Detection [31.9114940121939]
  Non-maximum suppression (NMS) is widely used in object detection pipelines for removing duplicated bounding boxes. Inconsistency between the confidence for NMS and the real localization confidence seriously affects detection performance. We propose a novel Decoupled IoU Regression model to handle these problems.
  arXiv  Detail & Related papers  (2022-02-02T04:01:11Z)
• 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)
• DM-VIO: Delayed Marginalization Visual-Inertial Odometry [62.746533939737446]
  We present DM-VIO, a visual-inertial system based on delayed marginalization and pose graph bundle adjustment. We evaluate our system on the EuRoC, TUM-VI, and 4Seasons datasets, which comprise flying drone, large-scale handheld, and automotive scenarios.
  arXiv  Detail & Related papers  (2022-01-11T18:30:37Z)
• Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression [59.72580239998315]
  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.
  arXiv  Detail & Related papers  (2021-10-26T13:09:20Z)

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.