Focal and Efficient IOU Loss for Accurate Bounding Box Regression

• URL: http://arxiv.org/abs/2101.08158v1
• Date: Wed, 20 Jan 2021 14:33:58 GMT
• Title: Focal and Efficient IOU Loss for Accurate Bounding Box Regression
• Authors: Yi-Fan Zhang, Weiqiang Ren, Zhang Zhang, Zhen Jia, Liang Wang, Tieniu Tan
• Abstract summary: 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.
• Score: 63.14659624634066
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In object detection, bounding box regression (BBR) is a crucial step that determines the object localization performance. However, we find that 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. (ii) Most of the loss functions ignore the imbalance problem in BBR that the large number of anchor boxes which have small overlaps with the target boxes contribute most to the optimization of BBR. To mitigate the adverse effects caused thereby, we perform thorough studies to exploit the potential of BBR losses in this paper. Firstly, an Efficient Intersection over Union (EIOU) loss is proposed, which explicitly measures the discrepancies of three geometric factors in BBR, i.e., the overlap area, the central point and the side length. After that, we state the Effective Example Mining (EEM) problem and propose a regression version of focal loss to make the regression process focus on high-quality anchor boxes. Finally, the above two parts are combined to obtain a new loss function, namely Focal-EIOU loss. Extensive experiments on both synthetic and real datasets are performed. Notable superiorities on both the convergence speed and the localization accuracy can be achieved over other BBR losses.

Related papers

• 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)
• Class Anchor Margin Loss for Content-Based Image Retrieval [97.81742911657497]
  We propose a novel repeller-attractor loss that falls in the metric learning paradigm, yet directly optimize for the L2 metric without the need of generating pairs. We evaluate the proposed objective in the context of few-shot and full-set training on the CBIR task, by using both convolutional and transformer architectures.
  arXiv  Detail & Related papers  (2023-06-01T12:53:10Z)
• Improving Segmentation of Objects with Varying Sizes in Biomedical Images using Instance-wise and Center-of-Instance Segmentation Loss Function [0.3437656066916039]
  We propose a novel two-component loss for biomedical image segmentation tasks called the Instance-wise and Center-of-Instance (ICI) loss. The ICI loss addresses the instance imbalance problem commonly encountered when using pixel-wise loss functions such as the Dice loss.
  arXiv  Detail & Related papers  (2023-04-13T02:53:50Z)
• Optimized Hybrid Focal Margin Loss for Crack Segmentation [1.8492669447784602]
  We propose a novel hybrid focal loss to handle extreme class imbalance and prevent overfitting for crack segmentation. Our experiments demonstrate that the focal margin component can significantly increase the IoU of cracks by 0.43 on DeepCrack-DB and 0.44 on our PanelCrack dataset.
  arXiv  Detail & Related papers  (2023-02-09T01:26:38Z)
• 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)
• Benchmarking Deep AUROC Optimization: Loss Functions and Algorithmic Choices [37.559461866831754]
  We benchmark a variety of loss functions with different algorithmic choices for deep AUROC optimization problem. We highlight the essential choices such as positive sampling rate, regularization, normalization/activation, and weights. Our findings show that although Adam-type method is more competitive from training perspective, but it does not outperform others from testing perspective.
  arXiv  Detail & Related papers  (2022-03-27T00:47:00Z)
• 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)
• 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)
• Learning with Multiclass AUC: Theory and Algorithms [141.63211412386283]
  Area under the ROC curve (AUC) is a well-known ranking metric for problems such as imbalanced learning and recommender systems. In this paper, we start an early trial to consider the problem of learning multiclass scoring functions via optimizing multiclass AUC metrics.
  arXiv  Detail & Related papers  (2021-07-28T05:18:10Z)
• PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments [33.27663718573774]
  An oriented bounding box (OBB) can better target rotated objects by reducing the overlap with background areas. Existing OBB approaches are mostly built on horizontal bounding box detectors by introducing an additional dimension optimized by a distance loss. A novel loss, Pixels-IoU (PIoU) Loss, is formulated to exploit both the angle and IoU for accurate OBB regression.
  arXiv  Detail & Related papers  (2020-07-19T03:51:59Z)

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.