Marginalized Generalized IoU (MGIoU): A Unified Objective Function for Optimizing Any Convex Parametric Shapes

• URL: http://arxiv.org/abs/2504.16443v2
• Date: Thu, 24 Apr 2025 01:22:46 GMT
• Title: Marginalized Generalized IoU (MGIoU): A Unified Objective Function for Optimizing Any Convex Parametric Shapes
• Authors: Duy-Tho Le, Trung Pham, Jianfei Cai, Hamid Rezatofighi,
• Abstract summary: Marginalized Generalized IoU (MGIoU) is a novel loss function that overcomes challenges by projecting structured convex shapes onto their unique shape Normals to compute one-dimensional normalized GIoU.<n>Experiments on standard benchmarks demonstrate that MGIoU and MGIoU+ consistently outperform existing losses while reducing loss latency by 10-40x.
• Score: 32.1114758137734
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Optimizing the similarity between parametric shapes is crucial for numerous computer vision tasks, where Intersection over Union (IoU) stands as the canonical measure. However, existing optimization methods exhibit significant shortcomings: regression-based losses like L1/L2 lack correlation with IoU, IoU-based losses are unstable and limited to simple shapes, and task-specific methods are computationally intensive and not generalizable accross domains. As a result, the current landscape of parametric shape objective functions has become scattered, with each domain proposing distinct IoU approximations. To address this, we unify the parametric shape optimization objective functions by introducing Marginalized Generalized IoU (MGIoU), a novel loss function that overcomes these challenges by projecting structured convex shapes onto their unique shape Normals to compute one-dimensional normalized GIoU. MGIoU offers a simple, efficient, fully differentiable approximation strongly correlated with IoU. We then extend MGIoU to MGIoU+ that supports optimizing unstructured convex shapes. Together, MGIoU and MGIoU+ unify parametric shape optimization across diverse applications. Experiments on standard benchmarks demonstrate that MGIoU and MGIoU+ consistently outperform existing losses while reducing loss computation latency by 10-40x. Additionally, MGIoU and MGIoU+ satisfy metric properties and scale-invariance, ensuring robustness as an objective function. We further propose MGIoU- for minimizing overlaps in tasks like collision-free trajectory prediction. Code is available at https://ldtho.github.io/MGIoU

Related papers

• Regularized second-order optimization of tensor-network Born machines [2.8834278113855896]
  Born machines (TNBMs) are quantum-inspired generative models for learning data distributions.<n>We present an improved second-order optimization technique for TNBM training, which significantly enhances convergence rates and the quality of the optimized model.
  arXiv  Detail & Related papers  (2025-01-30T19:00:04Z)
• Encoding arbitrary Ising Hamiltonians on Spatial Photonic Ising Machines [0.0]
  We introduce and experimentally validate a SPIM instance that enables direct control over the full interaction matrix. We demonstrate the conformity of the experimentally measured Ising energy with the theoretically expected values and then proceed to solve both the unweighted and weighted graph problems. Our approach greatly expands the applicability of SPIMs for real-world applications without sacrificing any of the inherent advantages of the system.
  arXiv  Detail & Related papers  (2024-07-12T10:54:07Z)
• Towards Universal Mesh Movement Networks [13.450178050669964]
  We introduce the Universal Mesh Movement Network (UM2N) UM2N can be applied in a non-intrusive, zero-shot manner to move meshes with different size distributions and structures. We evaluate our method on advection and Navier-Stokes based examples, as well as a real-world tsunami simulation case.
  arXiv  Detail & Related papers  (2024-06-29T09:35:12Z)
• Stochastic Optimal Control Matching [53.156277491861985]
  Our work introduces Optimal Control Matching (SOCM), a novel Iterative Diffusion Optimization (IDO) technique for optimal control. The control is learned via a least squares problem by trying to fit a matching vector field. Experimentally, our algorithm achieves lower error than all the existing IDO techniques for optimal control.
  arXiv  Detail & Related papers  (2023-12-04T16:49:43Z)
• ParaFormer: Parallel Attention Transformer for Efficient Feature Matching [8.552303361149612]
  This paper proposes a novel parallel attention model entitled ParaFormer. It fuses features and keypoint positions through the concept of amplitude and phase, and integrates self- and cross-attention in a parallel manner. Experiments on various applications, including homography estimation, pose estimation, and image matching, demonstrate that ParaFormer achieves state-of-the-art performance. The efficient ParaFormer-U variant achieves comparable performance with less than 50% FLOPs of the existing attention-based models.
  arXiv  Detail & Related papers  (2023-03-02T03:29:16Z)
• Effective Invertible Arbitrary Image Rescaling [77.46732646918936]
  Invertible Neural Networks (INN) are able to increase upscaling accuracy significantly by optimizing the downscaling and upscaling cycle jointly. A simple and effective invertible arbitrary rescaling network (IARN) is proposed to achieve arbitrary image rescaling by training only one model in this work. It is shown to achieve a state-of-the-art (SOTA) performance in bidirectional arbitrary rescaling without compromising perceptual quality in LR outputs.
  arXiv  Detail & Related papers  (2022-09-26T22:22:30Z)
• 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)
• Distribution-aware Margin Calibration for Semantic Segmentation in Images [78.65312390695038]
  Jaccard index, also known as Intersection-over-Union (IoU), is one of the most critical evaluation metrics in image semantic segmentation. Direct optimization of IoU score is very difficult because the learning objective is neither differentiable nor decomposable. We propose a margin calibration method, which can be directly used as a learning objective, for an improved generalization of IoU over the data-distribution.
  arXiv  Detail & Related papers  (2021-12-21T22:38:25Z)
• Joint inference and input optimization in equilibrium networks [68.63726855991052]
  deep equilibrium model is a class of models that foregoes traditional network depth and instead computes the output of a network by finding the fixed point of a single nonlinear layer. We show that there is a natural synergy between these two settings. We demonstrate this strategy on various tasks such as training generative models while optimizing over latent codes, training models for inverse problems like denoising and inpainting, adversarial training and gradient based meta-learning.
  arXiv  Detail & Related papers  (2021-11-25T19:59:33Z)
• Edge Federated Learning Via Unit-Modulus Over-The-Air Computation (Extended Version) [64.76619508293966]
  This paper proposes a unit-modulus over-the-air computation (UM-AirComp) framework to facilitate efficient edge federated learning. It uploads simultaneously local model parameters and updates global model parameters via analog beamforming. We demonstrate the implementation of UM-AirComp in a vehicle-to-everything autonomous driving simulation platform.
  arXiv  Detail & Related papers  (2021-01-28T15:10:22Z)

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.