paper-with-me

Papers

Heavy-tailed Distances for Gradient Based Image Descriptors

2011-12-01 · NeurIPS 2011 12 · Yangqing Jia, Trevor Darrell

Many applications in computer vision measure the similarity between images or image patches based on some statistics such as oriented gradients. These are often modeled implicitly or explicitly with a Gaussian noise assumption, leading to the use of the Euclidean distance when comparing image descriptors. In this paper, we show that the statistics of gradient based image descriptors often follow a heavy-tailed distribution, which undermines any principled motivation for the use of Euclidean distances. We advocate for the use of a distance measure based on the likelihood ratio test with appropriate probabilistic models that fit the empirical data distribution. We instantiate this similarity measure with the Gamma-compound-Laplace distribution, and show significant improvement over existing distance measures in the application of SIFT feature matching, at relatively low computational cost.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributions

2021-01-22 · Todd Huster, Jeremy E. J. Cohen, Zinan Lin, Kevin Chan 외

Generative adversarial networks (GANs) are often billed as "universal distribution learners", but precisely what distributions they can represent and learn is still an open question. Heavy-tailed distributions are preval…

EpidemiologyOpen-Ended Question Answering

On Proximal Policy Optimization's Heavy-tailed Gradients

2021-02-20 · Saurabh Garg, Joshua Zhanson, Emilio Parisotto, Adarsh Prasad 외

Modern policy gradient algorithms such as Proximal Policy Optimization (PPO) rely on an arsenal of heuristics, including loss clipping and gradient clipping, to ensure successful learning. These heuristics are reminiscen…

continuous-controlContinuous ControlMuJoCo

Asynchronous Heavy-Tailed Optimization

2026-02-20 · Junfei Sun, Dixi Yao, Xuchen Gong, Tahseen Rabbani 외 arxiv

Heavy-tailed stochastic gradient noise, commonly observed in transformer models, can destabilize the optimization process. Recent works mainly focus on developing and understanding approaches to address heavy-tailed nois…

Local Gradient Hexa Pattern: A Descriptor for Face Recognition and Retrieval

2022-01-03 · Soumendu Chakraborty, Satish Kumar Singh, Pavan Chakraborty

Local descriptors used in face recognition are robust in a sense that these descriptors perform well in varying pose, illumination and lighting conditions. Accuracy of these descriptors depends on the precision of mappin…

Face RecognitionRetrieval

Gradient Normalization Provably Benefits Nonconvex SGD under Heavy-Tailed Noise

2024-10-21 · Tao Sun, Xinwang Liu, Kun Yuan

This paper investigates the roles of gradient normalization and clipping in ensuring the convergence of Stochastic Gradient Descent (SGD) under heavy-tailed noise. While existing approaches consider gradient clipping ind…