paper-with-me

홈 › Papers

A Revisit of the Normalized Eight-Point Algorithm and A Self-Supervised Deep Solution

2023-04-21 · Bin Fan, Yuchao Dai, Yongduek Seo, Mingyi He

The normalized eight-point algorithm has been widely viewed as the cornerstone in two-view geometry computation, where the seminal Hartley's normalization has greatly improved the performance of the direct linear transformation algorithm. A natural question is, whether there exists and how to find other normalization methods that may further improve the performance as per each input sample. In this paper, we provide a novel perspective and propose two contributions to this fundamental problem: 1) we revisit the normalized eight-point algorithm and make a theoretical contribution by presenting the existence of different and better normalization algorithms; 2) we introduce a deep convolutional neural network with a self-supervised learning strategy for normalization. Given eight pairs of correspondences, our network directly predicts the normalization matrices, thus learning to normalize each input sample. Our learning-based normalization module can be integrated with both traditional (e.g., RANSAC) and deep learning frameworks (affording good interpretability) with minimal effort. Extensive experiments on both synthetic and real images demonstrate the effectiveness of our proposed approach.

📄 PDF Abstract BibTeX arXiv:2304.10771

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learning

Similar Papers 제목 키워드 기반

Superpixel Segmentation Using Linear Spectral Clustering

2015-06-01 · CVPR 2015 6 · Zhengqin Li, Jiansheng Chen

We present in this paper a superpixel segmentation algorithm called Linear Spectral Clustering (LSC), which produces compact and uniform superpixels with low computational costs. Basically, a normalized cuts formulation …

ClusteringImage SegmentationSegmentationSemantic Segmentation+1

Revisiting Weighted Aggregation in Federated Learning with Neural Networks

2023-02-14 · Zexi Li, Tao Lin, Xinyi Shang, Chao Wu

In federated learning (FL), weighted aggregation of local models is conducted to generate a global model, and the aggregation weights are normalized (the sum of weights is 1) and proportional to the local data sizes. In …

Federated Learning

Revisiting Checkpoint Averaging for Neural Machine Translation

2022-10-21 · Yingbo Gao, Christian Herold, Zijian Yang, Hermann Ney

Checkpoint averaging is a simple and effective method to boost the performance of converged neural machine translation models. The calculation is cheap to perform and the fact that the translation improvement almost come…

Machine TranslationTranslation

Path-SGD: Path-Normalized Optimization in Deep Neural Networks

2015-06-08 · NeurIPS 2015 12 · Behnam Neyshabur, Ruslan Salakhutdinov, Nathan Srebro

We revisit the choice of SGD for training deep neural networks by reconsidering the appropriate geometry in which to optimize the weights. We argue for a geometry invariant to rescaling of weights that does not affect th…

Learning Rate Transfer in Normalized Transformers

2026-04-29 · Boris Shigida, Boris Hanin, Andrey Gromov arxiv

The Normalized Transformer, or nGPT (arXiv:2410.01131) achieves impressive training speedups and does not require weight decay or learning rate warmup. However, despite having hyperparameters that explicitly scale with m…