paper-with-me

홈 › Papers

FMRT: Learning Accurate Feature Matching with Reconciliatory Transformer

2023-10-20 · Xinyu Zhang, Li Wang, Zhiqiang Jiang, Kun Dai, Tao Xie, Lei Yang, Wenhao Yu, Yang shen, Jun Li

Local Feature Matching, an essential component of several computer vision tasks (e.g., structure from motion and visual localization), has been effectively settled by Transformer-based methods. However, these methods only integrate long-range context information among keypoints with a fixed receptive field, which constrains the network from reconciling the importance of features with different receptive fields to realize complete image perception, hence limiting the matching accuracy. In addition, these methods utilize a conventional handcrafted encoding approach to integrate the positional information of keypoints into the visual descriptors, which limits the capability of the network to extract reliable positional encoding message. In this study, we propose Feature Matching with Reconciliatory Transformer (FMRT), a novel Transformer-based detector-free method that reconciles different features with multiple receptive fields adaptively and utilizes parallel networks to realize reliable positional encoding. Specifically, FMRT proposes a dedicated Reconciliatory Transformer (RecFormer) that consists of a Global Perception Attention Layer (GPAL) to extract visual descriptors with different receptive fields and integrate global context information under various scales, Perception Weight Layer (PWL) to measure the importance of various receptive fields adaptively, and Local Perception Feed-forward Network (LPFFN) to extract deep aggregated multi-scale local feature representation. Extensive experiments demonstrate that FMRT yields extraordinary performance on multiple benchmarks, including pose estimation, visual localization, homography estimation, and image matching.

📄 PDF Abstract BibTeX arXiv:2310.13605

Code (0)

등록된 구현이 없습니다.

Tasks

Homography EstimationPose EstimationVisual Localization

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Explanation Generation for Contradiction Reconciliation with LLMs

2026-03-24 · Jason Chan, Zhixue Zhao, Robert Gaizauskas arxiv

Existing NLP work commonly treats contradictions as errors to be resolved by choosing which statements to accept or discard. Yet a key aspect of human reasoning in social interactions and professional domains is the abil…

Natural Language InferenceExplanation Generation

Correspondence Transformers With Asymmetric Feature Learning and Matching Flow Super-Resolution

2023-01-01 · CVPR 2023 1 · Yixuan Sun, Dongyang Zhao, Zhangyue Yin, Yiwen Huang 외

This paper solves the problem of learning dense visual correspondences between different object instances of the same category with only sparse annotations. We decompose this pixel-level semantic matching problem int…

Super-Resolution

LoFLAT: Local Feature Matching using Focused Linear Attention Transformer

2024-10-30 · Naijian Cao, Renjie He, Yuchao Dai, Mingyi He

Local feature matching is an essential technique in image matching and plays a critical role in a wide range of vision-based applications. However, existing Transformer-based detector-free local feature matching methods …

ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses

2024-10-30 · Junjie Ni, Guofeng Zhang, Guanglin Li, Yijin Li 외

We tackle the efficiency problem of learning local feature matching. Recent advancements have given rise to purely CNN-based and transformer-based approaches, each augmented with deep learning techniques. While CNN-based…

Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling

2020-12-23 · Vitaly Feldman, Audra McMillan, Kunal Talwar

Recent work of Erlingsson, Feldman, Mironov, Raghunathan, Talwar, and Thakurta [EFMRTT19] demonstrates that random shuffling amplifies differential privacy guarantees of locally randomized data. Such amplification implie…