paper-with-me

홈 › Papers

3rd Place: A Global and Local Dual Retrieval Solution to Facebook AI Image Similarity Challenge

2021-12-04 · Xinlong Sun, Yangyang Qin, Xuyuan Xu, Guoping Gong, Yang Fang, Yexin Wang

As a basic task of computer vision, image similarity retrieval is facing the challenge of large-scale data and image copy attacks. This paper presents our 3rd place solution to the matching track of Image Similarity Challenge (ISC) 2021 organized by Facebook AI. We propose a multi-branch retrieval method of combining global descriptors and local descriptors to cover all attack cases. Specifically, we attempt many strategies to optimize global descriptors, including abundant data augmentations, self-supervised learning with a single Transformer model, overlay detection preprocessing. Moreover, we introduce the robust SIFT feature and GPU Faiss for local retrieval which makes up for the shortcomings of the global retrieval. Finally, KNN-matching algorithm is used to judge the match and merge scores. We show some ablation experiments of our method, which reveals the complementary advantages of global and local features.

📄 PDF Abstract BibTeX arXiv:2112.02373

Code (1)

sun-xl/ISC2021 공식 구현 pytorch

Tasks

GPURetrievalSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
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 $x$…
Residual Connection 설명 없음
Adam 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

2nd Place Solution to Google Landmark Retrieval 2020

2022-07-11 · Min Yang, Cheng Cui, Xuetong Xue, Hui Ren 외

This paper presents the 2nd place solution to the Google Landmark Retrieval Competition 2020. We propose a training method of global feature model for landmark retrieval without post-processing, such as local feature and…

Retrieval

RadLoc: Radar-based 3-DoF Global Localization via Fast, Robust, and Lightweight Spatial Descriptor Across Diverse Environmental Scenarios

2026-07-09 · Hogyun Kim, Jiwon Choi, Jungwoo Lee, Younggun Cho arxiv

While global localization using spinning radar has gained attention for its robustness to adverse weather and challenging environments, many studies have focused on individual components such as place recognition or pose…

Pose Estimation

LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition

2021-09-17 · Kavisha Vidanapathirana, Milad Ramezani, Peyman Moghadam, Sridha Sridharan 외

Retrieval-based place recognition is an efficient and effective solution for re-localization within a pre-built map, or global data association for Simultaneous Localization and Mapping (SLAM). The accuracy of such an ap…

3D Place RecognitionRetrievalSimultaneous Localization and Mapping

LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis

2018-12-11 · ICCV 2019 10 · Zhe Liu, Shunbo Zhou, Chuanzhe Suo, Yingtian Liu 외

Point cloud based place recognition is still an open issue due to the difficulty in extracting local features from the raw 3D point cloud and generating the global descriptor, and it's even harder in the large-scale dyna…

3D Place RecognitionPoint Cloud RetrievalRetrievalVisual Place Recognition

Improved Bag-of-Words Image Retrieval with Geometric Constraints for Ground Texture Localization

2025-05-16 · Aaron Wilhelm, Nils Napp

Ground texture localization using a downward-facing camera offers a low-cost, high-precision localization solution that is robust to dynamic environments and requires no environmental modification. We present a significa…

Image RetrievalLoop Closure Detection