paper-with-me

홈 › Papers

RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval

2022-06-17 · Yihan Wu, Hongyang Zhang, Heng Huang

Recent research works have shown that image retrieval models are vulnerable to adversarial attacks, where slightly modified test inputs could lead to problematic retrieval results. In this paper, we aim to design a provably robust image retrieval model which keeps the most important evaluation metric Recall@1 invariant to adversarial perturbation. We propose the first 1-nearest neighbor (NN) image retrieval algorithm, RetrievalGuard, which is provably robust against adversarial perturbations within an $\ell_2$ ball of calculable radius. The challenge is to design a provably robust algorithm that takes into consideration the 1-NN search and the high-dimensional nature of the embedding space. Algorithmically, given a base retrieval model and a query sample, we build a smoothed retrieval model by carefully analyzing the 1-NN search procedure in the high-dimensional embedding space. We show that the smoothed retrieval model has bounded Lipschitz constant and thus the retrieval score is invariant to $\ell_2$ adversarial perturbations. Experiments on image retrieval tasks validate the robustness of our RetrievalGuard method.

📄 PDF Abstract BibTeX arXiv:2206.11225

Code (0)

등록된 구현이 없습니다.

Tasks

Image RetrievalRetrieval

Methods 이 논문이 사용한 방법론

Test 설명 없음
BASE 설명 없음

Similar Papers 제목 키워드 기반

DistillPose: Lightweight Camera Localization Using Auxiliary Learning

2021-08-09 · Yehya Abouelnaga, Mai Bui, Slobodan Ilic

We propose a lightweight retrieval-based pipeline to predict 6DOF camera poses from RGB images. Our pipeline uses a convolutional neural network (CNN) to encode a query image as a feature vector. A nearest neighbor looku…

Auxiliary LearningCamera LocalizationInformation RetrievalPose Prediction+1

Distance Adaptive Beam Search for Provably Accurate Graph-Based Nearest Neighbor Search

2025-05-21 · Yousef Al-Jazzazi, Haya Diwan, Jinrui Gou, Cameron Musco 외

Nearest neighbor search is central in machine learning, information retrieval, and databases. For high-dimensional datasets, graph-based methods such as HNSW, DiskANN, and NSG have become popular thanks to their empirica…

Information Retrieval

Medical Image Retrieval via Nearest Neighbor Search on Pre-trained Image Features

2022-10-05 · Deepak Gupta, Russell Loane, Soumya Gayen, Dina Demner-Fushman

Nearest neighbor search (NNS) aims to locate the points in high-dimensional space that is closest to the query point. The brute-force approach for finding the nearest neighbor becomes computationally infeasible when the …

Image RetrievalMedical Image RetrievalRetrieval

Yes, we CANN: Constrained Approximate Nearest Neighbors for local feature-based visual localization

2023-06-15 · ICCV 2023 1 · Dror Aiger, André Araujo, Simon Lynen

Large-scale visual localization systems continue to rely on 3D point clouds built from image collections using structure-from-motion. While the 3D points in these models are represented using local image features, direct…

Image RetrievalRetrievalVisual Localization

Nearest Neighbor Normalization Improves Multimodal Retrieval

2024-10-31 · Neil Chowdhury, Franklin Wang, Sumedh Shenoy, Douwe Kiela 외

Multimodal models leverage large-scale pre-training to achieve strong but still imperfect performance on tasks such as image captioning, visual question answering, and cross-modal retrieval. In this paper, we present a s…

Cross-Modal RetrievalImage CaptioningImage RetrievalImage-text Retrieval+4