Adversarial Learning of Hard Positives for Place Recognition

05/08/2022
by   Wenxuan Fang, et al.
0

Image retrieval methods for place recognition learn global image descriptors that are used for fetching geo-tagged images at inference time. Recent works have suggested employing weak and self-supervision for mining hard positives and hard negatives in order to improve localization accuracy and robustness to visibility changes (e.g. in illumination or view point). However, generating hard positives, which is essential for obtaining robustness, is still limited to hard-coded or global augmentations. In this work we propose an adversarial method to guide the creation of hard positives for training image retrieval networks. Our method learns local and global augmentation policies which will increase the training loss, while the image retrieval network is forced to learn more powerful features for discriminating increasingly difficult examples. This approach allows the image retrieval network to generalize beyond the hard examples presented in the data and learn features that are robust to a wide range of variations. Our method achieves state-of-the-art recalls on the Pitts250 and Tokyo 24/7 benchmarks and outperforms recent image retrieval methods on the rOxford and rParis datasets by a noticeable margin.

READ FULL TEXT
research
01/24/2020

SOLAR: Second-Order Loss and Attention for Image Retrieval

Recent works in deep-learning have shown that utilising second-order inf...
research
08/08/2023

Coarse-to-Fine: Learning Compact Discriminative Representation for Single-Stage Image Retrieval

Image retrieval targets to find images from a database that are visually...
research
11/03/2017

Fine-tuning CNN Image Retrieval with No Human Annotation

Image descriptors based on activations of Convolutional Neural Networks ...
research
07/16/2021

All the attention you need: Global-local, spatial-channel attention for image retrieval

We address representation learning for large-scale instance-level image ...
research
08/14/2023

Global Features are All You Need for Image Retrieval and Reranking

Utilizing a two-stage paradigm comprising of coarse image retrieval and ...
research
04/04/2022

Correlation Verification for Image Retrieval

Geometric verification is considered a de facto solution for the re-rank...
research
12/20/2021

Learning with Label Noise for Image Retrieval by Selecting Interactions

Learning with noisy labels is an active research area for image classifi...

Please sign up or login with your details

Forgot password? Click here to reset