The Devil Is in the Details: Self-supervised Attention for Vehicle Re-identification
| Autor: | Jun-Cheng Chen, Neehar Peri, Pirazh Khorramshahi, Rama Chellappa |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
050210 logistics & transportation
Self supervised learning Scale (ratio) Computer science business.industry 05 social sciences 02 engineering and technology Machine learning computer.software_genre Re identification Discriminative model Research community 0502 economics and business 0202 electrical engineering electronic engineering information engineering Key (cryptography) 020201 artificial intelligence & image processing Artificial intelligence business computer |
| Zdroj: | Computer Vision – ECCV 2020 ISBN: 9783030585679 ECCV (14) |
| DOI: | 10.1007/978-3-030-58568-6_22 |
| Popis: | In recent years, the research community has approached the problem of vehicle re-identification (re-id) with attention-based models, specifically focusing on regions of a vehicle containing discriminative information. These re-id methods rely on expensive key-point labels, part annotations, and additional attributes including vehicle make, model, and color. Given the large number of vehicle re-id datasets with various levels of annotations, strongly-supervised methods are unable to scale across different domains. In this paper, we present Self-supervised Attention for Vehicle Re-identification (SAVER), a novel approach to effectively learn vehicle-specific discriminative features. Through extensive experimentation, we show that SAVER improves upon the state-of-the-art on challenging VeRi, VehicleID, Vehicle-1M and VERI-Wild datasets. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|