The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification

By Pirazh Khorramshahi, Neehar Peri, Jun-Cheng Chen, Ramalingam Chellappa. 2020

160 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Xi Li
2. Pichao Wang
3. Wei Jiang
4. Qi Tian
5. Haowen Luo
6. Fan Wang
7. Hao Li
8. Shuting He

Citations in the corpus

• MgSvF: Multi-Grained Slow versus Fast Framework for Few-Shot Class-Incremental Learning (2020, methodology): “Our intra-space SvF analysis is more inspired by the work on frequency-based decouple [87], discussing different properties of different frequency components and proposing a frequency-aware regularization method for FSCIL.”
• TransReID: Transformer-based Object Re-Identification (2021, methodology): “CNN-based methods [16, 23, 31, 37] have achieved great success in both person and vehicle ReID lately.”