CNN Image Retrieval in PyTorch: Training and evaluating CNNs for Image Retrieval in PyTorch

Full name	Student-ID	Role
Dang Thi Tuong Vy	20522176	Leader
Nguyen Hoang Long	20521568	Member
Nguyen Tu Luan	20521583	Member
Le Hoang Long	20521563	Member

Our video demo click here

Table of contents

1. Introduction
2. Demo
3. Results
4. References

---

1. Introduction

we choose the approach as the unsupervised CNNs fine-tuning for image retrieval. Firstly, we harness SfM information and enforce for both hard unmatched and matched examples for CNNs training. Secondly, we let our architectures learn the whitening through the same training data to avoid the short representations Finally, We choose to use a trainable pooling layer which generalizes existing popular pooling schemes for CNNs and thus both enhances the performance and preserving the same descriptor dimensionality as well.

2. Demo

Our video demo is storaged in here

3. Results

4. References

Our work is inspired from: CNN Image Retrieval in PyTorch: Training and evaluating CNNs for Image Retrieval in PyTorch