Global Features are All You Need for Image Retrieval and Reranking

2 code implementations • ICCV 2023 • Shihao Shao, KaiFeng Chen, Arjun Karpur, Qinghua Cui, Andre Araujo, Bingyi Cao

Image retrieval systems conventionally use a two-stage paradigm, leveraging global features for initial retrieval and local features for reranking.

Image Retrieval Retrieval

1st Place Solution in Google Universal Images Embedding

no code implementations • 16 Oct 2022 • Shihao Shao, Qinghua Cui

This paper presents the 1st place solution for the Google Universal Images Embedding Competition on Kaggle.

A layer-stress learning framework universally augments deep neural network tasks

no code implementations • 14 Nov 2021 • Shihao Shao, Yong liu, Qinghua Cui

Here we presented a layer-stress deep learning framework (x-NN) which implemented automatic and wise depth decision on shallow or deep feature map in a deep network through firstly designing enough number of layers and then trading off them by Multi-Head Attention Block.