DeepAI AI Chat
Log In Sign Up

DALG: Deep Attentive Local and Global Modeling for Image Retrieval

by   Yuxin Song, et al.

Deeply learned representations have achieved superior image retrieval performance in a retrieve-then-rerank manner. Recent state-of-the-art single stage model, which heuristically fuses local and global features, achieves promising trade-off between efficiency and effectiveness. However, we notice that efficiency of existing solutions is still restricted because of their multi-scale inference paradigm. In this paper, we follow the single stage art and obtain further complexity-effectiveness balance by successfully getting rid of multi-scale testing. To achieve this goal, we abandon the widely-used convolution network giving its limitation in exploring diverse visual patterns, and resort to fully attention based framework for robust representation learning motivated by the success of Transformer. Besides applying Transformer for global feature extraction, we devise a local branch composed of window-based multi-head attention and spatial attention to fully exploit local image patterns. Furthermore, we propose to combine the hierarchical local and global features via a cross-attention module, instead of using heuristically fusion as previous art does. With our Deep Attentive Local and Global modeling framework (DALG), extensive experimental results show that efficiency can be significantly improved while maintaining competitive results with the state of the arts.


page 12

page 13


DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features

Image Retrieval is a fundamental task of obtaining images similar to the...

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

We address representation learning for large-scale instance-level image ...

Unifying Deep Local and Global Features for Efficient Image Search

A key challenge in large-scale image retrieval problems is the trade-off...

LA-HCN: Label-based Attention for Hierarchical Multi-label TextClassification Neural Network

Hierarchical multi-label text classification(HMTC) problems become popul...

SuperGF: Unifying Local and Global Features for Visual Localization

Advanced visual localization techniques encompass image retrieval challe...

Aggregating Global Features into Local Vision Transformer

Local Transformer-based classification models have recently achieved pro...

MUSE: Multi-Scale Temporal Features Evolution for Knowledge Tracing

Transformer based knowledge tracing model is an extensively studied prob...