Fuse Local and Global Semantics in Representation Learning

02/28/2022
by   Yuchi Zhao, et al.
0

We propose Fuse Local and Global Semantics in Representation Learning (FLAGS) to generate richer representations. FLAGS aims at extract both global and local semantics from images to benefit various downstream tasks. It shows promising results under common linear evaluation protocol. We also conduct detection and segmentation on PASCAL VOC and COCO to show the representations extracted by FLAGS are transferable.

READ FULL TEXT
research
12/28/2020

Local-to-Global Contraction in Simplicial Complexes

We give a local-to-global principle for relative entropy contraction in ...
research
05/31/2022

Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning

Unsupervised/self-supervised graph representation learning is critical f...
research
08/18/2023

Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity

Graph representation learning (GRL) methods, such as graph neural networ...
research
02/04/2022

Decoupling Local and Global Representations of Time Series

Real-world time series data are often generated from several sources of ...
research
12/15/2021

Graph Representation Learning via Contrasting Cluster Assignments

With the rise of contrastive learning, unsupervised graph representation...
research
06/07/2023

Improving neural network representations using human similarity judgments

Deep neural networks have reached human-level performance on many comput...
research
05/18/2022

Symbolic-Numeric Factorization of Differential Operators

We present a symbolic-numeric Las Vegas algorithm for factoring Fuchsian...

Please sign up or login with your details

Forgot password? Click here to reset