SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.10093 · IJCAI · 2023

Clustered-patch Element Connection for Few-shot Learning

Jun Liu, Chengjie Wang, Bin-Bin Gao, Xiaochen Chen, Jinxiang Lai, Siqian Yang, Wenlong Wu, Junhong Zhou

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Weak feature representation problem has influenced the performance of few-shot classification task for a long time. To alleviate this problem, recent researchers build connections between support and query instances through embedding patch features to generate discriminative representations. However, we observe that there exists semantic mismatches (foreground/ background) among these local patches, because the location and size of the target object are not fixed. What is worse, these mismatches result in unreliable similarity confidences, and complex dense connection exacerbates the problem. According to this, we propose a novel Clustered-patch Element Connection (CEC) layer to correct the mismatch problem. The CEC layer leverages Patch Cluster and Element Connection operations to collect and establish reliable connections with high similarity patch features, respectively. Moreover, we propose a CECNet, including CEC layer based attention module and distance metric. The former is utilized to generate a more discriminative representation benefiting from the global clustered-patch features, and the latter is introduced to reliably measure the similarity between pair-features. Extensive experiments demonstrate that our CECNet outperforms the state-ofthe-art methods on classification benchmark. Furthermore, our CEC approach can be extended into few-shot segmentation and detection tasks, which achieves competitive performances.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2304.10093")
get_code_for_paper("2304.10093")
have("2304.10093")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2304.10093.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2304.10093.svg)](https://syntology.ai/paper/2304.10093)

Connect an agent — have() is free.