Channel Relationship Prediction with Forget-Update Module for Few-shot Classification

TL;DR

This paper introduces a novel pipeline combining a channel vector sequence construction module and a forget-update module to improve few-shot classification by inferring class relationships more effectively.

Contribution

It proposes a new architectural module and a forget-update mechanism that enhance sequence prediction for few-shot classification tasks, achieving state-of-the-art results.

Findings

Achieves state-of-the-art performance on miniImagenet and CUB datasets.

Effectively infers class relationships in few-shot scenarios.

Improves sequence prediction accuracy with the proposed modules.

Abstract

In this paper, we proposed a pipeline for inferring the relationship of each class in support set and a query sample using forget-update module. We first propose a novel architectural module called "channel vector sequence construction module", which boosts the performance of sequence-prediction-model-based few-shot classification methods by collecting the overall information of all support samples and a query sample. The channel vector sequence generated by this module is organized in a way that each time step of the sequence contains the information from the corresponding channel of all support samples and the query sample to be inferred. Channel vector sequence is obtained by a convolutional neural network and a fully connected network, and the spliced channel vector sequence is spliced of the corresponding channel vectors of support samples and a query sample in the original channel order. Also, we propose a forget-update module consisting of stacked forget-update blocks. The forget block modify the original information with the learned weights and the update block establishes a dense connection for the model. The proposed pipeline, which consists of channel vector sequence construction module and forget-update module, can infer the relationship between the query sample and support samples in few-shot classification scenario. Experimental results show that the pipeline can achieve state-of-the-art results on miniImagenet, CUB dataset, and cross-domain scenario.