SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.04751 · 2023

Multimodal Parameter-Efficient Few-Shot Class Incremental Learning

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

Few-Shot Class Incremental Learning (FSCIL) is a challenging continual learning task, where limited training examples are available during several learning sessions. To succeed in this task, it is necessary to avoid over-fitting new classes caused by biased distributions in the few-shot training sets. The general approach to address this issue involves enhancing the representational capability of a pre-defined backbone architecture by adding special modules for backward compatibility with older classes. However, this approach has not yet solved the dilemma of ensuring high classification accuracy over time while reducing the gap between the performance obtained on larger training sets and the smaller ones. In this work, we propose an alternative approach called Continual Parameter-Efficient CLIP (CPE-CLIP) to reduce the loss of information between different learning sessions. Instead of adapting additional modules to address information loss, we leverage the vast knowledge acquired by CLIP in large-scale pre-training and its effectiveness in generalizing to new concepts. Our approach is multimodal and parameter-efficient, relying on learnable prompts for both the language and vision encoders to enable transfer learning across sessions. We also introduce prompt regularization to improve performance and prevent forgetting. Our experimental results demonstrate that CPE-CLIP significantly improves FSCIL performance compared to state-of-the-art proposals while also drastically reducing the number of learnable parameters and training costs.

For agents

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

get_harvested_code_for_paper("2303.04751")
get_code_for_paper("2303.04751")
have("2303.04751")

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

curl https://syntology.ai/api/ran/2303.04751.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.04751.svg)](https://syntology.ai/paper/2303.04751)

Connect an agent — have() is free.