AI Paper Atlas

Research map / Continual learning / Domain and prompt-based

Introducing Language Guidance in Prompt-based Continual Learning

Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc Van Gool, Didier Stricker, Federico Tombari, Muhammad Zeshan Afzal

ICCV 2023 · Continual learning › Domain and prompt-based · approach: Prompt-based continual learning · 47 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add language guidance (LGCL) to DualPromptDualPrompt · Split ImageNet-Raverage accuracy (%): 68.13 -> 69.46Improved
add language guidance (LGCL) to DualPromptDualPrompt · Split CIFAR-100average accuracy (%): 86.51 -> 87.23Improved
add language guidance (LGCL) to L2PL2P · Split CIFAR-100forgetting (%): 7.35 -> 5.83Improved
add language guidance (LGCL) to L2PL2P · Split ImageNet-Raverage accuracy (%): 61.57 -> 62.51Improved
add task-level language loss only (ablation)DualPrompt · Split ImageNet-Raverage accuracy (%): 68.13 -> 69.43Improved
add class-level language loss only (ablation)L2P · Split ImageNet-Raverage accuracy (%): 61.57 -> 62.36Improved
add both task-level and class-level losses (ablation)DualPrompt · Split ImageNet-Raverage accuracy (%): 68.13 -> 69.46Improved
use CLIP text encoder instead of BERT or RoBERTa (ablation)DualPrompt + LGCL · Split CIFAR-100average accuracy (%): 87.04 (RoBERTa), 87.11 (BERT) -> 87.23Improved
use learnable keys instead of frozen CLIP text keys (ablation)DualPrompt + LGCL · Split CIFAR-100average accuracy (%): 86.15 -> 87.23Improved
use frozen CLIP keys instead of learnable keys (ablation)DualPrompt + LGCL · Split CIFAR-100forgetting (%): 5.10 -> 3.93Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy