AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

ProLoG: Hybrid Prompt and LoRA Based Adaptation of Vision-Language Models for OOD Generalization

Jungwuk Park, Dong-Jun Han, Jaekyun Moon

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs · 0 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 the hybrid prompt+LoRA network (ablation)CLIP · Base-to-new, 11 datasets (ViT-B/16)harmonic mean: 71.70 -> 78.96Improved
add the hybrid network (ablation)CLIP · Base-to-new, 11 datasets (ViT-B/16)new-class accuracy: 74.22 -> 73.57No clear effect
add augmentation-based regularization loss (ablation)hybrid network · Base-to-new, 11 datasets (ViT-B/16)new-class accuracy: 73.57 -> 76.18Improved
add augmentation-based regularization loss (ablation)hybrid network · Base-to-new, 11 datasets (ViT-B/16)base-class accuracy: 85.21 -> 84.52Hurt
add augmentation-based regularization loss (ablation)hybrid network · Base-to-new, 11 datasets (ViT-B/16)harmonic mean: 78.96 -> 80.13Improved
add masking strategy for LoRA on class-specific tokens (ablation)hybrid network + regularization · Base-to-new, 11 datasets (ViT-B/16)harmonic mean: 80.13 -> 80.33Improved
add task-similarity adaptive inference (ablation)ProLoG · Base-to-new, 11 datasets (ViT-B/16)new-class accuracy: 76.32 -> 76.89Improved
add task-similarity adaptive inference (ablation)ProLoG · Base-to-new, 11 datasets (ViT-B/16)harmonic mean: 80.33 -> 80.64Improved
use ProLoG instead of PromptSRCCLIP ViT-B/32 · Base-to-new, 11 datasetsharmonic mean: 75.95 -> 76.84Improved
use ProLoG instead of PromptSRCCLIP ViT-B/32 · Base-to-new, 11 datasetsbase-class accuracy: 81.28 -> 81.05No clear effect
use ProLoG instead of CoPromptCLIP ViT-B/16 · Cross-dataset (UCF101 base)avg target accuracy: 60.26 -> 64.19Improved
use ProLoG instead of PromptSRCCLIP ViT-B/16 · Cross-dataset (DTD base)avg target accuracy: 65.69 -> 66.10Improved

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