AI Paper Atlas

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

How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?

Yifei Ming, Yixuan Li

IJCV 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs · 40 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
fine-tune CLIP with CoCoOp prompt learning (ablation)ZOCLIP · Caltech-101 (ID)avg FPR95 with S_MS: 37.96 -> 5.94Improved
fine-tune CLIP with CoCoOp (ablation)ZOCLIP · Caltech-101 (ID)avg FPR95 with S_MCM: 15.28 -> 5.02Improved
fine-tune CLIP with CoOp (ablation)ZOCLIP · Food-101 (ID)avg FPR95 with S_MS: 1.24 -> 0.36Improved
fine-tune CLIP with CoOp (ablation)ZOCLIP · Stanford-Cars (ID)avg FPR95 with S_MS: 0.07 -> 0.02No clear effect
use S_MCM instead of S_MS (softmax scaling with temperature) (ablation)TipAdaptor · Caltech-101 (ID)avg FPR95: 13.86 -> 6.19Improved
use S_MCM instead of S_MS (ablation)CoCoOp · Caltech-101 (ID)avg FPR95: 5.94 -> 5.02Improved
use S_MS instead of default-temperature S_MSP (ablation)CoOp · Caltech-101 (ID)avg FPR95: 26.66 -> 8.35Improved
use S_MCM instead of S_MSP (ablation)CoOp, CLIP-B/32 · Caltech-101 (ID)avg FPR95: 26.40 -> 6.17Improved
use S_MCM instead of S_MSP (ablation)CoOp · ImageNet-O (ID ImageNet-1k)FPR95: 77.20 -> 61.50Improved
use S_MCM instead of S_MS (ablation)CoOp · ImageNet-1k (ID)avg FPR95: 7.44% lowerImproved
scale backbone from RN50 to CLIP-L/14 (ablation)CoOp with S_MCM · Caltech-101 (ID)avg FPR95: 14.67 -> 3.50Improved
use S_MS instead of S_MSP on ViT versus ResNet (ablation)CoOp · Caltech-101 (ID)avg FPR95: RN101 27.11 -> 26.93; CLIP-B/32 26.40 -> 17.13Mixed

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