AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition

Haoxuan Qu, Xiaofei Hui, Yujun Cai, Jun Liu

NeurIPS 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 5 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
Use LMC instead of the strongest listed baseline, PMALOpen-set recognition · CIFAR10AUROC: 95.1 ± - -> 96.6 ± 0.3Improved
Use LMC instead of the strongest listed baseline, MLSOpen-set recognition · CIFAR+10AUROC: 97.9 ± - -> 98.9 ± 0.7Improved
Use LMC instead of ZOCOpen-set recognition · CIFAR+50AUROC: 97.6 ± 0.0 -> 98.5 ± 0.4Improved
Use LMC instead of ZOCOpen-set recognition · TinyImageNetAUROC: 84.6 ± 1.0 -> 86.7 ± 1.4Improved
Use LMC instead of ARPL+CSOpen-set recognition · CIFAR10OSCR: 87.9 ± 1.5 -> 93.6 ± 1.5Improved
Use LMC instead of ARPL+CSOpen-set recognition · CIFAR+10OSCR: 94.7 ± 0.7 -> 96.8 ± 0.7Improved
Use LMC instead of ARPL+CSOpen-set recognition · CIFAR+50OSCR: 92.9 ± 0.3 -> 96.4 ± 0.4Improved
Use LMC instead of ARPL+CSOpen-set recognition · TinyImageNetOSCR: 65.9 ± 3.8 -> 80.6 ± 3.4Improved
Add CLIP alignment with class names (ablation)LMC on TinyImageNet · TinyImageNetAUROC: 84.4 -> 86.7Improved
Add DINO alignment with generated class images (ablation)LMC on TinyImageNet · TinyImageNetAUROC: 82.1 -> 86.7Improved
Add intermediate reasoning and self-checking to class-name prompts (ablation)LMC on TinyImageNet · TinyImageNetAUROC: 84.1 -> 86.7Improved
Add intermediate reasoning to class-name prompts (ablation)LMC on TinyImageNet · TinyImageNetAUROC: 85.6 -> 86.7Improved

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