AI Paper Atlas

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

RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments

Mengxue Qu, Yu Wu, Wu Liu, Xiaodan Liang, Jingkuan Song, Yao Zhao, Yunchao Wei

NeurIPS 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary 3D and world perception · 2 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 pretraining on noun grounding data (ablation)MDETR · RIO detectionAP@0.5: 2.57 -> 48.16Improved
put confidence only on the word 'something' instead of whole sentence (ablation)MDETR · RIO detectionAP@0.5: 27.6 -> 48.16Improved
add object noun [obj] into the sentence with confidence on [obj] (ablation)MDETR · RIO detectionAP@0.5: 27.6 -> 32.64Improved
use [obj] sentence form instead of 'something' form (ablation)MDETR · RIO detectionAP@0.5: 48.16 -> 32.64Hurt
add noun-pronoun distillation from [obj] to something (ablation)TOIST vs MDETR · RIO detectionAP@0.5: 48.16 -> 49.00Improved
noun-pronoun distillation (TOIST vs MDETR), common setTOIST · RIO common setAP@0.5: 48.61 -> 49.05Improved
noun-pronoun distillation (TOIST vs MDETR), uncommon setTOIST · RIO uncommon setAP@0.5: 24.20 -> 21.96Hurt
replace COCO category names with synonyms (ablation)GroundingDINO · COCO2014 valAP: 48.4 -> 35.6Hurt
replace COCO category names with synonyms (ablation)GroundingDINO · COCO2014 valAP50: 64.6 -> 47.5Hurt
use end-to-end MDETR instead of detector-reasoner D-R*MDETR · RIO common setAP@0.5: 45.15 -> 48.61Improved
fine-tune GroundingDINO on COCO in detector-reasonerD-R* · RIO uncommon setTop1-Acc: 33.07 -> 41.98Improved
evaluate on uncommon intentions instead of commonMDETR · RIOAP@0.5: 48.61 -> 24.20Hurt

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