AI Paper Atlas

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

AIMS: All-Inclusive Multi-Level Segmentation for Anything

Lu Qi, Jason Kuen, Weidong Guo, Jiuxiang Gu, Zhe Lin, Bo Du, Yu Xu, Ming-Hsuan Yang

NeurIPS 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 1 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
train on all five datasets instead of PPP onlybaseline decoders · COCO-PSGAP_entity: 25.7 -> 40.4Improved
train on all datasets instead of COCO-PSG onlybaseline decoders · COCO-PSGAP_relation: 39.6 -> 38.9Hurt
add mask prompt encoder (ablation)baseline · PPPAP_part: 24.5 -> 25.7Improved
add task complementarity module (ablation)baseline · PPPAP_part: 24.5 -> 25.9Improved
add association module (ablation)baseline · PPPAR_EP@100: 69.7 -> 70.6Improved
use only full-image mask prompts in training (ablation)AIMS · PPPAP_entity: 53.2 -> 53.4No clear effect
use only partial-image mask prompts in training (ablation)AIMS · PPPAP_part: 24.5 -> 22.1Hurt
use both full and partial image prompts (ablation)AIMS · PPPAP_part: 24.5 -> 25.6Improved
add single-entity and dual-entity mask prompts to full and partial prompts (ablation)AIMS · PPPAP_part: 25.6 -> 26.5Improved
use only dual/single-entity prompts without full or partial prompts (ablation)AIMS · PPPAP_part: 24.5 -> 20.4Hurt
add a second CONV1 layer to mask encoder (ablation)mask prompt encoder · PPPAP_part: 26.5 -> 26.4No clear effect
remove CONV1 from mask encoder (ablation)mask prompt encoder · PPPAP_part: 26.5 -> 25.9Hurt

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