AI Paper Atlas

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

Towards Fine-grained Interactive Segmentation in Images and Videos

Yuan Yao, Qiushi Yang, Miaomiao Cui, Liefeng Bo

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 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
add Localization Augment (LA) to SAM2 (ablation)SAM2 · Average of 4 fine-grained datasetsmIoU: 78.5 -> 85.0Improved
add Localization Augment (LA) to SAM2 (ablation)SAM2 · Average of 4 fine-grained datasetsmBIoU: 71.5 -> 67.4Hurt
add Prompt Retargeting (PR) to LA+MR (ablation)SAM2Refiner · Average of 4 fine-grained datasetsmIoU: 92.7 -> 93.1Improved
add Prompt Retargeting (PR) to LA+MR (ablation)SAM2Refiner · Average of 4 fine-grained datasetsmBIoU: 88.3 -> 88.9Improved
add Mask Refinement (MR) to LA+PR (ablation)SAM2Refiner · Average of 4 fine-grained datasetsmIoU: 91.4 -> 93.1Improved
add Mask Refinement (MR) to LA+PR (ablation)SAM2Refiner · Average of 4 fine-grained datasetsmBIoU: 86.2 -> 88.9Improved
add Localization Augment (LA) to PR+MR (ablation)SAM2Refiner · Average of 4 fine-grained datasetsmIoU: 91.1 -> 93.1Improved
add Localization Augment (LA) to PR+MR (ablation)SAM2Refiner · Average of 4 fine-grained datasetsmBIoU: 86.0 -> 88.9Improved
use SAM2Refiner (hiera_l) instead of HQ-SAM (vit_h)SAM2Refiner · Average of 4 fine-grained datasetsmIoU: 88.2 -> 93.1Improved
use SAM2Refiner instead of SAM2 on ThinObjectSAM2Refiner · ThinObjectmIoU: 77.8 -> 95.9Improved
use SAM2Refiner instead of SAM2 on LVOS v1SAM2Refiner · LVOS v1J&F: 77.2 -> 80.9Improved
use SAM2Refiner instead of HQ-SAM2 on LVOS v2SAM2Refiner · LVOS v2J&F: 79.1 -> 79.9Improved

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