AI Paper Atlas

Research map / Detection and segmentation / CNN features

SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation

Lingchen Meng, Shiyi Lan, Hengduo Li, Jose M Alvarez, Zuxuan Wu, Yu-Gang Jiang

ECCV 2024 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 15 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 geometric, visual and meta instructions together instead of any one alone (ablation)SegIC (DINOv2-B) · COCO-20i / FSS-1000 / DAVIS-17mIoU / J&F: COCO-20i 48.9 (none) -> 74.6 (all three)Improved
use only meta instructions (ablation)SegIC (DINOv2-B) · FSS-1000 / DAVIS-17mIoU / J&F: FSS-1000 63.7, DAVIS-17 21.6 (vs 87.4, 68.4 with all)Hurt
add context reversion and negative entity augmentation together (ablation)SegIC (DINOv2-B) · COCO-20i / FSS-1000 / DAVIS-17mIoU / J&F: COCO-20i 70.0 -> 74.6; DAVIS-17 66.3 -> 68.4Improved
add either training strategy alone (ablation)SegIC (DINOv2-B) · DAVIS-17J&F: 66.3 -> 65.0 (negative) / 64.3 (reversion)Hurt
add COCO instance segmentation annotations to training (ablation)SegIC (DINOv2-B) · DAVIS-17J&F: 45.1 -> 70.1Improved
add ADE20k to COCO semantic training data (ablation)SegIC (DINOv2-B) · FSS-1000 / DAVIS-17mIoU / J&F: FSS-1000 80.9 -> 82.3; DAVIS-17 45.1 -> 40.1Mixed
joint training on COCO-excluded datasets (ADE20k, LVIS, FSS-1000)SegIC · COCO-20i one-shotmean mIoU: 53.6 -> 62.3Improved
use frozen backbone lacking high/multi-resolution support (CLIP-ViT-B, MAE-B) (ablation)SegIC · COCO-20imIoU: 74.6 (DINOv2-B) -> 15.3 (CLIP-ViT-B), 12.0 (MAE-B)Hurt
scale the frozen DINOv2 backbone from B to G (ablation)SegIC · COCO-20i / FSS-1000 / DAVIS-17AVG: 76.8 -> 77.8No clear effect
use DINOv1 (image self-distillation) instead of DINOv2 backbone (ablation)SegIC · COCO-20imIoU: 74.6 -> 53.5Hurt
use SegIC (DINOv2-G) vs Matcher on LVIS-92iSegIC · LVIS-92imean mIoU: 33.0 -> 47.8Improved

Later papers that compared with this method

2 later accepted papers report SegIC as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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