AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Referring Image Segmentation Using Text Supervision

Fang Liu, Yuhao Liu, Yuqiu Kong, Ke Xu, Lihe Zhang, Baocai Yin, Gerhard Hancke, Rynson Lau

ICCV 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 51 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 bilateral prompt (both directions) instead of no prompt (ablation)TRIS Step-1 · RefCOCOg (U) trainPointM: 36.93 -> 40.92Improved
bilateral prompt instead of unilateral text-to-visual prompt (ablation)TRIS Step-1 · RefCOCOg (U) trainIoU: 19.70 -> 20.43Improved
add positive foreground enhancement term in calibration (ablation)TRIS Step-1 with bilateral prompt · RefCOCOg (U) trainIoU: 20.43 -> 24.18Improved
add negative background suppression term in calibration (ablation)TRIS Step-1 with bilateral prompt · RefCOCOg (U) trainIoU: 20.43 -> 22.43Improved
combine both calibration terms with bilateral prompt (ablation)TRIS Step-1 · RefCOCOg (U) trainIoU: 18.94 -> 27.81Improved
add positive response map selection (PRMS) (ablation)TRIS pseudo-label generation · RefCOCO+ valIoU: 22.31 -> 24.48Improved
add PRMS (ablation)TRIS pseudo-label generation · RefCOCOg val (U)IoU: 26.62 -> 27.06No clear effect
use negative text queries (N+1 from 1 to 48) in classification (ablation)TRIS Step-1 · RefCOCOg (U) trainIoU: 11.16 -> 27.81Improved
increase negative queries from 48 to 60 (ablation)TRIS Step-1 · RefCOCOg (U) trainIoU: 27.81 -> 27.61Hurt
increase calibration negatives K from 6 to 12 (ablation)TRIS Step-1 · RefCOCOg (U) trainIoU: 27.81 -> 27.63Hurt
train segmentation network on pseudo-labels (Step-2) instead of Step-1 response maps (ablation)TRIS · RefCOCOg val (U)IoU: 26.62 -> 36.19Improved
text-only supervision versus text-supervised adaptations (WWbL)WWbL · ReferIt testIoU: 27.68 -> 44.57Improved

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