AI Paper Atlas

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

Shatter and Gather: Learning Referring Image Segmentation with Text Supervision

Dongwon Kim, Namyup Kim, Cuiling Lan, Suha Kwak

ICCV 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 22 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 the entity discovery module (bottom-up slot attention) (ablation)Shatter and Gather · RefCOCO valmIoU: 5.91 -> 34.76Improved
add the modality fusion module with C3 loss (ablation)Shatter and Gather · RefCOCO valmIoU: 14.65 -> 34.76Improved
add reconstruction loss (ablation)Shatter and Gather · RefCOCO valmIoU: 21.84 -> 34.76Improved
use slot attention in aggregation block rather than a transformer (ablation)Shatter and Gather · RefCOCO valmIoU: 12.61 -> 34.76Improved
add the interaction block (ablation)Shatter and Gather · RefCOCO valmIoU: 33.69 -> 34.76Improved
use entity slots instead of query slots (36 slots) (ablation)Shatter and Gather · RefCOCO valmIoU: 18.16 -> 34.76Improved
use entity slots instead of random slots (36 slots) (ablation)Shatter and Gather · RefCOCO valmIoU: 30.15 -> 34.76Improved
increase number of query slots from 24 to 36 (ablation)Query slot variant · RefCOCO valmIoU: 24.78 -> 18.16Hurt
weight slot maps by A_fuse rather than uniform averaging (ablation)Shatter and Gather · RefCOCO valmIoU: 8.16 -> 34.76Improved
use more entity discovery iterations (1 to 6) (ablation)Shatter and Gather · RefCOCO valmIoU: 28.00 -> 34.76Improved
weakly supervised model versus TSEGShatter and Gather · RefCOCO valmIoU: 25.44 -> 34.76Improved

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