AI Paper Atlas

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

QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learning

Tianran Ouyang, Xingping Dong, Jing Zhang, Mang Ye, Kaihao Zhang, Bo Du

ECCV 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Slot attention methods · 0 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 coverage criterion to slot selection (ablation)QASA (Transformer) · COCOmBOi: 25.5 -> 25.3No clear effect
add coverage criterion to slot selection (ablation)QASA (Transformer) · COCOmBOc: 25.9 -> 34.5Improved
add slot-quality prioritization on top of coverage (ablation)QASA (Transformer) · COCOmBOi: 25.3 -> 35.0Improved
add novelty constraint on top of coverage and quality (ablation)QASA (Transformer) · COCOmBOi: 35.0 -> 36.7Improved
add K/V gate g1 to decoder (ablation)QASA (Transformer) · COCOmBOi: 25.5 -> 33.2Improved
add logit gate g2 alone (ablation)QASA (Transformer) · COCOmBOi: 25.5 -> 25.5No clear effect
add logit gate g2 on top of g1 (ablation)QASA (Transformer) · COCOmBOi: 33.2 -> 36.7Improved
use Transformer instead of MLP decoderQASA · COCOmBOi: 33.6 -> 36.7Improved
increase Kmax from 20 to 32 beyond max object count (ablation)QASA (Transformer) · MOVi-CmBOi: 46.9 -> 45.4Hurt
reduce Kmax from 20 to 15 (ablation)QASA (Transformer) · MOVi-CmBOi: 46.9 -> 44.4Hurt
increase Kmax from 30 to 64 (ablation)QASA (Transformer) · MOVi-EmBOi: 39.1 -> 38.7Hurt
use QASA slots instead of SPOT for property prediction (MLP predictor)QASA (Transformer) · COCO property predictionclass top-1: 45.9 -> 59.6Improved

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