AI Paper Atlas

Research map / Detection and segmentation / CNN features

Mask-Attention-Free Transformer for 3D Instance Segmentation

Xin Lai, Yuhui Yuan, Ruihang Chu, Yukang Chen, Han Hu, Jiaya Jia

ICCV 2023 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 37 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 iterative refinement of position queries (ablation)Mask-attention-free transformer · ScanNetv2 valmAP: 57.5 -> 58.4Improved
add center matching to bipartite matching (ablation)Mask-attention-free transformer · ScanNetv2 valmAP: 56.7 -> 58.4Improved
add center loss (ablation)Mask-attention-free transformer · ScanNetv2 valmAP: 56.8 -> 58.4Improved
add both center matching and center loss together with iterative refinement (ablation)Mask-attention-free transformer · ScanNetv2 valmAP: 56.4 -> 58.4Improved
use relative position encoding instead of Fourier absolute encoding (ablation)Mask-attention-free transformer · ScanNetv2 valmAP: 57.7 -> 58.4Improved
add any position encoding (versus none) (ablation)Mask-attention-free transformer · ScanNetv2 valmAP: 0.0 -> 58.4Improved
use learnable position queries instead of FPS-initialized (ablation)Mask-attention-free transformer · ScanNetv2 valmAP: 57.3 -> 58.4Improved
use zero-initialized instead of learnable content queries (ablation)Mask-attention-free transformer · ScanNetv2 valmAP: 58.1 -> 58.4Improved
replace mask attention with center regression and position-aware designsMask3D/SPFormer-style baseline · ScanNetv2 valconvergence: 128 epochs outperform baseline trained 512 epochsImproved
add surface normal inputMask-attention-free transformer · ScanNetv2 valmAP: 58.4 -> 59.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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