AI Paper Atlas

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

Incremental Class Discovery for Semantic Segmentation With RGBD Sensing

Yoshikatsu Nakajima, Byeongkeun Kang, Hideo Saito, Kris Kitani

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 21 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
combine geometric and deep features with entropy-based confidence weighting instead of geometric features only (ablation)Ours · NYUDv2 (140 sequences, 13 classes)mean IoU: 42.24 -> 46.05Improved
combine geometric and deep features with entropy-based confidence weighting instead of deep features only (ablation)Ours · NYUDv2 (140 sequences, 13 classes)mean IoU: 42.22 -> 46.05Improved
use RGBD SLIC-based incremental segmentation (color + depth) instead of depth-only 3D segmentationOurs · NYUDv2 (140 sequences, 13 classes)mean IoU: 41.59 -> 46.05Improved
use deep features only instead of geometric only (trained classes) (ablation)Ours · NYUDv2 (140 sequences, 13 classes) trained classesmean IoU: bed 51.95 -> 60.07Mixed
use geometric features instead of deep features only on unseen classes (ablation)Ours · NYUDv2 (140 sequences, 13 classes) novel classesmean IoU: window 42.30 -> 52.43Improved
add color via SLIC segmentation on poor-geometry classes (picture)Ours · NYUDv2 (140 sequences, 13 classes) picturemean IoU: 19.37 -> 28.69Improved
add color via SLIC segmentation on poor-geometry classes (window)Ours · NYUDv2 (140 sequences, 13 classes) windowmean IoU: 31.30 -> 53.92Improved
cluster segments instead of elements (processing time of clustering)Ours · NYUDv2 (140 sequences, 13 classes)processing time: 13.4 msImproved
store features per segment instead of per element (memory)Ours · NYUDv2 (140 sequences, 13 classes)memory footprint (number of stored units): 196 vs 900,478Improved

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