AI Paper Atlas

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

Learned Shape-Tailored Descriptors for Segmentation

Naeemullah Khan, Ganesh Sundaramoorthi

CVPR 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 7 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
learn an invariant metric over shape-tailored descriptorstexture segmentation · Real-World Texture DatasetGT-cov. ODS: 0.86 -> 0.92Improved
use shape-tailored descriptors rather than non-STLD descriptors (ablation)learned descriptor segmentation · Real-World Texture DatasetGT-cov. ODS: 0.89 -> 0.92Improved
add learned invariance to handcrafted STLD (ablation)texture segmentation · Real-World Texture DatasetGT-cov. ODS: 0.86 -> 0.92Improved
use a 5by5, 4by4, or 3by3 box tessellation initialization (ablation)Learned STLD · Real-World Texture DatasetGT-cov. ODS: 0.91; 0.91; 0.91No clear effect
vary hidden units from 21 to 61 in the two-layer network (ablation)Learned STLD · Real-World Texture DatasetGT-cov. ODS: 0.90; 0.91; 0.91; 0.91; 0.91No clear effect
increase network depth to 3 or 4 layers with 41 units (ablation)Learned STLD · Real-World Texture DatasetGT-cov. ODS: 0.91 -> 0.89; 0.91 -> 0.88Hurt
reduce training images from 128 to 100, 75, or 50 (ablation)Learned STLD · Real-World Texture DatasetGT-cov. ODS: 0.91 -> 0.90; 0.91 -> 0.90; 0.91 -> 0.89Hurt
vary the number of dilation steps during training (ablation)Learned STLD · Real-World Texture DatasetGT-cov. ODS: 0.91; 0.91; 0.90; 0.91; 0.90No clear effect
use learned shape-tailored descriptors instead of handcrafted STLDtexture segmentation · Synthetic Texture DatasetGT-cov. ODS: 0.87 -> 0.90Improved
use learned shape-tailored descriptors instead of handcrafted STLDtexture segmentation · GrazGT-cov. ODS: 0.70 -> 0.76Improved
use learned shape-tailored descriptors instead of handcrafted STLDtexture segmentation · BSDS500GT-cov. ODS: 0.57 -> 0.67Improved
use learned shape-tailored descriptors rather than VGG convolutional descriptorstexture segmentation · Real-World Texture DatasetGT-cov. ODS: 0.84 -> 0.92; 0.79 -> 0.92; 0.86 -> 0.92Improved

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