AI Paper Atlas

Research map / Detection and segmentation / CNN features

Attend and Segment: Attention Guided Active Semantic Segmentation

Soroush Seifi, Tinne Tuytelaars

ECCV 2020 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 15 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
use 3-scale retina glimpses instead of full-resolution glimpses at 18% pixel budget (ablation)glimpse-only agent · CityScapesmean pixel accuracy: 71.9% -> 78.1%Improved
use 3-scale retina glimpses instead of 2-scale at same pixel budget (ablation)glimpse-only agent · CityScapesmean pixel accuracy: 77.2% -> 78.1%Improved
increase number of glimpses from 1 to 10 (ablation)glimpse-only agent · CityScapesmean pixel accuracy: 63% -> 78.1%Improved
increase number of glimpses from 1 to 10 (ablation)glimpse-only agent · CamVidmean pixel accuracy: 68.2% -> 80.9%Improved
increase number of glimpses from 1 to 10 (ablation)glimpse-only agent · Kittimean pixel accuracy: 64.3% -> 76.1%Improved
keep glimpse coverage ratio constant when doubling input size to 256x512 with 96x96 glimpses (ablation)glimpse-only agent · CityScapesmean pixel accuracyNo clear effect
choose next glimpse by predicted uncertainty instead of random location (ablation)glimpse-only agent · CityScapesmean pixel accuracyImproved
choose next glimpse by uncertainty instead of horizon-only or restricted movement (ablation)glimpse-only agent · CityScapesmean pixel accuracyImproved
add low-resolution 32x32 view of the whole scene at the first step (hybrid agent) (ablation)glimpse-only agent · CityScapes, CamVid, Kittimean pixel accuracyImproved
increase number of glimpses for the hybrid agent (ablation)hybrid agent · CityScapes, CamVid, Kittigap to glimpse-onlyMixed
downscale input from full to 1/16 for scale-only agent (ablation)scale-only agent · Kittimean pixel accuracy: 81.7 -> 75.5Hurt
use full-image U-net instead of glimpse-only agent with 18% pixelsglimpse-only agent · CityScapesmean IoU: 0.508 -> 0.590Improved

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