AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

DeepGaze IIE: Calibrated Prediction in and Out-of-Domain for State-of-the-Art Saliency Modeling

Akis Linardos, Matthias Kümmerer, Ori Press, Matthias Bethge

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 128 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
replace VGG19 backbone with ResNet50 featuresDeepGaze II readout · MIT1003information gain (% of gold standard): 78% to 85%Improved
use stronger ImageNet backbones such as EfficientNetB5 beyond ResNet50DeepGaze readout · MIT1003information gainNo clear effect
add DenseNet-201 to ResNext-50 mixture (ablation)backbone mixture · MIT1003information gain: 1.0368 -> 1.1075Improved
add EfficientNet-B5 to ResNext-50 + DenseNet-201 (ablation)backbone mixture · MIT1003information gain: 1.1075 -> 1.1256Improved
add ShapeNet-C to ResNext-50 + DenseNet-201 + EfficientNet-B5 (ablation)backbone mixture · MIT1003information gain: 1.1256 -> 1.1285Improved
add ResNet-50 as fifth backbone to mixture (ablation)DSRE · MIT1003information gainHurt
increase instances per backbone from 1 to 3 (ablation)DSRE · MIT1003information gain: 1.1285 -> 1.13294Improved
increase instances per backbone from 3 to 5 (ablation)DSRE · MIT1003information gain: 1.13294 -> 1.13287No clear effect
ensemble DeepGaze IIE vs DeepGaze IIsaliency model · MIT300information gain: 0.9247 -> 1.0715Improved
use 4 instances per backbone ensemble instead of single instance on MIT300 (ablation)DeepGaze IIE · MIT300information gain: 1.0679 -> 1.0715Improved
average only models with the same backbone (ablation)ensemble · PASCAL-S/TorontocalibrationNo clear effect
fine-tune the backbone (ablation)DeepGaze · MIT1003performanceHurt

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