AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Real Time Image Saliency for Black Box Classifiers

Piotr Dabkowski, Yarin Gal

NeurIPS 2017 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 77 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 a trained masking model to predict saliency maps in one forward passImageNet localisation with GoogLeNet · ImageNet validationlocalisation error (%): 43.1 -> 36.9Improved
Use a trained masking model rather than gradient saliencyImageNet localisation with GoogLeNet · ImageNet validationlocalisation error (%): 41.7 -> 36.9Improved
Use a trained masking model rather than Excitation BackpropImageNet localisation with GoogLeNet · ImageNet validationlocalisation error (%): 39.0 -> 36.9Improved
Use a trained masking model rather than the Center box baselineImageNet localisation with GoogLeNet · ImageNet validationlocalisation error (%): 46.3 -> 36.9Improved
Use a trained masking model rather than the Excitation Backprop mapImageNet saliency evaluation with GoogLeNet · ImageNet validationsaliency metric: 0.415 -> 0.318Improved
Use a trained masking model rather than gradient saliencyImageNet saliency evaluation with GoogLeNet · ImageNet validationsaliency metric: 0.451 -> 0.318Improved
Train the masking model on ResNet-50 rather than AlexNetMasking model · ImageNet validationlocalisation error (%): 39.8 -> 36.7Improved
Train the masking model on GoogLeNet rather than AlexNetMasking model · ImageNet validationlocalisation error (%): 39.8 -> 36.9Improved
Add random fake-class selectors during training and apply only the area penalty for themMasking model training · ImageNetclass-selector conditioningImproved
Randomly vary the evidence-removal image between blurred input and random noisy colourMasking model training · ImageNetmask qualityImproved
Use the two-channel absolute-ratio mask output instead of sigmoid or tanh (ablation)Masking model · ImageNettraining optimisationImproved
Add total-variation smoothness regularisation to the mask objectiveMasking model · ImageNet saliency mapsartifact suppressionImproved

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