AI Paper Atlas

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

Towards Realistic Predictors

Pei Wang, Nuno Vasconcelos

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 33 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
add an identically structured HP-Net with loss weightingVGG16 classifier · ImageNet valtop-1 accuracy: 71.6% -> 73.3%Improved
add an identically structured HP-Net with loss weightingResNet50 classifier · ImageNet valtop-1 accuracy: 76.1% -> 76.4%Improved
add an identically structured HP-Net with loss weightingVGG16 classifier · MIT67top-1 accuracy: 72.2% -> 72.3%No clear effect
add an identically structured HP-NetLeNet5 classifier · MNISTaccuracy: 99.0% -> 99.1%No clear effect
use a ResNet50 HP-Net with a VGG16 classifier instead of a VGG16 HP-Net (ablation)VGG16 classifier · MIT67top-1 accuracy: 72.3% -> 67.9%Hurt
use a VGG16 HP-Net with a ResNet50 classifier instead of a ResNet50 HP-Net (ablation)ResNet50 classifier · MIT67top-1 accuracy: 75.8% -> 72.7%Hurt
share convolutional weights between classifier and HP-Net (ablation)VGG16-VGG16 · MIT67top-1 accuracy: 72.3% -> 67.6%Hurt
share convolutional weights between classifier and HP-Net (ablation)ResNet50-ResNet50 · MIT67top-1 accuracy: 75.8% -> 73.2%Hurt
share convolutional weights between classifier and HP-Net (ablation)kerasNet-kerasNet · MNISTaccuracy: 99.2% -> 97.9%Hurt
reject by HP-Net score instead of max softmax confidence (ablation)F' on VGG16-VGG16 · MIT67 (reject 5%)top-1 accuracy: 73.4 -> 75.4Improved
reject by HP-Net score instead of max softmax confidence (ablation)F' on VGG16-VGG16 · ImageNet val (reject 5%)top-5 accuracy: 91.2 -> 91.9Improved
reject by HP-Net score instead of max softmax confidence (ablation)F' on VGG16-VGG16 · MIT67 (reject 25%)top-1 accuracy: 83.1 -> 82.9No clear effect

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