AI Paper Atlas

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

Evaluating Capability of Deep Neural Networks for Image Classification via Information Plane

Hao Cheng, Dongze Lian, Shenghua Gao, Yanlin Geng

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 21 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
increase depth from CNN-2 to CNN-16 (VGG) (ablation)CNN on CIFAR-10 · CIFAR-10 validationaccuracy: 0.45 -> 0.89Improved
increase depth from CNN-9 to CNN-16 (ablation)CNN on CIFAR-10 · CIFAR-10 validationaccuracy: 0.77 -> 0.89Improved
increase number of conv layers from CNN-2 to CNN-16 (ablation)CNN trained by SGD · CIFAR-10 training setinversion percentage: 0.56 -> 0.96Improved
train CNN-9 with SGD instead of BGDCNN-9 · CIFAR-10 training setinversion percentage: 0.821 -> 0.865Improved
train linear network with SGD instead of BGDLinear network · CIFAR-10 training setinversion percentage: 0.594 -> 0.755Improved
use CNN-9 instead of a linear network (SGD)CNN-9 · CIFAR-10 training setinversion percentage: 0.755 -> 0.865Improved
replace FC-3 with CNN-4FC-3 · MNIST validation (Table 4 models)accuracy: 0.983 -> 0.994Improved
replace FC-3 with CNN-4FC-3 · CIFAR-10 validation (Table 4 models)accuracy: 0.534 -> 0.705Improved
increase FC depth from 6 to 9 layers (ablation)FC-6 · CIFAR-10 validation (Table 4 models)accuracy: 0.575 -> 0.56Hurt
increase FC depth from 3 to 9 layers (ablation)FC-3 · MNIST validation (Table 4 models)accuracy: 0.983 -> 0.988Improved
increase number of samples from 100 to 600 for inversion percentageVGG-16 · VGG-16 validation setinversion percentage: 0.905 -> 0.924No 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