AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Collaborative Layer-Wise Discriminative Learning in Deep Neural Networks

Xiaojie Jin, Yunpeng Chen, Jian Dong, Jiashi Feng, Shuicheng Yan

ECCV 2016 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 20 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 CLDL loss with collaborating classifiers instead of independent softmax losses (ablation)DSN*-NIN · CIFAR-100 (without data augmentation)error rate (%): 34.12 -> 30.40Improved
use CLDL loss with collaborating classifiers instead of independent softmax losses (ablation)DSN*-NIN · CIFAR-100 (with data augmentation)error rate (%): 32.95 -> 29.05Improved
add feedback from top classifiers to bottom classifiers (ablation)CLDL--NIN · CIFAR-100 (without data augmentation)error rate (%): 31.27 -> 30.40Improved
add feedback from top classifiers to bottom classifiers (ablation)CLDL--NIN · CIFAR-100 (with data augmentation)error rate (%): 30.41 -> 29.05Improved
train NIN with CLDLNIN* · CIFAR-100 (without data augmentation)error rate (%): 35.96 -> 30.40Improved
train NIN with CLDLNIN* · CIFAR-100 (with data augmentation)error rate (%): 32.75 -> 29.05Improved
train NIN with CLDL instead of DSNDSN · MNISTerror rate (%): 0.39 -> 0.28Improved
train GoogLeNet with CLDLGoogLeNet · ImageNet valtop-5 error (%): 11.1 -> 10.21Improved
fine-tune VGGNet with CLDLVGGNet_ft · MIT67top-1 accuracy (%): 83.10 -> 84.69Improved
fine-tune VGGNet with CLDLVGGNet_ft · SUN397top-1 accuracy (%): 68.47 -> 70.40Improved
fine-tune VGGNet with CLDLVGGNet_ft · Places205top-5 (%) as printed: 87.60 -> 88.67Improved
increase number of collaborative classifiers from 1 to 3 then to 4 or 5 (ablation)CLDL-NIN · CIFAR-100 (with data augmentation)accuracyMixed

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