AI Paper Atlas

Research map / Detection and segmentation / CNN features

Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation

Jingyu Zhao, Yanwen Fang, Guodong Li

NeurIPS 2021 · Detection and segmentation › CNN features · approach: Efficient network training and design · 12 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 RLA to ResNet-50ResNet-50 · ImageNet validationTop-1 error (%): 24.70 -> 22.83Improved
add RLA to ResNet-101ResNet-101 · ImageNet validationTop-1 error (%): 23.60 -> 21.48Improved
add RLA to ResNet-152ResNet-152 · ImageNet validationTop-1 error (%): 23.00 -> 21.22Improved
add RLA to ResNet-50ResNet-50 with Faster R-CNN · COCO val2017AP: 36.4 -> 38.8Improved
add RLA to ResNet-101ResNet-101 with RetinaNet · COCO val2017AP: 37.7 -> 40.3Improved
add RLA to ResNet-50ResNet-50 with Mask R-CNN · COCO val2017instance segmentation AP: 34.1 -> 35.6Improved
add RLA to ECANetECANet-50 · ImageNet validationTop-1 error (%): 22.52 -> 22.15Improved
share 1x1 convolution weights by lag (ablation)DenseNet · CIFAR-10classification error (%): 5.80± 0.33 -> 6.22Hurt
share 1x1 convolution weights by layer ordinal (ablation)DenseNet · CIFAR-10classification error (%): 5.80± 0.33 -> 6.29Hurt
increase channels by 32 instead of adding RLA (ablation)ResNet-50 · ImageNet validationTop-1 error (%): 24.70 -> 23.54Improved
remove parameter sharing from RLA (ablation)RLA-v1 on ResNet-50 · ImageNet validationTop-1 error (%): 22.83 -> 22.93Hurt
remove information flow from RLA to the main CNN (ablation)RLA-v1 on ResNet-50 · ImageNet validationTop-1 error (%): 22.83 -> 23.42Hurt

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