AI Paper Atlas

Research map / Detection and segmentation / CNN features

Pelee: A Real-Time Object Detection System on Mobile Devices

Robert J. Wang, Xiang Li, Charles X. Ling

NeurIPS 2018 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 101 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 transition layers without compression (ablation)DenseNet-41 · Stanford Dogs (customized ILSVRC subset)Top-1 accuracy: 75.02 -> 76.1Improved
Add post-activation to the no-compression transition variant (ablation)DenseNet-41 · Stanford Dogs (customized ILSVRC subset)Top-1 accuracy: 76.1 -> 75.2Hurt
Add dynamic bottleneck channels to the no-compression transition variant (ablation)DenseNet-41 · Stanford Dogs (customized ILSVRC subset)Top-1 accuracy: 75.02 -> 75.8Improved
Add a stem block to the no-compression transition and dynamic bottleneck variant (ablation)DenseNet-41 · Stanford Dogs (customized ILSVRC subset)Top-1 accuracy: 75.8 -> 76.8Improved
Add two-way dense layers (ablation)PeleeNet variant without the extra dense layers · Stanford Dogs (customized ILSVRC subset)Top-1 accuracy: 76.8 -> 78.8Improved
Add three extra dense layers (ablation)PeleeNet · Stanford Dogs (customized ILSVRC subset)Top-1 accuracy: 78.8 -> 79.25Improved
Add residual prediction blocks (ablation)Pelee object detector · PASCAL VOC 2007mAP: 68.6 -> 70.8Improved
Use 1x1 instead of 3x3 prediction kernels (ablation)Pelee object detector with residual prediction blocks · PASCAL VOC 2007mAP: 70.8 -> 70.9No clear effect
Use 1x1 instead of 3x3 prediction kernels (ablation)Pelee object detector with residual prediction blocks · PASCAL VOC 2007FLOPs: 1,470 M -> 1,210 MImproved
Omit the 38x38 feature map (ablation)Pelee object detector without residual prediction blocks · PASCAL VOC 2007mAP: 69.3 -> 68.6Hurt
Use conventional convolution-based PeleeNet rather than MobileNetImageNet classification · ImageNet ILSVRC 2012Top-1 accuracy: 70.6 -> 72.6Improved
Use PeleeNet rather than MobileNet on TX2 at 224x224ImageNet classification · TX2, 224x224Speed (images per second): 136.2 -> 240.3Improved

Later papers that compared with this method

1 later accepted paper reports Pelee as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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