Research map / Detection and segmentation / CNN features
Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Choose SSD rather than R-FCN or Faster R-CNN | Object detectors · COCO, images of size 300 | mAP points per millisecond of GPU computation | Helped |
| Use SSD with MobileNet | Object detectors · Large objects | mAP points per millisecond of GPU computation: about 0.9 mAP points per millisecond | Helped |
| Use MobileNet as the feature extractor | Object detectors · Almost all settings | total memory usage: less than 1Gb | Helped |
| Use conv5 features instead of conv4 features (ablation) | SSD with ResNet-101 · COCO | mAP | No clear effect |
| Use conv5 features instead of conv4 features (ablation) | SSD with ResNet-101 · COCO | computational cost | Hurt |
Closest papers by meaning
- R-FCN: Object Detection via Region-based Fully Convolutional Networks (NeurIPS 2016 · similarity 0.88)
- SpeedDETR: Speed-aware Transformers for End-to-end Object Detection (ICML 2023 · similarity 0.88)
- Mobile Video Object Detection With Temporally-Aware Feature Maps (CVPR 2018 · similarity 0.88)
- Feature Pyramid Networks for Object Detection (CVPR 2017 · similarity 0.87)
- DETRs Beat YOLOs on Real-time Object Detection (CVPR 2024 · similarity 0.85)
- DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation (ICLR 2025 · similarity 0.85)
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.