Research map / Detection and segmentation / CNN features
MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection
Zhenhong Sun, Ming Lin, Xiuyu Sun, Zhiyu Tan, Hao Li, Rong Jin
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Search a backbone with MAE-DET rather than use ResNet-50 at similar compute | GFLV2 on COCO · COCO val2017 | AP_val: 44.7 -> 46.8 | Improved |
| Use MAE-DET-M rather than DetNAS-3.8G under matched GFLV2 training | GFLV2 · COCO val2017 | AP_val: 46.4 -> 46.8 | Improved |
| Use MAE-DET rather than training-based search methods | Object-detection backbone NAS · COCO test-dev | search cost (GPU days): 68 -> 0.6; 26 -> 0.6 | Improved |
| Use multi-scale rather than single-scale entropy (ablation) | MAE-DET search · COCO with YOLOF | AP_val: +0.3% | Improved |
| Use multi-scale rather than single-scale entropy (ablation) | MAE-DET search · COCO with FCOS | AP_val: 0.6% | Improved |
| Use multi-scale rather than single-scale entropy (ablation) | MAE-DET search · ImageNet-1K | TOP-1 accuracy | No clear effect |
| Replace single-scale entropy with Zen-Score (ablation) | Zero-shot backbone search · COCO with FCOS | AP_val: 38.8 -> 38.1 | Hurt |
| Add coarse-to-fine mutation to multi-scale entropy search (ablation) | MAE-DET · ImageNet-1K | TOP-1 accuracy: 78.9 -> 79.1 | Improved |
| Add coarse-to-fine mutation to multi-scale entropy search (ablation) | MAE-DET · COCO with YOLOF | AP_val: 40.1 -> 40.3 | Improved |
| Add coarse-to-fine mutation to multi-scale entropy search (ablation) | MAE-DET · COCO with FCOS | AP_val: 39.4 -> 40.0 | Improved |
| Increase the C5 weight in MSEP, using α=1:1:6 instead of α=1:1:1 (ablation) | MAE-DET · COCO val2017, FCOS | AP_val: 37.4 -> 39.4 | Improved |
| Set MSEP weights to α=1:4:1 rather than α=1:1:6 (ablation) | MAE-DET · COCO val2017, FCOS | AP_val: 39.4 -> 35.7 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- SpineNet-96 — SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization (CVPR 2020) · better on 1 of 1 shared result
- DetNAS — DetNAS: Backbone Search for Object Detection (NeurIPS 2019) · better on 1 of 1 shared result
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
- Joint-DetNAS: Upgrade Your Detector With NAS, Pruning and Dynamic Distillation (CVPR 2021 · similarity 0.89)
- DetNAS: Backbone Search for Object Detection (NeurIPS 2019 · similarity 0.89)
- NAS-FCOS: Fast Neural Architecture Search for Object Detection (CVPR 2020 · similarity 0.89)
- G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection (AAAI 2024 · similarity 0.86)
- Accelerating Non-Maximum Suppression: A Graph Theory Perspective (NeurIPS 2024 · similarity 0.86)
- MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism (CVPR 2025 · similarity 0.86)
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.
