Data checked 2026-08-13. Data may be stale - beyond the review cycle.
Review cycles are documented on the Methodology page. Methodology
Megvii-BaseDetection/YOLOX
Software Tool Tier A perception_ai Apache-2.0
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Engineering Snapshot
Use cases & tasks 6
- Best suited for
-
- Engineers deploying real-time object detection on edge devices
- UAV perception pipelines requiring multi-backend export
- Teams needing Apache-2.0 licensed detection baseline
- Primary tasks
-
- Real-time object detection for autonomous navigation
- Multi-platform inference (NVIDIA Jetson, Intel OpenVINO, mobile ncnn)
- Model export and optimization for production deployment
Stack & ecosystem
- Resource type
- Software Tool
- Ecosystem
- deep-learning · megengine · ncnn · object-detection · onnx · openvino
License & compliance
- License
-
Apache-2.0(Inferred)
Lifecycle & freshness Show
- Maintenance
- Active
- Latest version
- Not recorded
- Last activity
- 2026-08-13
- Last checked
- 2026-08-13
- Verification
- Official confirmed
What It Solves
Need a high-performance anchor-free object detector that exceeds YOLOv3-v5 accuracy with flexible deployment across multiple inference backends (ONNX, TensorRT, ncnn, OpenVINO, MegEngine).
Primary use cases
- Real-time object detection for autonomous navigation
- Multi-platform inference (NVIDIA Jetson, Intel OpenVINO, mobile ncnn)
- Model export and optimization for production deployment
Secondary use cases
- Research benchmarking against YOLOv3-v5
- Integration with tracking systems (e.g., ByteTrack)
- Transfer learning on custom aerial datasets
When to Use
Consider when
- Anchor-free design preferred for simpler pipeline
- Multiple inference backend support required
- Apache-2.0 license compatibility needed
Verify before adopting
- Actual latency/accuracy on target hardware and backend
- Maintenance activity (last commit 2026-08-13)
- Compatibility with specific PyTorch/MegEngine versions
- Export stability for ONNX/TensorRT/ncnn/OpenVINO
Where It Fits
Stack layer perception_localization
Downstream / used by
Start Here
Adoption Checklist
- Needs verification Actual latency/accuracy on target hardware and backend
- Needs verification Maintenance activity (last commit 2026-08-13)
- Needs verification Compatibility with specific PyTorch/MegEngine versions
- Needs verification Export stability for ONNX/TensorRT/ncnn/OpenVINO
Each check stays "needs verification" until an official source confirms it; unconfirmed items are never marked verified.
Known Limitations & Unknowns
Known limitations
- Performance varies significantly by deployment backend
- No official hardware-specific benchmarks provided
- Anchor-free design may affect small-object detection
Not publicly verified
- Specific version/release tags
- Quantitative benchmarks on UAV datasets
- Supported hardware targets beyond generic categories
Alternatives & Related Tools
Related tools
- onnx-runtime — Integrates with
- openvino — Integrates with
- jetson-inference — compatible with
- bytetrack — Used for
- tensorrt — Integrates with
How is it used?
Start from the recorded entry points below, then validate against the technical checklist.
- Official site https://github.com/Megvii-BaseDetection/YOLOX
- Repository https://github.com/Megvii-BaseDetection/YOLOX
- Documentation https://github.com/Megvii-BaseDetection/YOLOX
Technical checklist
- OK License identified Recorded: Apache-2.0
- OK Maintenance signal Active
- OK Verification status Official confirmed
- OK Source evidence attached 1 source record(s)
- NEEDS REVIEW Latest version recorded Not recorded
Official Links
Metadata & Governance
| License | Apache-2.0 — Inferred |
|---|---|
| Commercial model | Unknown |
| Maintenance status | Active |
| Verification status | Official confirmed — Confirmed via the official repository API responses in SourceRefs below. |
| Latest version | Not recorded |
| Latest release | Not recorded |
| Last activity | 2026-08-13 |
| Last checked | 2026-08-13 |
| First seen | Not recorded |
Dataset facts
Facts above come from the official dataset card only; unconfirmed fields stay unknown.
Related Resources & Dependencies
- onnx-runtime — integrates with (verified)
- openvino — integrates with (verified)
- jetson-inference — compatible with (verified)
- bytetrack — used for (verified)
- tensorrt — integrates with (confirmed)
Recent Activity
New resource: Megvii-BaseDetection/YOLOX
New repository resource added by the sprint promote pipeline.
Related Knowledge
Collections
- Aerial Perception Models and Datasets — Source-backed aerial dataset and model repositories for detection and tracking research and prototyping.
- Visual Perception Models and Data — Indexed model and dataset repositories for aerial visual perception research and prototyping.