Academia Sinica Vision Models

Compare all 4 Academia Sinica vision models we track, all of them open-weight.

4 models · 4 open-weight · Updated Feb 2024

About Academia Sinica Vision Models

Every Academia Sinica vision model in our catalog is open-weight. All 4 publish downloadable weights, so you can self-host under their own licenses instead of paying per request. The open-weight side runs on GPL v3 and Custom licenses. The newest additions are YOLOv9 (Feb 2024) and YOLOv7 (Jul 2022).

The Academia Sinica models we list cover object detection (4 models) and instance segmentation (1). For object detection, start with YOLOv9, YOLOv7, or YOLOv4-tiny.

On the open-weight tier, YOLOv7 is the largest at 6.2M-151.7M parameters and YOLOv9 the smallest at 2.0M-57.3M, small enough to run on a single GPU or on-device. All 4 ship under custom or copyleft terms, so read the license before you deploy commercially.

With every model here open-weight, the real trade is size against generality: the smaller checkpoints fine-tune and deploy cheaply on your own hardware, while the larger ones cover more ground out of the box. Compare their licenses, sizes, prices, and release dates in the tables below, then open any model page for the full specification.

Which Academia Sinica Model Should You Use?

What each of the 4 Academia Sinica vision models in our catalog is built for, and how you run it.

YOLOv9: Best for: Instance Segmentation and Object Detection. Open weights: GPL v3 license, 2.0M-57.3M parameters. Self-host it or run it here. Small enough for on-device and edge deployment.
YOLOv7: Best for: Object Detection. Open weights: GPL v3 license, 6.2M-151.7M parameters. Self-host it or run it here. Small enough for on-device and edge deployment.
YOLOv4-tiny: Best for: Object Detection. Open weights: Custom license. Self-host it or run it here.
YOLOv4: Best for: Object Detection. Open weights: Custom license. Self-host it or run it here.

Open-Source Academia Sinica Models

4 models with downloadable weights you can self-host under their licenses (GPL v3 and Custom).

YOLOv9

YOLOv9 is a real-time object detection model developed by Chien-Yao Wang and Hong-Yuan Mark Liao at Academia Sinica, released in February 2024 under the GPL-3.0 license. It introduces Programmable Gradient Information (PGI), a mechanism that preserves complete input information through auxiliary reversible branches during training to address information loss in deep network layers. It also introduces the Generalized Efficient Layer Aggregation Network (GELAN), which achieves better parameter utilization compared to prior CSP-based designs.YOLOv9-C achieves 53.0% AP on COCO with 42% fewer parameters and 21% less computation than YOLOv8-C at comparable accuracy. YOLOv9-E achieves 55.6% AP. The model is deployable through Roboflow Inference and supports fine-tuning via the standard training pipeline in the official repository.

YOLOv7

YOLOv7 is a real-time object detection model developed by Chien-Yao Wang and Hong-Yuan Mark Liao at Academia Sinica, released in July 2022 under the GPL-3.0 license. It introduces Extended Efficient Layer Aggregation Networks (E-ELAN) for improved gradient flow in the backbone, and trainable bag-of-freebies techniques including coarse-to-fine lead guided label assignment and auxiliary heads that improve accuracy without adding inference cost.YOLOv7 achieves 56.8% AP on COCO at 30 FPS on a V100 GPU at the time of release, establishing a strong accuracy-speed tradeoff among real-time detectors. It supports detection, instance segmentation, and pose estimation variants. YOLOv7 is deployable through Roboflow Inference and the standard training pipeline in the official repository.

YOLOv4-tiny

YOLOv4-tiny is a lightweight variant of YOLOv4 developed by Academia Sinica, released in November 2020. It retains the core YOLOv4 design principles while significantly reducing the number of convolutional layers and feature map channels to produce a model suitable for inference on devices with limited compute, including embedded hardware and mobile CPUs. It uses a simplified CSP backbone with fewer layers and two detection scales rather than three.YOLOv4-tiny is optimized for scenarios where inference speed is prioritized over peak accuracy, achieving substantially higher FPS than full YOLOv4 at the cost of reduced AP on standard benchmarks. It is commonly used in robotics, embedded vision systems, and applications where real-time detection is required without GPU acceleration.

YOLOv4

YOLOv4 is an object detection model developed by Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao at Academia Sinica, released in April 2020 via the Darknet framework. It combines a CSPDarknet53 backbone, PANet neck, and YOLOv3 detection head with a large set of training improvements — Bag of Freebies and Bag of Specials — that improve accuracy with minimal inference cost increase.YOLOv4 achieves 43.5% AP on COCO at 65 FPS on a Tesla V100 GPU. The Darknet implementation is the original version, distinguishing it from subsequent PyTorch-based reimplementations. It remains a widely referenced detection architecture and a supported training target in Roboflow Inference.

Frequently Asked Questions About Academia Sinica Vision Models

Are Academia Sinica vision models open source?

Yes. All 4 Academia Sinica vision models we track publish downloadable weights you can self-host under their licenses (GPL v3 and Custom).

How many Academia Sinica vision models are on Roboflow Playground?

We track 4 live Academia Sinica vision models. The most recent addition is YOLOv9, released Feb 2024.

This page lists all 4 Academia Sinica vision models in the Roboflow Playground catalog, all of them open-weight and free to self-host. They cover object detection and instance segmentation, among other tasks. Compare licenses, parameters, prices, and release dates side by side, or open any model page for full details.