Apple Vision Models

Compare the one Apple vision model we track, all of them open-weight.

1 model · 1 open-weight · Updated Oct 2023

About Apple Vision Models

Every Apple vision model in our catalog is open-weight. The one model we track publishes downloadable weights, so you can self-host under their own licenses instead of paying per request. The open-weight side runs on Custom terms. The most recent release is SAM-CLIP (Oct 2023).

The Apple models we list cover classification (1 model), instance segmentation (1), and zero shot segmentation (1).

Compare their licenses, sizes, prices, and release dates in the tables below, then open any model page for the full specification.

Which Apple Model Should You Use?

The one Apple vision model in our catalog and what it is built for.

SAM-CLIP: Best for: Zero Shot Segmentation and Instance Segmentation. Open weights: Custom license. Self-host it or run it here.

Open-Source Apple Models

1 model with downloadable weights you can self-host under their licenses (Custom).

SAM-CLIP

SAM-CLIP is a unified vision foundation model introduced by researchers at Apple and the University of Illinois Urbana-Champaign in October 2023. It merges two popular vision foundation models — Meta's Segment Anything Model (SAM) and OpenAI's CLIP — into a single shared Vision Transformer backbone through a combination of multi-task learning, continual learning, and teacher-student distillation. The method requires only a small fraction of the original pretraining datasets and demonstrates that complementary capabilities from distinct foundation models can be consolidated without retraining from scratch, reducing the storage and compute cost of running both models in inference.The resulting model retains SAM's zero-shot segmentation ability and CLIP's zero-shot classification and image-text retrieval, while introducing new capabilities the individual models lacked. SAM-CLIP establishes state-of-the-art results on zero-shot semantic segmentation across five benchmarks, improving mean IoU by 6.8 points on Pascal VOC and 5.9 points on COCO-Stuff over prior specialized models. The paper was accepted at the UniReps Workshop at NeurIPS 2023 and the eLVM Workshop at CVPR 2024. Apple has published the research but has not released model weights or inference code publicly.

Frequently Asked Questions About Apple Vision Models

Which Apple models can do classification?

1 of the 1 Apple vision models we track handles classification: SAM-CLIP. Each model page lists its full task coverage, license, and specs.

Which Apple models can do instance segmentation?

1 of the 1 Apple vision models we track handles instance segmentation: SAM-CLIP. Each model page lists its full task coverage, license, and specs.

Are Apple vision models open source?

Yes. The one Apple vision model we track publishes downloadable weights you can self-host under its license (Custom).

How many Apple vision models are on Roboflow Playground?

We track 1 live Apple vision model. The most recent addition is SAM-CLIP, released Oct 2023.

This page lists the one Apple vision model in the Roboflow Playground catalog, all of them open-weight and free to self-host. They cover classification, instance segmentation, and zero shot segmentation, among other tasks. Compare licenses, parameters, prices, and release dates side by side, or open any model page for full details.