RF-DETR Segmentation vs SAM-CLIP

RF-DETR Segmentation is a real-time instance segmentation model developed by Roboflow, with a preview base model released in October 2025 under the Apache 2.0 license and the full variant family — Nano through 2XL — released in January 2026. It extends the RF-DETR object detection architecture with a segmentation head inspired by MaskDINO, enabling pixel-level object delineation while maintaining the real-time performance characteristics of the base model. It is deployable through Roboflow Inference and the open-source rfdetr Python package.

RF-DETR Segmentation supports fine-tuning on custom COCO- or YOLO-format instance segmentation datasets and is benchmarked on Microsoft COCO. It is suited for applications requiring both precise object masks and real-time inference, such as robotic manipulation, quality control, and augmented reality overlays.

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.