Meta: SAM 3

SAM 2 is a real-time image and video segmentation model developed by Meta AI, released in July 2024 under the Apache 2.0 license. It extends the original Segment Anything Model to support video inputs by introducing a streaming memory architecture that maintains object state across frames, enabling consistent segmentation of objects through occlusion, motion, and scene changes. For image inputs, SAM 2 operates similarly to its predecessor with improved mask quality and speed.SAM 2 accepts point, box, and mask prompts and produces object masks interactively or in a fully automated mode. Its memory architecture enables video segmentation at real-time speeds. SAM 2 is used in annotation pipelines, video analysis, robotic perception, and any application requiring high-quality promptable segmentation across both images and video.

The Segment Anything Model is a promptable image segmentation foundation model developed by Meta AI, released in April 2023 under the Apache 2.0 license. It introduces a general-purpose segmentation architecture trained on SA-1B, a dataset of over 1 billion masks across 11 million images collected using a data engine that leveraged the model itself. SAM accepts point, bounding box, and mask prompts and generates high-quality segmentation masks for any object in an image, including objects not seen during training.SAM achieves strong zero-shot performance across a wide range of segmentation tasks and domains. Its promptable interface makes it suitable as a building block for automated annotation, interactive segmentation tools, and integration with detection models such as Grounding DINO. SAM has been extended by subsequent works including SAM 2, SAM 3, and Grounded-SAM.

Grounded SAM is an open-vocabulary image segmentation model developed by IDEA Research, released in January 2024 under the Apache 2.0 license. It combines Grounding DINO, a zero-shot open-vocabulary object detector, with the Segment Anything Model to produce precise segmentation masks for objects identified through free-form text prompts. The two models are used sequentially: Grounding DINO localizes objects from a text query, and SAM generates the corresponding segmentation masks.Grounded SAM enables zero-shot instance segmentation without task-specific training data, making it applicable to domains where labeled segmentation data is scarce. It supports arbitrary text queries and can segment objects not represented in standard training sets. The model is commonly used in automated labeling pipelines, robotic perception, and domain-specific vision applications requiring open-vocabulary segmentation.

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.

Florence-2, introduced by Microsoft Research at CVPR 2024, is an open-source vision-language foundation model designed to unify diverse computer vision tasks within a single sequence-to-sequence framework. Unlike traditional models that specialize in specific tasks, Florence-2 accepts both images and text prompts and outputs text for tasks such as captioning, object detection, segmentation, OCR, and region-based grounding. It comes in two sizes—Florence-2-base (~230M parameters) and Florence-2-large (~770M parameters)—and is trained on FLD-5B, a large dataset of ~126M images with ~5.4B annotations.The model demonstrates strong zero-shot and fine-tuned performance, often rivaling larger vision-language systems while remaining lightweight and efficient. Released under the MIT license, all weights are publicly available, making it accessible for fine-tuning and deployment in applications like VQA, content tagging, accessibility, and research. Florence-2’s compact design, versatility, and openness position it as a practical alternative to larger proprietary multimodal models.

YOLOE (YOLO with Everything) is an open-vocabulary object detection and segmentation model developed by THU-MIG at Tsinghua University, released in March 2025 under the AGPL-3.0 license. It extends the YOLO architecture to support open-vocabulary detection through text and visual prompts, enabling the model to detect arbitrary object categories beyond a fixed training set without retraining. The design integrates prompt encoding directly into the YOLO framework while preserving real-time inference speed.YOLOE is evaluated on COCO and LVIS benchmarks and supports both closed-set and open-vocabulary detection modes. It is built on the Ultralytics codebase and maintains compatibility with standard YOLO training and export workflows. YOLOE is suited for applications requiring flexible, prompt-driven object detection where the target object vocabulary may change at inference time.