Instance Segmentation Models

Released on November 19th, 2025, Segment Anything 3 (SAM 3) is a zero-shot image segmentation model that “detects, segments, and tracks objects in images and videos based on concept prompts.” This model was developed by Meta as the third model in the Segment Anything series.

Unlike its previous SAM models (Segment Anything and Segment Anything 2), you can provide SAM 3 with the prompt “shipping container” and it will generate precise segmentation masks for all shipping containers in an image. SAM 3 generates segmentation masks that correspond to the location of the objects found with a text prompt.

SAM 3D Objects is a 3D reconstruction model released on November 19, 2025 by Meta AI as part of the broader SAM 3 release. It extends the Segment Anything Model family from 2D segmentation into 3D object reconstruction, predicting geometry, texture, and spatial layout for individual objects from a single RGB image. Given an image together with a prompt identifying the object (a segmentation mask, point, or bounding box), the model outputs a full textured 3D mesh, without requiring multi-view captures, depth sensors, or known camera parameters.SAM 3D Objects uses a two-stage transformer architecture: a coarse stage that predicts 3D shape and object pose, followed by a refinement stage that adds texture and surface detail, with DINOv2 used to encode the input image. The model is trained via a human-and-model-in-the-loop data engine that combines synthetic 3D assets with real-image annotations, producing approximately 3.14 million mesh annotations across nearly 1 million images. Meta released SAM 3D Objects alongside SAM 3D Body, a companion model for single-image human mesh recovery, and SAM 3D Artist Objects (SA-3DAO), a new evaluation benchmark assembled with artist-created 3D ground truth. The model is designed as a companion to SAM 3 for downstream applications including augmented reality, robotics, content creation, and visual effects; it already powers the View in Room feature on Facebook Marketplace. SAM 3D Objects is released under the SAM 3 license; users should review the license terms prior to commercial use.

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.

YOLO26 is a real-time object detection model developed by Ultralytics, released in October 2025. It introduces a native end-to-end, NMS-free architecture that eliminates the Non-Maximum Suppression post-processing step, reducing CPU latency by up to 43% for the Nano variant compared to NMS-dependent versions. The model incorporates the MuSGD optimizer and ProgLoss with STAL for improved training stability and small-object detection, and removes Distribution Focal Loss to ensure maximum compatibility with ONNX and TensorRT export targets.YOLO26 supports object detection, instance segmentation, pose estimation, and oriented bounding box detection within a unified framework, with model sizes available from Nano to Extra Large. Its NMS-free design makes it particularly well suited for deployment scenarios where post-processing overhead is a bottleneck, such as embedded systems and real-time edge inference pipelines.

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.

YOLOv12 is an attention-centric real-time object detection model developed by researchers at Tsinghua University, with the arXiv paper published in February 2025 under the AGPL-3.0 license. It introduces an Area Attention module that partitions feature maps into regions and applies self-attention within each region, reducing the quadratic complexity of full self-attention while capturing long-range dependencies. It also incorporates R-ELAN for improved feature aggregation and scaled residual connections for training stability.YOLOv12-L achieves 54.0% AP on COCO, while the YOLOv12-N variant achieves 40.5% mAP at 1.62ms latency on an NVIDIA T4 GPU. The model is built on the Ultralytics codebase, supporting detection, segmentation, and other standard YOLO tasks at competitive real-time speeds.

YOLO11 is an object detection and multi-task vision model developed by Ultralytics, released in September 2024 under the AGPL-3.0 license. It is the latest generation in the Ultralytics YOLO series and supports object detection, instance segmentation, image classification, pose estimation, and oriented bounding box detection within a single unified framework. YOLO11 introduces architectural refinements that improve accuracy while reducing parameter count compared to YOLOv8 at equivalent model sizes.YOLO11 is available in five model sizes from Nano to Extra Large and is deployable through the Ultralytics Python package, Roboflow Inference, and export formats including ONNX, TensorRT, and CoreML. It supports fine-tuning on custom datasets through the standard Ultralytics training API.

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.

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.

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.

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.

YOLOv8 Instance Segmentation is the segmentation variant of the YOLOv8 model developed by Ultralytics, released in January 2023 under the AGPL-3.0 license. It extends the standard YOLOv8 detection head with a mask prediction branch that generates pixel-level segmentation masks for each detected object using a prototype mask approach. This enables real-time instance segmentation within a single forward pass.YOLOv8 Instance Segmentation shares the same backbone and neck architecture as the base detection model and is available in the same size range. It is deployable through Roboflow Inference and supports fine-tuning on custom COCO-format segmentation datasets. It is suited for applications requiring both object localization and precise mask prediction at real-time speeds.

Detectron2 is a computer vision model library developed by Facebook AI Research (Meta), released in September 2019. It serves as a comprehensive platform for object detection, instance segmentation, panoptic segmentation, keypoint detection, and DensePose, implemented in PyTorch. It is the successor to the original Detectron framework, which was written in Caffe2, and offers a more modular and extensible codebase designed for both research and production use.Detectron2 includes implementations of Faster R-CNN, Mask R-CNN, RetinaNet, Cascade R-CNN, Panoptic FPN, and several other architectures. Its modular design allows components such as backbones, necks, and heads to be swapped independently, making it widely used as a baseline framework in academic research. It supports training on COCO-format datasets and integrates with standard distributed training setups.

Mask R-CNN is an instance segmentation model developed by Facebook AI Research (Meta), released in October 2017. It extends Faster R-CNN by adding a parallel branch that predicts binary segmentation masks for each detected object, independent of the classification and bounding box regression branches. A key contribution is RoIAlign, which replaces RoIPool with bilinear interpolation to preserve spatial correspondence between features and input pixels, significantly improving mask quality.Mask R-CNN achieves strong performance on the COCO instance segmentation benchmark and supports keypoint detection as an additional output head. It remains a foundational architecture in instance segmentation and is available through Meta's Detectron2 framework. The model is most appropriate for tasks requiring pixel-level object delineation, such as medical imaging, autonomous driving, and industrial inspection.