Meta: DINOv2

OpenAI CLIP (Contrastive Language-Image Pretraining) is a vision-language model released in January 2021 by OpenAI. It jointly trains an image encoder and a text encoder to produce matching embeddings for image-caption pairs, using a contrastive objective over WebImageText (WIT), a dataset of 400 million image-text pairs collected from the public web. By learning to associate images with free-form text rather than a fixed set of class labels, CLIP produces a shared embedding space that enables zero-shot classification with arbitrary vocabularies at inference time.CLIP supports zero-shot image classification by embedding candidate class labels as text and selecting the label whose embedding is closest to a given image's embedding. It is also widely used for image-text retrieval, as a frozen backbone in downstream vision-language models, and as a building block for content moderation, similarity search, and generative model guidance — notably as the text conditioning mechanism in early versions of Stable Diffusion. OpenAI released several CLIP variants built on different vision encoders, including ResNet and Vision Transformer backbones at multiple sizes and input resolutions, with ViT-L/14 at 336 pixels being the largest and most widely adopted. CLIP is distributed under the MIT license. The model has been widely influential as the basis for subsequent vision-language work — including SigLIP, OpenCLIP, and MetaCLIP — and remains a common reference baseline despite being released in 2021 and surpassed on many benchmarks by later models.

ResNet-50 is a deep convolutional neural network architecture introduced in the 2015 paper "Deep Residual Learning for Image Recognition" by Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun at Microsoft Research. It is part of the ResNet (Residual Network) family, which introduced residual connections — shortcut paths that allow gradients to bypass layers during training — solving the degradation problem that had previously limited the practical training of very deep networks. ResNet-50 specifically refers to a 50-layer variant with approximately 25.6 million parameters, structured as a sequence of bottleneck residual blocks consisting of 1×1, 3×3, and 1×1 convolutions.ResNet-50 was trained on the ImageNet classification benchmark and achieved leading top-1 accuracy at release. Beyond classification, it became a widely used backbone feature extractor for downstream tasks including object detection (as the base network in Faster R-CNN, Mask R-CNN, and RetinaNet) and semantic and instance segmentation. Most current implementations in PyTorch torchvision, TensorFlow, and NVIDIA NGC use the ResNet-50 v1.5 variant, which relocates the stride-2 downsampling from the first 1×1 convolution to the 3×3 convolution within each bottleneck block, yielding approximately 0.5% higher top-1 accuracy than the original v1 formulation at a small throughput cost. ResNet-50 remains a common reference architecture in computer vision benchmarks and a standard backbone choice in detection and segmentation frameworks. The original Microsoft Research code is released under the MIT license.

YOLOv8 Classification is the image classification variant of the YOLOv8 model family from Ultralytics, released in January 2023. Unlike the primary YOLOv8 detection and segmentation models, which predict bounding boxes or pixel masks, YOLOv8 Classification predicts a single class label for a full input image, supporting standard single-label image classification tasks. It shares the YOLOv8 backbone architecture, including the C2f (Cross-Stage Partial with 2 convolutions) module, with the detection variants, making it straightforward to use within the same Ultralytics training and inference workflow as other YOLOv8 tasks.YOLOv8 Classification is released at five sizes: YOLOv8n-cls (nano, 2.7M parameters), YOLOv8s-cls (small, 6.4M), YOLOv8m-cls (medium, 17.0M), YOLOv8l-cls (large, 37.5M), and YOLOv8x-cls (extra-large, 57.4M). These variants allow users to trade off accuracy against inference speed and memory footprint. Pretrained checkpoints are provided for ImageNet classification at 224 pixel resolution, and the model can be fine-tuned on custom datasets using the Ultralytics Python API or command-line tools. The model supports export to common deployment formats including ONNX, TensorRT, CoreML, and TensorFlow Lite. YOLOv8 Classification is distributed under the AGPL-3.0 license, with an Enterprise License available from Ultralytics for proprietary deployments. The YOLOv8 family has since been succeeded by YOLO11 (September 2024) and YOLO26 (January 2026), each of which includes equivalent classification variants.

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.