Google: MobileNetV2

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.

Vision Transformer is an image classification model developed by Google Research, first published in October 2020. It applies the transformer architecture directly to sequences of image patches without convolutional layers. Each image is divided into fixed-size patches, linearly projected into embeddings, and processed by a standard transformer encoder with multi-head self-attention. A classification token prepended to the patch sequence aggregates global image information for the final prediction.When pre-trained on large datasets such as JFT-300M and fine-tuned on ImageNet, ViT achieves competitive accuracy with state-of-the-art CNNs of the period. It performs best when pre-training data is abundant, as the lack of convolutional inductive biases makes it less data-efficient than CNN-based classifiers on smaller datasets. ViT established the foundation for transformer-based vision architectures and has influenced a broad range of subsequent models.

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.

ResNet-34 is a deep residual network for image classification introduced by Kaiming He et al. in December 2015. It is a medium-sized variant in the original ResNet family, designed for ImageNet-scale classification with 34 convolutional layers organized into residual blocks using skip connections. These connections allow the model to learn residual mappings rather than full transformations, mitigating the vanishing gradient problem and enabling stable training of deeper architectures.ResNet-34 achieves a top-5 error rate of 7.36% on the ImageNet validation set. It is widely used as a backbone for transfer learning across classification, detection, and segmentation tasks and remains a common baseline architecture in computer vision research. The model is available through Meta's torchvision library.

SigLIP is a vision-language model released in March 2023 by researchers at Google DeepMind. It adapts the CLIP image-text pretraining approach by replacing CLIP's softmax-based contrastive loss with a pairwise sigmoid loss, which operates independently on each image-text pair rather than requiring a global view of all pairs in a batch. This change decouples the loss from batch size, enabling more memory-efficient training and improved performance at smaller batch sizes, a regime where softmax contrastive learning typically struggles. Despite this simplification, SigLIP matches or exceeds CLIP-style models on zero-shot image classification and image-text retrieval benchmarks when trained on comparable data.SigLIP is distributed as an image encoder plus aligned text encoder, supporting zero-shot classification with arbitrary class vocabularies, image-text retrieval, and use as a frozen backbone in downstream vision-language models. Pretrained models are available at multiple Vision Transformer sizes and input resolutions, including 224, 256, 384, and 512 pixel inputs. SigLIP is released under the Apache 2.0 license by Google and is used as the vision encoder in Google's PaliGemma and PaliGemma 2. A successor, SigLIP 2, was released in February 2025 with multilingual support across 109 languages, improvements to localization and dense prediction, and two resolution handling variants (FixRes for backward-compatible fixed resolutions and NaFlex for native aspect ratio with variable sequence length).

DINOv2 is a self-supervised vision foundation model released in April 2023 by Meta AI's FAIR lab. It produces general-purpose visual features that transfer to a wide range of downstream tasks (including image classification, semantic segmentation, depth estimation, and image retrieval) without requiring task-specific fine-tuning. DINOv2 is trained on a curated dataset of 142 million images using a self-supervised objective combining student-teacher distillation, masked image modeling, and an image-level contrastive loss, extending the approach introduced in the original DINO.The model family spans Vision Transformer sizes from ViT-S (21M parameters) to ViT-g (1.1B parameters), with the larger variants setting state-of-the-art results on linear-probing benchmarks for classification, segmentation, and dense prediction tasks at release. DINOv2 features can be used directly as frozen backbones, reducing the need for labeled training data in downstream applications. The model is primarily used as an image encoder rather than as a complete task-specific model, making it a common backbone choice for custom vision pipelines. DINOv2 code and pretrained weights are released under the Apache 2.0 license, which was adopted after an initial CC-BY-NC 4.0 release in response to community requests for commercial compatibility. A successor model, DINOv3, was released in August 2025 with further scaling and a new training technique called Gram anchoring.