ImageNet
ImageNet is a large labeled image database organized according to the WordNet hierarchy and widely used for visual-recognition research and benchmarking.
Sutskever's List
ImageNet is a large-scale image dataset organized according to a hierarchical set of semantic categories for visual recognition research.
- How it is used
- Positions ImageNet as a large-scale benchmark for testing whether neural networks can advance visual recognition.
- How deep it goes
- Traces the dataset’s origins and competition results, but does not detail its construction or annotation procedures.
- Examples
- Uses tables, lamps, and mugs to illustrate object categories, then contrasts early SVM results with AlexNet’s error reduction.
- What you can do after
- Understand how ImageNet’s competition helped demonstrate the impact of CNNs on visual recognition.
Inside Deep Learning: Math, Algorithms, Models
A large image classification dataset with 1,000 classes used here as the pretraining source domain for ResNet.
- How it is used
- Provides the source-domain pretraining that initializes ResNet for transfer learning on a new image-classification task.
- How deep it goes
- Explains dataset scale, pretrained filters, and classifier replacement, but does not detail ImageNet's data construction.
- Examples
- Uses a pretrained ResNet-18 adapted with a new two-class layer for cat-versus-dog classification.
- What you can do after
- Apply via torchvision.models by loading an ImageNet-pretrained ResNet and replacing its final classifier.
Read how Inside Deep Learning: Math, Algorithms, Models explains ImageNet →
Related concepts
- foundational modelused by · A base or foundation model is a pretrained model that provides learned parameters or capabilities as a starting point for reuse or adaptation to downstream tasks.
- ResNet50used by · ResNet50 is a 50-layer residual convolutional neural network architecture for visual recognition and image processing.
- datasetkind of · A dataset is an organized collection of related data items, records, or observations treated as a unit for storage, processing, analysis, or computation.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.