Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn computer vision techniques for search applications through hands-on implementation of image retrieval and classification methods. Master color histograms for image retrieval, implement bag of visual words for classification tasks, and explore deep learning architectures including AlexNet and convolutional neural networks using PyTorch. Dive into advanced topics such as Vision Transformers (ViT) with practical fine-tuning exercises, understand OpenAI's CLIP model for multi-modal machine learning, and apply CLIP for zero-shot image classification and fast object detection without traditional training data.
