End-to-end pipeline for adapting CLIP-style multi-modal models to domain-specific vision tasks. Uses Triplet Loss and custom retrieval metrics to enable semantic search over image/text pairs, with a focus on fashion datasets.
FashionCLIP
Deep learning pipeline for fine-tuning multi-modal vision models on custom datasets. Implementation of Triplet Loss and custom metric definitions for semantic search.
PyTorchMulti-modal TransformersFine-TuningModel Architecture