Jonas Jarutis

This presentation examines approaches for detecting and eliminating near-duplicate images across datasets ranging from small collections to repositories containing millions of images. We will compare the performance of several embedding models, including CLIP, ResNet, and other variants,...

Machine learning (ML) model serialization helps to optimize inference latency, memory, and disk space requirements and provides more options for model deployment. We will explore the use cases that benefit the most from this technique and some drawbacks.