Explore machine learning papers and reviews related to computervision. Find insights, analysis, and implementation details.
How AlexNet won ImageNet 2012 by a landslide and launched the deep-learning era: a deep convolutional network trained on two GPUs with ReLU activations, dropout regularization, and aggressive data augmentation.
How Florence-2 turns detection, segmentation, grounding, captioning, and OCR into one sequence-to-sequence problem driven by task prompts, expressing spatial outputs as location tokens in the text vocabulary.
How SAM 2 extends promptable segmentation from images to video with a streaming memory bank and memory attention, propagating masks across frames and recovering objects after occlusion.