arXiv (Cornell University) · 2024 · 12 citations · 0 references
ComputingComputer ScienceComputer VisionMachine LearningNatural Language ProcessingDeep LearningLanguage ModelingObject RecognitionPattern RecognitionScene UnderstandingTransfer LearningModel Base DesignMulti-task Learning For Computer VisionRepresentation Learning For TransferRepresentation TransferTransferable Representation LearningVision TransferVisual Transfer Learning
PaliGemma is an open Vision-Language Model (VLM) that is based on the SigLIP-So400m vision encoder and the Gemma-2B language model. It is trained to be a versatile and broadly knowledgeable base model that is effective to transfer. It achieves strong performance on a wide variety of open-world tasks. We evaluate PaliGemma on almost 40 diverse tasks including standard VLM benchmarks, but also more specialized tasks such as remote-sensing and segmentation.