전체 글76 [X:AI] SAM 논문 리뷰 논문 원본 : https://arxiv.org/abs/2304.02643 Segment AnythingWe introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest segmentation dataset to date (by far), with over 1 billion masks on 11M licensearxiv.org 1. Introduction대규모 웹 데이터셋으로 사전 학습된 LLM은 zero-shot 및 few-shot 일반화 성능을 통해 NL.. 2025. 8. 10. [X:AI] DINO 논문 리뷰 논문 원본 : https://arxiv.org/abs/2104.14294 Emerging Properties in Self-Supervised Vision TransformersIn this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets). Beyond the fact that adapting self-supervised methods to this architecture works particarxiv.org 1. Introduction ViT는 CNN과 경쟁력이 있지.. 2025. 7. 28. [X:AI] ViT 논문 리뷰 논문 원본 : https://arxiv.org/abs/2010.11929 An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleWhile the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to reparxiv.org 1. IntroductionS.. 2025. 7. 14. [X:AI] YOLOv4 논문 리뷰 논문 원본 : https://arxiv.org/abs/2004.10934 YOLOv4: Optimal Speed and Accuracy of Object DetectionThere are a huge number of features which are said to improve Convolutional Neural Network (CNN) accuracy. Practical testing of combinations of such features on large datasets, and theoretical justification of the result, is required. Some features operatearxiv.org 1. Introduction고속 고정확도의 객체 탐지기를 일반적인 .. 2025. 7. 9. [X:AI] ELECTRA 논문 리뷰 논문 원본 : https://arxiv.org/abs/2003.10555발표 영상 : https://www.youtube.com/watch?v=_uqNrzZKlk0 ELECTRA: Pre-training Text Encoders as Discriminators Rather Than GeneratorsMasked language modeling (MLM) pre-training methods such as BERT corrupt the input by replacing some tokens with [MASK] and then train a model to reconstruct the original tokens. While they produce good results when transferred to.. 2025. 5. 13. [Paper Review] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks 논문 원본 : https://arxiv.org/abs/2005.11401 Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksLarge pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, their ability to access and precisely manipulate knowledge is still limarxiv.org 1. Introduction사전학습된 신경망 언.. 2025. 4. 20. 이전 1 2 3 4 ··· 13 다음
