Computer Vision129 [2025-2] 황징아이 - Big Self Supervised Models Advance Medical Image Classifications 논문 : https://arxiv.org/pdf/2101.05224 Introduction본 논문은 Self Supervised Learning의 방법중 SimCLR을 활용하여 의료 이미지 분류 성능을 향상 시키는 논문입니다.Self-Supervised Learning은 데이터에 라벨을 부여하지 않고도 학습이 가능하다는 점에서 라벨링 비용이 높은 의료 분야에서 특히 더 강점을 드러낸다. SSL는 그동안 일반 이미지 도메인에서 많이 연구 되어 왔지만 본 논문은 SSL을 의료 도메인에 적용했다는 점에서 의미가 있고 기존 Supervised Learning 방식보다 효율적이고 좋은 일반화 성능을 보여줬다. 3단계의 학습 파이프라인을 제안한다 :ImageNet 기반 Self-Supervised Pretraini.. 2025. 7. 12. [2025-2] 전연주 - MaeTok: Masked Autoencoders Are Effective Tokenizers for Diffusion Models 논문 링크: arxiv.org/pdf/2502.03444깃허브 링크: Hhhhhhao/continuous_tokenizer GitHub - Hhhhhhao/continuous_tokenizerContribute to Hhhhhhao/continuous_tokenizer development by creating an account on GitHub.github.com허깅페이스 링크: MAETok/maetok-b-128 · Hugging Face MAETok/maetok-b-128 · Hugging FaceThis model has been pushed to the Hub using the PytorchModelHubMixin integration: Library: [More Information Need.. 2025. 7. 12. [2025-1] 최민서 - SDEDIT: Guided Image Synthesis and Editing with Stochastic Differential Equations [논문링크] https://arxiv.org/abs/2108.01073 SDEdit: Guided Image Synthesis and Editing with Stochastic Differential EquationsGuided image synthesis enables everyday users to create and edit photo-realistic images with minimum effort. The key challenge is balancing faithfulness to the user input (e.g., hand-drawn colored strokes) and realism of the synthesized image. Existing GANarxiv.org SDE Diffusi.. 2025. 6. 24. [2025-1] 황징아이 - Convolutional Character Networks 논문 : https://arxiv.org/abs/1910.07954 Convolutional Character NetworksRecent progress has been made on developing a unified framework for joint text detection and recognition in natural images, but existing joint models were mostly built on two-stage framework by involving ROI pooling, which can degrade the performance on rearxiv.org 1. Introduction기존 Text Reading 모델은 2단계를 거친다텍스트 검출 (Text Detect.. 2025. 5. 31. 이전 1 2 3 4 ··· 33 다음
