전체 글74 [X:AI] Detr 논문 리뷰 End-to-End Object Detection with Transformers Abstract본 논문에서는 Object Detection을 direct set prediction problem으로 보고 있음해당 접근 방식은 Prior Knowledge (NMS or anchor generation)를 사용하지 않아 detection pipeline 간소화DETR(DEtection TRansformer) 주요 요소는 set-based global loss를 기반으로 한 bipartite matching과 Transformer Encoder-Decoder ArchitectureFast R-CNN과 유사한 정확도와 panoptic segmentation에서도 활용할 수 있을 정도로 잘 generalize.. 2024. 7. 23. [X:AI] MOFA-Video 논문 리뷰 MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model논문 원본 : https://arxiv.org/abs/2405.20222 MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion ModelWe present MOFA-Video, an advanced controllable image animation method that generates video from the given image using.. 2024. 7. 20. [X:AI] GAN 논문 리뷰 Generative Adversarial Nets논문 원본 : https://arxiv.org/abs/1406.2661 Generative Adversarial NetworksWe propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability thatarxiv.org 1. Abstract & Introduction mi.. 2024. 7. 17. [X:AI] SimCLR 논문 리뷰 A Simple Framework for Contrastive Learning of Visual Representations논문 원본 : https://arxiv.org/abs/2002.05709 A Simple Framework for Contrastive Learning of Visual RepresentationsThis paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architecture.. 2024. 7. 14. [X:AI] Grad-CAM 논문 리뷰 Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization 논문 원본 : https://arxiv.org/abs/1610.02391 Grad-CAM: Visual Explanations from Deep Networks via Gradient-based LocalizationWe propose a technique for producing "visual explanations" for decisions from a large class of CNN-based models, making them more transparent. Our approach - Gradient-weighted Class Activation Ma.. 2024. 7. 6. [Stanford cs231n] Lecture 11(Detection&Segmentation) 강의 주제Object DetectionSemantic SegmentationInstance SegmentationR-CNNFast R-CNNFaster R-CNNMask R-CNN강의 영상https://www.youtube.com/watch?v=nDPWywWRIRo&list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zxk&index=11강의 자료https://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture11.pdf 2024. 6. 16. 이전 1 ··· 3 4 5 6 7 8 9 ··· 13 다음
