본문 바로가기

논문 리뷰15

[D&A] 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.
[X:AI] Taskonomy 논문 리뷰 Taskonomy: Disentangling Task Transfer Learning 논문 원본 : https://arxiv.org/abs/1804.08328발표 영상 : https://www.youtube.com/watch?v=rKw-vg6jtt8발표 자료  Taskonomy: Disentangling Task Transfer LearningDo visual tasks have a relationship, or are they unrelated? For instance, could having surface normals simplify estimating the depth of an image? Intuition answers these questions positively, implying exis.. 2024. 5. 21.
[X:AI] SegNet 논문 리뷰 SegNet: A Deep Convolutional Encoder-Decdoer Architecture for Image Segmentation논문 원본   https://arxiv.org/abs/1511.00561 SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image SegmentationWe present a novel and practical deep fully convolutional neural network architecture for semantic pixel-wise segmentation termed SegNet. This core trainable segmentation engine consists of an enco.. 2024. 4. 9.
[X:AI] ELMo 논문 리뷰 논문 원본  https://arxiv.org/abs/1802.05365 Deep contextualized word representationsWe introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i.e., to model polysemy). Our word vectors arearxiv.org 발표 영상  https://www.youtube.com/watch?v=eu67_hJJrbM 오.. 2024. 3. 25.