중간발표 : 최종적으로 리뷰, 참조한 논문 목록

1차 정기모임까지 리뷰 마친 논문 목록

A. design neural networks and object detection

1. Going deeper with convolutions

2. Rethinking the Inception Architecture for Computer Vision

3. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

4. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

5. Deep Residual Learning for Image Recognition

6. Residual Networks are Exponential Ensembles of Relatively Shallow Networks

7. Speed/accuracy trade-offs for modern convolutional object detectors

8. Dropout: A simple way to prevent neural networks from overfitting

//Dropout은 언급만하고 요지만 설명후 넘어갔습니다.

2차 정기모임까지 리뷰 마친 논문 목록

B. Viusal semantic embedding

1. Deep Visual-Semantic Alignments for Generating Image Descriptions***

2. Order-embeddings of images and language

3. Unifying visual-semantic embeddings with multimodal neural language models

4. Multimodal convolutional neural networks for matching image and sentence

5. Deep reinforcement learning-based image captioning with embedding reward

C. Image caption

1. Show and Tell: a neural image caption generator

2. Show, Adapt and Tell: Adversarial training of cross-domain image captioner

3. Show, Attend and Tell: Neural image caption generation with visual attention ***

4. Bottom-up and top-down attention for image captioning and visual question answering ***

5. Generating images from captions with attention***

D. unsupervised learning, Deep Generative Model

1. Building high-level features using large scale unsupervised learning

2. Auto-encoding variational bayes

3. Generative adversarial nets

4. Unsupervised representation learning with deep convolutional generative adversarial networks

5. DRAW: A recurrent neural network for image generation.

6. Pixel recurrent neural networks

7. Conditional image generation with PixelCNN decoders

// ***표시 논문은 내용의 복잡도가 높아 다시 읽기로 했습니다. 3차 정기모임까지 리뷰 마친 논문 목록

E. image attention mechanism

1. Show, Attend and Tell: Neural image caption generation with visual attention***

2. Generating images from captions with attention

3. Self-Attention Generative Adversarial Networks

4. Bottom-up and top-down attention for image captioning and visual question answering***

5. Generative Image Inpainting with Contextual Attention***

6. Watch What You Just Said: Image Captioning with Text-Conditional Attention

7. Deep Visual-Semantic Alignments for Generating Image Descriptions***

// ***표시 논문은 다시 읽은 논문입니다.

F. generative adversarial nets

1. Unsupervised representation learning with deep convolutional generative adversarial networks(DCGAN 2016)

2. Semi-Supervised Learning with Generative Adversarial Networks(SLGAN 2016)

3. Conditional Generative Adversarial Nets(CGAN 2014)

4. Wang_Stacked_Conditional_Generative(StackedGAN 2018)

5. chang_PairedCycleGAN_Asymmetric_Style(CycleGAN 2018)