Generative model

[diffusion model] Denoising Diffusion Probabilistic Models (Neurips 2020)

StyleT2I:Toward Compositional and High-Fidelity Text-to-Image Synthesis ( CVPR 2022 )

StarGAN v1

[GAN] WGAN(Wasserstein GAN) (2017)

[GAN]Conditional Generative Adversarial Nets( cGAN ) (2014)

DCGAN (2016)

Self-supervised learning

DINO(Emerging Properties in Self-Supervised Vision Transformers)(Facebook AI Research, 2021)

[VQ-VAE] Neural Discrete Representation Learning

Denoising Pretraining for Semantic Segmentation (CVPR 2022)

Image Restoration

Improving Image Restoration by Revisiting Global Information Aggregation (ECCV 2022)

Dual Super-Resolution Learning for Semantic Segmentation ( CVPR2020 ) (1)

Perceptual Variousness Motion Deblurring with Light Global Context Refinement ( ICCV 2021 ) (1)

Wide Receptive Field and Channel Attention Network for JPEG Compressed Image Deblurring(CVPR 2021) (1)

High-Resolution Dual-Stage Multi-Level Feature Aggregation for Single Image and Video Deblurring(CVPR 2020) (1)

DeblurGANv2(ICCV 2019)

When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach ( IJCAI 2018 ) (1)

HINet: Half Instance Normalization Network for Image Restoration( CVPR 2021 )

MPRNet(CVPR 2021)

DeblurGAN (CVPR 2018)

etc.

[ConvMixer] Patches Are All You Need?

[skipinit]Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks(Camera-ready version of NeurIPS 2020)

Pay Less Attention with LightWeight and Dynamic Convolution

Non-Local Neural Networks(CVPR 2018)

CBAM: Convolutional Block Attention Module(ECCV 2018)

[SENet] Squeeze-and-Excitation Networks ( CVPR 2018 )

[KD]Solving ImageNet : a Unified Scheme for Training any Backbone to Top Results

Grad CAM: Visual Explanations from Deep Networks via Gradient-based Localization

VGG

Inception V1 ~ V3

ResNet, VGG16 구현하고 비교하기

ResNet 꼼꼼한 리뷰

Transformer

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (2021)

Multi modal

CLIP : Learning Transferable Visual Models From Natural Language Supervision (2021)

Segmentation

Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation (CVPR2019)

CGNet : : A Light-weight Context Guided Network for Semantic Segmentation (2020)

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation(2016)

Deeplab

U-Net

Semi-supervised Segmentation

UniMatch: Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation (CVPR 2023)

PS-MT : Perturbe and Strict Mean Teachers for Semi-supervised Semantic Segmentation

$U^2PL$ : Semi-supervised Semantic Segmentation Using Unreliable Pseudo Label ( CVPR 2022 )

Part Segmentation

이전 블로그 글

DeepSORT(SIMPLE ONLINE AND REALTIME TRACKING WITH A DEEP ASSOCIATION METRIC)

SORT(Simple Online And Realtime Tracking)

A Style-Based Generator Architecture for Generative Adversarial Networks:StyleGAN

Unpaired Image-to-Image Translationusing Cycle-Consistent Adversarial Networks (CycleGAN)

SSD: Single Shot MultiBox Detector

SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization(CVPR 2020)

Pix2Pix code review 코드리뷰

[Pix2Pix]Image-to-Image Translation with Conditional Adversarial Networks

U-GAT-IT

Spatially Attentive Output Layer for Image Classification (SAOL)(CVPR 2020)

Class Activation Map(Learning Deep Features for Discriminative Localization) (CVPR2016)

Attention Branch Network: Learning of Attention Mechanism for Visual Explanation(ABN, CVPR2019)요약

DeOldify