Anleeno-Xu/ILuvCV

Fabulous papers for CV field.

ILuvCV

Fabulous papers for CV field.

Conference Deadlines

• AI Deadlines
• CCF Deadlines

Contents

• 1. Summary of Conference Papers
• 2. Papers of Some Fields
• 2.1. Common Vision Backbone
  • Vision Transformer
  • CNN
  • GNN
• 2.2. Object Detection
• 2.3. Image Segmentation
• 2.4. Data Augmentation
• 2.5. Image Enhancement
  • Backlit/Dark-night Image Enhancement
  • Dehazing
  • Denoising
  • Feature Matching
  • HDR
• 2.6. Image Composition

1. Summary of Conference Papers

• CVPR2023 -> Paper List

2. Papers of Some Fields

2.1. Common Vision Backbone

Vision Transformer

1. (ICLR 2021) An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
   • paper: ViT
2. (ICCV 2021) Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
   • paper: Swin Transformer
3. (CVPR 2022) Swin Transformer V2: Scaling Up Capacity and Resolution
   • paper: Swin Transformer v2
4. (ICCV 2023) FLatten Transformer: Vision Transformer using Focused Linear Attention
   • paper: Flatten Transformer
5. (ICCV 2023) SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications
   • paper: SwiftFormer

CNN

1. (CVPR 2015) Going Deeper with Convolutions
   • paper: GoogLeNet
2. (CVPR 2016) Deep Residual Learning for Image Recognition
   • paper: ResNet
3. (CVPR 2018) MobileNetV2: Inverted Residuals and Linear Bottlenecks
   • paper: MobileNetv2
4. (ECCV 2018) ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
   • paper: ShuffleNet v2
5. (CVPR 2023) SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy
   • paper: SCConv
6. (ICCV 2023) RepViT: Revisiting Mobile CNN From ViT Perspective
   • paper: RepViT
   • code: https://github.com/THU-MIG/RepViT/

GNN

2.2. Object Detection

• Paper List

2.3. Image Segmentation

1. (CVPR 2015 best) Fully Convolutional Networks for Semantic Segmentation
   • paper: https://arxiv.org/abs/1411.4038
   • code: https://github.com/pytorch/vision/blob/main/torchvision/models/segmentation/fcn.py
2. (MICCAI 2015) U-Net: Convolutional Networks for Biomedical Image Segmentation
   • paper: https://arxiv.org/abs/1505.04597
   • code: https://github.com/milesial/Pytorch-UNet
3. (ICCV 2017) Mask R-CNN
   • paper: https://arxiv.org/abs/1703.06870
   • code: https://github.com/facebookresearch/Detectron
4. (CVPR 2019) Panoptic FPN：Panoptic Feature Pyramid Networks
   • paper: https://arxiv.org/abs/1901.02446
   • code: https://github.com/facebookresearch/detectron2
5. (CVPR 2021) Panoptic FCN：Panoptic Fully Convolutional Networks
   • paper: https://arxiv.org/abs/2012.00720v2
   • code: https://github.com/dvlab-research/PanopticFCN
6. (ICCV 2023) Segment Anything
   • paper: https://arxiv.org/abs/2304.02643
   • code: https://github.com/facebookresearch/segment-anything
7. (Arxiv 2023) Fast Segment Anything
   • paper: https://arxiv.org/abs/2306.12156
   • code: https://github.com/casia-iva-lab/fastsam

2.4. Data Augmentation

Survey

1. (Arxiv 2023) Advanced Data Augmentation Approaches: A Comprehensive Survey and Future directions
   • paper: https://arxiv.org/abs/2301.02830
   • link: https://github.com/kmr2017/Advanced-Data-augmentation-codes

Research

1. (CVPR 2019) AutoAugment: Learning Augmentation Policies from Data

   • paper: https://arxiv.org/abs/1805.09501v1
   • code: https://github.com/DeepVoltaire/AutoAugment

2. (CVPRW 2020) Randaugment: Practical automated data augmentation with a reduced search space

   • paper: https://arxiv.org/abs/1909.13719
   • code: https://github.com/heartInsert/randaugment

3. (Arxiv 2017) Improved Regularization of Convolutional Neural Networks with Cutout

   • paper: https://arxiv.org/abs/1708.04552
   • code: https://github.com/uoguelph-mlrg/Cutout

4. (AAAI 2020) Random Erasing Data Augmentation

   • paper: https://arxiv.org/abs/1708.04896
   • code: https://github.com/zhunzhong07/Random-Erasing

5. (ICCV 2017) Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization

   • paper: https://arxiv.org/abs/1811.02545
   • code: https://github.com/kkanshul/Hide-and-Seek

6. (Arxiv 2020) GridMask Data Augmentation

   • paper: https://arxiv.org/abs/2001.04086
   • code: https://github.com/dvlab-research/GridMask

7. (ICLR 2018) Mixup: Beyond Empirical Risk Minimization

   • paper: https://arxiv.org/abs/1710.09412
   • code: https://github.com/facebookresearch/mixup-cifar10

8. (ICCV 2019) CutMix: Regularization Strategy to Train Strong Classififiers with Localizable Features

   • paper: https://arxiv.org/abs/1905.04899v2
   • code: https://github.com/clovaai/CutMix-PyTorch

2.5. Image Enhancement

Backlit/Dark-night Image Enhancement

1. (ICCV 2023) Iterative Prompt Learning for Unsupervised Backlit Image Enhancement
   • paper: CLIP-LIT
   • code: https://github.com/ZhexinLiang/CLIP-LIT
2. (ICCV 2023) Empowering Low-Light Image Enhancer through Customized Learnable Priors
   • paper: CUE
   • code: https://github.com/zheng980629/CUE
3. Double Domain Guided Real-Time Low-Light Image Enhancement for Ultra-High-Definition Transportation Surveillance
   • paper: DDNet
   • code: https://github.com/QuJX/DDNet
4. Dimma: Semi-supervised Low Light Image Enhancement with Adaptive Dimming
   • paper: Dimma
   • code: https://github.com/WojciechKoz/Dimma

Dehazing

1. (ICCV 2023) MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing
   • paper: MB-TaylorFormer
   • code: https://github.com/FVL2020/ICCV-2023-MB-TaylorFormer

Denosing

1. (ICCV 2023) Lighting Every Darkness in Two Pairs: A Calibration-Free Pipeline for RAW Denosing
   • paper: LED
   • code: https://github.com/Srameo/LED

Feature Matching

1. (ICCV 2023) LightGlue: Local Feature Matching at Light Speed
   • paper: LightGlue
   • code: https://github.com/cvg/LightGlue

HDR

1. (IPOL 2021) An Analysis and Implementation of the HDR+ Burst Denoising Method
   • paper: HDR+
   • code: python, C++

2.6. Image Composition

Survey

1. (Arxiv 2021) Making Images Real Again: A Comprehensive Survey on Deep Image Composition
   • paper: https://arxiv.org/abs/2106.14490
   • link: https://github.com/bcmi/Awesome-Image-Composition