Paper Notes

Paper Notes

CascadeTabNet An approach for end to end table detection and structure recognition from image-based documents

CDeC-Net Composite Deformable Cascade Network for Table Detection in Document Images

CharFormer A Glyph Fusion based Attentive Framework for High-Confidence Regularized Self-Training

data2vec

DE⫶TR End-to-End Object Detection with Transformers

Diffusion Models Beat GANs on Image Synthesis

DINO

Discriminative Feature Alignment Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment

DocTr Document Image Transformer for Geometric Unwarping

Document Dewarping with Control Points

Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting Entropy Minimization vs. Diversity Maximization

Few-shot Compositional Font Generation with Dual Memory

Few-shot Font Generation with Multiple Localized Experts

Hierarchical Text-Conditional Image Generation with CLIP Latents

LiLT A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding

LoFTR Detector-Free Local Feature Matching with Transformers

Mask TextSpotter v3 Segmentation Proposal

MaskOCR Text Recognition with Masked

Maximum Density Divergence for Domain Adaptation

Mean teachers are better role models Weight-averaged consistency targets improve semi-supervised deep learning results

MixMatch A Holistic Approach to Semi-Supervised Learning

R2D2 Repeatable and Reliable Detector and Descript

Segmentation Domain Adaptation Notes

Semi-supervised Learning by Entropy Minimization

Sequence-to-Sequence Contrastive Learning & ScrabbleGAN

Sequence-to-Sequence Domain Adaptation

Simple Baselines for Image Restoration

SVTR Scene Text Recognition with a Single Visual Model

Text Gestalt Stroke-Aware Scene Text Image Super-Resolution

THE CURIOUS CASE OF NEURAL TEXT DeGENERATION

Unified Contrastive Learning in Image-Text-Label Space

Workshop & Conference Notes

Fintech Survey 2022 notes

ICIP 2022 notes

INTERSPEECH 2022 notes

OPTIMIZING MODEL PARAMETERS in Pytorch

Adafactor: Adaptive Learning Rates with Sublinear Memory Cost