clovaai

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

Text recognition (optical character recognition) with deep learning methods, ICCV 2019

StarGAN v2 - Official PyTorch Implementation (CVPR 2020)

Official implementation of Character Region Awareness for Text Detection (CRAFT)

Official Pytorch implementation of CutMix regularizer

In defence of metric learning for speaker recognition

Software that can perform photorealistic style transfer without the need of any post-processing steps.

Official Implementation of SynthTIGER (Synthetic Text Image Generator), ICDAR 2021

CORD: A Consolidated Receipt Dataset for Post-OCR Parsing

Rethinking the Truly Unsupervised Image-to-Image Translation - Official PyTorch Implementation (ICCV 2021)

Official Pytorch implementation of ReXNet (Rank eXpansion Network) with pretrained models

Official PyTorch implementation of "A Comprehensive Overhaul of Feature Distillation" (ICCV 2019)

AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (ICLR 2021)

Rethinking Data Augmentation for Image Super-resolution (CVPR 2020)

Evaluating Weakly Supervised Object Localization Methods Right (CVPR 2020)

Tensorflow implementation of "Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network"

Official PyTorch implementation of "AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks"

Code base for the precision, recall, density, and coverage metrics for generative models. ICML 2020.

The unified repository for few-shot font generation methods. This repository includes FUNIT (ICCV'19), DM-Font (ECCV'20), LF-Font (AAAI'21) and MX-Font (ICCV'21).

ClovaCall dataset and Pytorch LAS baseline code (Interspeech 2020)

Official PyTorch implementation of LF-Font (Few-shot Font Generation with Localized Style Representations and Factorization) AAAI 2021

CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks

Official PyTorch implementation of MX-Font (Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts) ICCV 2021

Official EXTD Pytorch code

StarGAN v2 - Official Tensorflow Implementation (CVPR 2020)

TedEval: A Fair Evaluation Metric for Scene Text Detectors

Official Pytorch implementation of ReBias (Learning De-biased Representations with Biased Representations), ICML 2020

Official Tensorflow Implementation of SATRN (CVPR Workshop WTDDLE 2020)

Official PyTorch implementation of DM-Font (ECCV 2020)

SOM-DST: Efficient Dialogue State Tracking by Selectively Overwriting Memory (ACL 2020)

Official pytorch implementation of Rainbow Memory (CVPR 2021)

Official implementation for (Show, Attend and Distill: Knowledge Distillation via Attention-based Feature Matching, AAAI-2021)

[EMNLP 2019] Mixture Content Selection for Diverse Sequence Generation (Question Generation / Abstractive Summarization)

Official Implementation of Web-based Visual Corpus Builder (Webvicob), ICDAR 2023

FrostNet: Towards Quantization-Aware Network Architecture Search

Official Pytorch Implementation of Length-Adaptive Transformer (ACL 2021)

Official MXNet implementation of "Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning" (CVPR 2020)

Look Who’s Talking: Active Speaker Detection in the Wild

Official Tensorflow implementation of "Symmetrical Synthesis for Deep Metric Learning" (AAAI 2020)

Subword Language Model for Query Auto-Completion

Official PyTorch Implementation of SSMix (Findings of ACL 2021)

[NeurIPS 2021] SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning

[CVPR2023] The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation

[CVPR 2022] Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement

(CVPR 2024) ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning