[Paper Explain] Communication-Efficient Learning of Deep Networks from Decentralized Data

[Paper Explain] Lottery Ticket Hypothesis

Understanding YOLOX: A Breakthrough in Object Detection - Paper Explanation

[Paper Explain] DualStyleGAN: Exemplar-Based High-Resolution Portrait Style Transfer

[Paper Explain] JoJoGAN for One Shot Face Stylization

[Paper Explain] - Hiểu về Skip Connection - một kĩ thuật "nhỏ mà có võ" trong các kiến trúc Residual Networks

[Paper Explain] Two-phase training mitigates class imbalance for camera trap image classification with CNNs

[Paper Explain] Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection

[Paper Explain] Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection

[Paper Explain] Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition - Bàn luận 1 chút về video augmentation.

[Paper Explain] A Simple Framework for Contrastive Learning of Visual Representations

[Paper Summary] YOLOR: A New Trend in Computer Vision?

[Paper Explain] Thủ thuật làm tăng độ chính xác cho các mạng Object Detection

[Paper Explain][End-to-End Dense Video Captioning with Parallel Decoding] PDVC - Hướng tiếp cận end-to-end với giải mã song song cho bài toán Dense Video Captioning

[Paper Explained] - mixup: BEYOND EMPIRICAL RISK MINIMIZATION

[Paper Explain] What’s Hidden in a Randomly Weighted Neural Network? - Implement with PyTorch

[Paper Explain] Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

[Paper Explain] Deep Learning on a Data Diet: Finding Important Examples Early in Training

[Paper Explain][Face Anti-Spoofing phần 2] SGTD - Tận dụng thông tin không gian và thời gian cho bài toa Face Anti-spoofing

[Paper Explain] EFFICIENT MASKED FACE RECOGNITION METHOD DURING THECOVID-19 PANDEMIC

[Paper Explaination] A survey of loss functions for semantic segmentation

[Paper Explain] Thủ thuật cho các mạng CNN trong Classification

[Paper Explain] Reading Race: AI Recognises Patient's Racial Identity In Medical Images

[Paper Explaination] V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

[Paper Explain] Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection

[Paper Explain] Revisiting Skeleton-based Action Recognition - BKAI-NAVER Challenge 2022 Top1 Solution Baseline