Sep 7, 2025 · Artificial Intelligence

Tackling Imbalanced Data: MixUp, CutMix, and Focal Loss Explained

This article examines the challenges of imbalanced datasets in machine learning, especially in fields like medical imaging, and provides a detailed analysis of three key techniques—MixUp data mixing, CutMix region replacement, and the Focal Loss function—along with their implementations, advantages, limitations, and practical integration strategies.

CutMixFocal LossMixUp

0 likes · 11 min read

Tackling Imbalanced Data: MixUp, CutMix, and Focal Loss Explained

Meitu Technology

Aug 17, 2018 · Artificial Intelligence

Deep Learning-based Object Detection Algorithm Review (Part 2): Solutions and Network Improvements

The article reviews deep learning object detection solutions: small object detection via FPN and TDM, irregular shapes via deformable convolution, sample imbalance via focal loss and cascade methods, occlusion handling with Soft‑NMS and RRC, large‑batch training using MegDet, relationship modeling with Relation Networks, and network improvements such as DetNet, RefineDet, Pelee, and RFBNet.

FPNFocal LossNeural Networks

0 likes · 38 min read

Deep Learning-based Object Detection Algorithm Review (Part 2): Solutions and Network Improvements