https://github.com/guoyurong0104/crl-code
공식 코드Competing Ratio Loss for Discriminative Multi-class Image Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Facial tasks in machine learning operate based on images or video frames (or other datasets) focussed on human faces.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Competing Ratio Loss for Discriminative Multi-class Image Classification
FoundPAD: Foundation Models Reloaded for Face Presentation Attack Detection
MADation: Face Morphing Attack Detection with Foundation Models
DAAL: Density-Aware Adaptive Line Margin Loss for Multi-Modal Deep Metric Learning
End2End Occluded Face Recognition by Masking Corrupted Features
What Should Be Balanced in a "Balanced" Face Recognition Dataset?
Face Recognition Accuracy Across Demographics: Shining a Light Into the Problem
Logical Consistency and Greater Descriptive Power for Facial Hair Attribute Learning
LFW-Beautified: A Dataset of Face Images with Beautification and Augmented Reality Filters
Ensemble Learning using Transformers and Convolutional Networks for Masked Face Recognition
Towards Semi-Supervised Deep Facial Expression Recognition with An Adaptive Confidence Margin
DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection
One-shot Face Sketch Synthesis in the Wild via Generative Diffusion Prior and Instruction Tuning
A Unified Framework for Masked and Mask-Free Face Recognition via Feature Rectification
Regularizing Face Verification Nets For Pain Intensity Regression
Teacher-Student Adversarial Depth Hallucination to Improve Face Recognition
Depth-Aware Generative Adversarial Network for Talking Head Video Generation
SpanEmo: Casting Multi-label Emotion Classification as Span-prediction
Center and Scale Prediction: Anchor-free Approach for Pedestrian and Face Detection
TT-DF: A Large-Scale Diffusion-Based Dataset and Benchmark for Human Body Forgery Detection
Distributional Modeling for Location-Aware Adversarial Patches
Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.