https://github.com/abhuse/cyclic-cosine-decay
There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
A Simple Framework for Contrastive Learning of Visual Representations
Towards Robust and Reproducible Active Learning Using Neural Networks
Applying Convolutional Neural Networks to Data on Unstructured Meshes with Space-Filling Curves
RandAugment: Practical automated data augmentation with a reduced search space
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
A Simple Way to Initialize Recurrent Networks of Rectified Linear Units
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Unsupervised Representation Learning by Predicting Image Rotations
Unsupervised Representation Learning by Predicting Image Rotations
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Image Classification with Classic and Deep Learning Techniques
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.