https://github.com/simo-bat/Crack_detection
Very Deep Convolutional Networks for Large-Scale Image Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Algorithms trying to solve the general task of classification.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Very Deep Convolutional Networks for Large-Scale Image Recognition
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Tile2Vec: Unsupervised representation learning for spatially distributed data
Very Deep Convolutional Networks for Large-Scale Image Recognition
Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
Very Deep Convolutional Networks for Large-Scale Image Recognition
Task Agnostic Robust Learning on Corrupt Outputs by Correlation-Guided Mixture Density Networks
Multitask Deep Learning with Spectral Knowledge for Hyperspectral Image Classification
Character-level Convolutional Networks for Text Classification
Hierarchical Representations for Efficient Architecture Search
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Very Deep Convolutional Networks for Large-Scale Image Recognition
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification
Adversarial Perturbations Against Real-Time Video Classification Systems
Anchor Loss: Modulating Loss Scale based on Prediction Difficulty
Discovering a sparse set of pairwise discriminating features in high dimensional data
Very Deep Convolutional Networks for Large-Scale Image Recognition
Robust Loss Functions under Label Noise for Deep Neural Networks
Bag of Tricks for Image Classification with Convolutional Neural Networks
SPECTER: Document-level Representation Learning using Citation-informed Transformers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.