https://github.com/George091/CNN
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
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.
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Very Deep Convolutional Networks for Large-Scale Image Recognition
Very Deep Convolutional Networks for Large-Scale Image Recognition
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach
Soft-Label Dataset Distillation and Text Dataset Distillation
FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics
Towards Partial Supervision for Generic Object Counting in Natural Scenes
Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks
Learning to Generalize: Meta-Learning for Domain Generalization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.