https://github.com/2023-MindSpore-1/ms-code-142
MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens
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.
MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens
CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification
EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
3D CNN with Localized Residual Connections for Hyperspectral Image Classification
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
ISyNet: Convolutional Neural Networks design for AI accelerator
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Xception: Deep Learning with Depthwise Separable Convolutions
MnasNet: Platform-Aware Neural Architecture Search for Mobile
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.