https://github.com/2023-MindSpore-4/Code-5/tree/main/Inception-v2
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
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.
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
MnasNet: Platform-Aware Neural Architecture Search for Mobile
EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction
EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Very Deep Convolutional Networks for Large-Scale Image Recognition
Aggregated Residual Transformations for Deep Neural Networks
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Aggregated Residual Transformations for Deep Neural Networks
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
A Simple Framework for Contrastive Learning of Visual Representations
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.