https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/edgenext
EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications
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.
EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications
EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction
FasterViT: Fast Vision Transformers with Hierarchical Attention
FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation
Scaling Local Self-Attention for Parameter Efficient Visual Backbones
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
High-Performance Large-Scale Image Recognition Without Normalization
UniFormer: Unifying Convolution and Self-attention for Visual Recognition
Very Deep Convolutional Networks for Large-Scale Image Recognition
Very Deep Convolutional Networks for Large-Scale Image Recognition
Efficiently Modeling Long Sequences with Structured State Spaces
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
Flatten-T Swish: a thresholded ReLU-Swish-like activation function for deep learning
Flatten-T Swish: a thresholded ReLU-Swish-like activation function for deep learning
LiSHT: Non-Parametric Linearly Scaled Hyperbolic Tangent Activation Function for Neural Networks
Gradient Centralization: A New Optimization Technique for Deep Neural Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.