https://github.com/MindSpore-scientific/code-10/tree/main/token_learner
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
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.
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
Dataset Distillation with Infinitely Wide Convolutional Networks
Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation
Knowledge distillation: A good teacher is patient and consistent
Seesaw-Net: Convolution Neural Network With Uneven Group Convolution
An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Knowledge distillation: A good teacher is patient and consistent
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.