https://github.com/ZhouDaShan123/vit
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
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.
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
Towards Deep Learning Models Resistant to Adversarial Attacks
LSQ+: Improving low-bit quantization through learnable offsets and better initialization
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Learning Transferable Visual Models From Natural Language Supervision
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
Understanding deep learning requires rethinking generalization
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language
Towards Deep Learning Models Resistant to Adversarial Attacks
Towards Deep Learning Models Resistant to Adversarial Attacks
FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning
SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Improving the Resolution of CNN Feature Maps Efficiently with Multisampling
MnasNet: Platform-Aware Neural Architecture Search for Mobile
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.