https://github.com/facebookresearch/AttentiveNAS
AlphaNet: Improved Training of Supernets with Alpha-Divergence
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.
AlphaNet: Improved Training of Supernets with Alpha-Divergence
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
CrypTen: Secure Multi-Party Computation Meets Machine Learning
Video Classification with Channel-Separated Convolutional Networks
Learning Transferable Visual Models From Natural Language Supervision
Bootstrap your own latent: A new approach to self-supervised Learning
LayoutLM: Pre-training of Text and Layout for Document Image Understanding
Unsupervised representation learning with recognition-parametrised probabilistic models
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
X3D: Expanding Architectures for Efficient Video Recognition
A Simple Way to Initialize Recurrent Networks of Rectified Linear Units
Billion-scale semi-supervised learning for image classification
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Very Deep Convolutional Networks for Large-Scale Image Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.