https://github.com/lessw2020/auto-adaptive-ai
Accelerating Training of Deep Neural Networks with a Standardization Loss
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.
Accelerating Training of Deep Neural Networks with a Standardization Loss
U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection
Improved Regularization of Convolutional Neural Networks with Cutout
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment
An Algorithm for Out-Of-Distribution Attack to Neural Network Encoder
A Closer Look at Self-Supervised Lightweight Vision Transformers
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints
Very Deep Convolutional Networks for Large-Scale Image Recognition
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Momentum Contrast for Unsupervised Visual Representation Learning
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.