https://github.com/anindex/noprop
NoProp: Training Neural Networks without Back-propagation or Forward-propagation
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.
NoProp: Training Neural Networks without Back-propagation or Forward-propagation
Robust Training in High Dimensions via Block Coordinate Geometric Median Descent
Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser
Learning Representations For Images With Hierarchical Labels
Cached Transformers: Improving Transformers with Differentiable Memory Cache
CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters
Regularized Evolution for Image Classifier Architecture Search
A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers
A Simple Framework for Contrastive Learning of Visual Representations
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
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.