https://github.com/Ximilar-com/tf-image
Improved Regularization of Convolutional Neural Networks with Cutout
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.
Improved Regularization of Convolutional Neural Networks with Cutout
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Very Deep Convolutional Networks for Large-Scale Image Recognition
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
Dense Contrastive Learning for Self-Supervised Visual Pre-Training
MetaKernel: Learning Variational Random Features with Limited Labels
GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations
Learning Semantically Enhanced Feature for Fine-Grained Image Classification
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
Learning to Detect and Retrieve Objects from Unlabeled Videos
Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Very Deep Convolutional Networks for Large-Scale Image Recognition
Involution: Inverting the Inherence of Convolution for Visual Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.