https://github.com/kynk94/TF2-Image-Generation
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
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.
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Very Deep Convolutional Networks for Large-Scale Image Recognition
Learning Transferable Visual Models From Natural Language Supervision
NoisyNN: Exploring the Impact of Information Entropy Change in Learning Systems
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
Learning rotation invariant convolutional filters for texture classification
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
ResMLP: Feedforward networks for image classification with data-efficient training
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compression
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.