https://github.com/VITA-Group/AutoSpeech
AutoSpeech: Neural Architecture Search for Speaker Recognition
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.
AutoSpeech: Neural Architecture Search for Speaker Recognition
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Very Deep Convolutional Networks for Large-Scale Image Recognition
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Learning Deep Representations of Fine-grained Visual Descriptions
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Aggregated Residual Transformations for Deep Neural Networks
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Towards Deep Learning Models Resistant to Adversarial Attacks
Learning Deep Representations of Fine-grained Visual Descriptions
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
Very Deep Convolutional Networks for Large-Scale Image Recognition
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.