https://github.com/DanielKovach/AG-Net
Attend and Guide (AG-Net): A Keypoints-driven Attention-based Deep Network for Image 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.
Attend and Guide (AG-Net): A Keypoints-driven Attention-based Deep Network for Image Recognition
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
LSQ+: Improving low-bit quantization through learnable offsets and better initialization
LSQ+: Improving low-bit quantization through learnable offsets and better initialization
Very Deep Convolutional Networks for Large-Scale Image Recognition
C-Net: A Reliable Convolutional Neural Network for Biomedical Image Classification
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.