Tez Dosyaları 12
Generative model based approaches to learning with incomplete supervision
Streaming multiscale deep equilibrium models
Closed-form sample probing for training generative models in zero-shot learning
Scene-preserving person appearance transfer
Generalized zero-shot object recognition without class-attribute relations
Attention mechanisms for semantic few-shot learning
Improved image generation in normalizing flows through a multi-scale architecture and variational training
PriorBox: Long-tail calibration with priors
Object detection with minimal supervision
Semi-supervised generative guidance for zero-shot semantic segmentation
Prior knowledge guided weakly supervised object detection and semantic segmentation
Terrain classification by using hyperspectral and LiDAR data