- PseudoEdgeNet: Nuclei Segmentation only with Point Annotations
- C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
- SRM : A Style-based Recalibration Module for Convolutional Neural Networks
- Weight Standardization
- Video Object Segmentation using Space-Time Memory Networks
- Towards Universal Object Detection by Domain Attention
- FickleNet:Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference
- Image Inpainting using Deep Learning
- Revisiting Self-Supervised Visual Representation Learning
- StyleGAN: A Style-Based Generator Architecture for GANs
