2 papers
cs.CV2023
Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs
Yi Sun, Xin Xu, Jian Li +3
Multi-output deep neural networks(MONs) contain multiple task branches, and these tasks usually share partial network filters that lead to the entanglement of different task infere…
cs.CV2022
Interpolation-based Contrastive Learning for Few-Label Semi-Supervised Learning
Xihong Yang, Xiaochang Hu, Sihang Zhou +2
Semi-supervised learning (SSL) has long been proved to be an effective technique to construct powerful models with limited labels. In the existing literature, consistency regulariz…