Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs

no code implementations • 31 May 2023 • Yi Sun, Xin Xu, Jian Li, Xiaochang Hu, Yifei Shi, Ling-Li Zeng

By designing the learnable task-specific importance variables, DR-MGF evaluates the importance of filters for different tasks.

Interpolation-based Contrastive Learning for Few-Label Semi-Supervised Learning

no code implementations • 24 Feb 2022 • Xihong Yang, Xiaochang Hu, Sihang Zhou, Xinwang Liu, En Zhu

Specifically, the proposed algorithm outperforms the second best algorithm (Comatch) with 5. 3% by achieving 88. 73% classification accuracy when only two labels are available for each class on the CIFAR-10 dataset.

Contrastive Learning Data Augmentation