Search Results for author:
Found 4 papers, 0 papers with code
Deep Semi-supervised Learning with Double-Contrast of Features and Semantics
Therefore, a more realistic strategy is to leverage semi-supervised learning (SSL) with a small amount of labeled data and a large amount of unlabeled data.
Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts
Self-supervised learning (SSL), as a newly emerging unsupervised representation learning paradigm, generally follows a two-stage learning pipeline: 1) learning invariant and discriminative representations with auto-annotation pretext(s), then 2) transferring the representations to assist downstream task(s).
Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Task
Multi-task learning is to improve the performance of the model by transferring and exploiting common knowledge among tasks.
Learning Twofold Heterogeneous Multi-Task by Sharing Similar Convolution Kernel Pairs
However, to the best of our knowledge, there is limited study on twofold heterogeneous MTL (THMTL) scenario where the input and the output spaces are both inconsistent or heterogeneous.
