no code implementations • 25 Mar 2022 • Li Ke, Meng Pan, Weigao Wen, Dong Li
Learning with few labeled data is a key challenge for visual recognition, as deep neural networks tend to overfit using a few samples only.
no code implementations • 24 Jan 2019 • Xia Yuan, Liao xiaoli, Li Shilei, Shi Qinwen, Wu Jinfa, Li Ke
The results show that the proposed multitask SVM classification model based on 1-2gram TF-IDF features exhibits the best performance among the tested models.