Dashan Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dashan Guo has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Liang Qiao
College of Computer Science & Technology Zhejiang University
1 shared publication - Linlan Zhao
Dept. of Electronic Engineering Shanghai Jiao Tong University Shanghai China
1 shared publication - Shiliang Pu
Hikvision Research Institute China
1 shared publication - Xiangzhong Fang
Shanghai Jiao Tong University
1 shared publication - Yi Niu
Hikvision Research Institute
1 shared publication - Yunlu Xu
Hikvision Research Institute China
1 shared publication
Latest Publications
- Open Access
A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning
Few-shot learning (FSL) aims to learn models that generalize to novel classes with limited training samples. Recent works advance FSL towards a scenario where unlabeled examples are also available and propose semi-supervised FSL methods. Another line of methods also cares about the performance of base classes in addition to the novel ones and thus establishes the incremental FSL scenario. In this paper, we generalize the above two under a more realistic yet complex setting, named by Semi-Supervised Incremental Few-Shot Learning (S2 I-FSL). To tackle the task, we propose a novel paradigm containing two parts: (1) a well-designed meta-training algorithm for mitigating ambiguity between base and novel classes caused by unreliable pseudo labels and (2) a model adaptation mechanism to learn discriminative features for novel classes while preserving base knowledge using few labeled and all the unlabeled data. Extensive experiments on standard FSL, semi-supervised FSL, incremental FSL, and the firstly built S2 I-FSL benchmarks demonstrate the effectiveness of our proposed method.
Open AccessA Strong Baseline for Semi-Supervised Incremental Few-Shot Learning
Few-shot learning (FSL) aims to learn models that generalize to novel classes with limited training samples. Recent works advance FSL towards a scenario where unlabeled examples are also available and propose semi-supervised FSL methods. Another line of methods also cares about the performance of base classes in addition to the novel ones and thus establishes the incremental FSL scenario. In this paper, we generalize the above two under a more realistic yet complex setting, named by Semi-Supervised Incremental Few-Shot Learning (S2 I-FSL). To tackle the task, we propose a novel paradigm containing two parts: (1) a well-designed meta-training algorithm for mitigating ambiguity between base and novel classes caused by unreliable pseudo labels and (2) a model adaptation mechanism to learn discriminative features for novel classes while preserving base knowledge using few labeled and all the unlabeled data. Extensive experiments on standard FSL, semi-supervised FSL, incremental FSL, and the firstly built S2 I-FSL benchmarks demonstrate the effectiveness of our proposed method.