42 citations · 91 across the 9 of their papers we have counts for
9 papers
MILD: Modeling the Instance Learning Dynamics for Learning with Noisy Labels
Chuanyang Hu, Shipeng Yan, Zhitong Gao +1
Despite deep learning has achieved great success, it often relies on a large amount of training data with accurate labels, which are expensive and time-consuming to collect. A prom…
Generative Negative Text Replay for Continual Vision-Language Pretraining
Shipeng Yan, Lanqing Hong, Hang Xu +4
Vision-language pre-training (VLP) has attracted increasing attention recently. With a large amount of image-text pairs, VLP models trained with contrastive loss have achieved impr…
General Incremental Learning with Domain-aware Categorical Representations
Jiangwei Xie, Shipeng Yan, Xuming He
Continual learning is an important problem for achieving human-level intelligence in real-world applications as an agent must continuously accumulate knowledge in response to strea…
Budget-aware Few-shot Learning via Graph Convolutional Network
Shipeng Yan, Songyang Zhang, Xuming He
This paper tackles the problem of few-shot learning, which aims to learn new visual concepts from a few examples. A common problem setting in few-shot classification assumes random…
An EM Framework for Online Incremental Learning of Semantic Segmentation
Shipeng Yan, Jiale Zhou, Jiangwei Xie +2
Incremental learning of semantic segmentation has emerged as a promising strategy for visual scene interpretation in the open- world setting. However, it remains challenging to acq…
How Well Does Self-Supervised Pre-Training Perform with Streaming Data?
Dapeng Hu, Shipeng Yan, Qizhengqiu Lu +6
Prior works on self-supervised pre-training focus on the joint training scenario, where massive unlabeled data are assumed to be given as input all at once, and only then is a lear…
DER: Dynamically Expandable Representation for Class Incremental Learning
Shipeng Yan, Jiangwei Xie, Xuming He
We address the problem of class incremental learning, which is a core step towards achieving adaptive vision intelligence. In particular, we consider the task setting of incrementa…
Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
Songyang Zhang, Zeming Li, Shipeng Yan +2
Despite the recent success of deep neural networks, it remains challenging to effectively model the long-tail class distribution in visual recognition tasks. To address this proble…
FOTS: Fast Oriented Text Spotting with a Unified Network
Xuebo Liu, Ding Liang, Shi Yan +3
Incidental scene text spotting is considered one of the most difficult and valuable challenges in the document analysis community. Most existing methods treat text detection and re…