1 code implementation • 26 Apr 2024 • Jiajun Liang, Baoquan Zhang, Yunming Ye, Xutao Li, Chuyao Luo, Xukai Fu
Different from the previous models, MCSDNet targets on multi-frames detection and leverages multi-scale spatiotemporal information for the detection of MCS regions in remote sensing imagery(RSI).
no code implementations • 16 Apr 2024 • Kuai Dai, Xutao Li, Junying Fang, Yunming Ye, Demin Yu, Di Xian, Danyu Qin
In terms of application, our system operates efficiently (forecasting 4 hours of convection in 8 minutes), and is highly transferable with the potential to collaborate with multiple satellites for global convection nowcasting.
no code implementations • 15 Mar 2024 • Baoquan Zhang, Huaibin Wang, Luo Chuyao, Xutao Li, Liang Guotao, Yunming Ye, Xiaochen Qi, Yao He
To this end, we propose a novel codebook transfer framework with part-of-speech, called VQCT, which aims to transfer a well-trained codebook from pretrained language models to VQIM for robust codebook learning.
1 code implementation • 2024 2024 • Kuai Dai, Xutao Li, Huiwei Lin, Yin Jiang, Xunlai Chen, Yunming Ye, Di Xian
In this article, we propose a lightweight prediction framework TinyPredNet for satellite image sequence prediction, in which a spatial encoder and decoder model the intra-frame appearance features and a temporal translator captures inter-frame motion patterns.
1 code implementation • 11 Dec 2023 • Demin Yu, Xutao Li, Yunming Ye, Baoquan Zhang, Chuyao Luo, Kuai Dai, Rui Wang, Xunlai Chen
A unified and flexible framework that can equip any type of spatio-temporal models is proposed based on residual diffusion, which effectively tackles the shortcomings of previous methods.
1 code implementation • 26 Sep 2023 • Huiwei Lin, Shanshan Feng, Baoquan Zhang, Xutao Li, Yew-Soon Ong, Yunming Ye
Inspired by this finding, we propose a novel replay-based method called proxy-based contrastive replay (PCR), which replaces anchor-to-sample pairs with anchor-to-proxy pairs in the contrastive-based loss to alleviate the phenomenon of forgetting.
no code implementations • 8 Sep 2023 • Huiwei Lin, Shanshan Feng, Baoquan Zhang, Hongliang Qiao, Xutao Li, Yunming Ye
By decomposing the dot-product logits into an angle factor and a norm factor, we empirically find that the bias problem mainly occurs in the angle factor, which can be used to learn novel knowledge as cosine logits.
no code implementations • 31 Jul 2023 • Baoquan Zhang, Chuyao Luo, Demin Yu, Huiwei Lin, Xutao Li, Yunming Ye, BoWen Zhang
Its key idea is learning a deep model in a bi-level optimization manner, where the outer-loop process learns a shared gradient descent algorithm (i. e., its hyperparameters), while the inner-loop process leverage it to optimize a task-specific model by using only few labeled data.
1 code implementation • IEEE Transactions on Geoscience and Remote Sensing 2023 • Kuai Dai, Xutao Li, Chi Ma, Shenyuan Lu, Yunming Ye, Di Xian, Lin Tian, Danyu Qin
As an extremely challenging spatial–temporal sequence prediction task, satellite image sequence prediction has various and significant applications in real-world scenarios.
1 code implementation • CVPR 2023 • Huiwei Lin, Baoquan Zhang, Shanshan Feng, Xutao Li, Yunming Ye
It aims to continuously learn new classes from data stream and the samples of data stream are seen only once, which suffers from the catastrophic forgetting issue, i. e., forgetting historical knowledge of old classes.
1 code implementation • IEEE Transactions on Geoscience and Remote Sensing 2022 • Kuai Dai, Xutao Li, Yunming Ye, Shanshan Feng, Danyu Qin, Rui Ye
To address the sequential error accumulation issue, MSTCGAN adopts a parallel prediction framework to produce the future image sequences by a one-hot time condition input.
no code implementations • 3 Mar 2022 • Baoquan Zhang, Hao Jiang, Xutao Li, Shanshan Feng, Yunming Ye, Rui Ye
Then, resorting to the prior, we split each few-shot task to a set of subtasks with different concept levels and then perform class prediction via a model of decision tree.
no code implementations • 9 Oct 2021 • Baoquan Zhang, Shanshan Feng, Xutao Li, Yunming Ye, Rui Ye
In this framework, a scene graph construction module is carefully designed to represent each test remote sensing image or each scene class as a scene graph, where the nodes reflect these co-occurrence objects meanwhile the edges capture the spatial correlations between these co-occurrence objects.
1 code implementation • 3 Oct 2021 • Chuyao Luo, ZhengZhang, Rui Ye, Xutao Li, Yunming Ye
Natural disasters caused by heavy rainfall often cost huge loss of life and property.
no code implementations • 29 Sep 2021 • Zehua Yu, Xianwei Zheng, Zhulun Yang, Xutao Li
To address the anomaly detection problem for datasets with a spatial-temporal structure, in this work, we propose a novel graph multi-domain splitting framework, called GMDS, by integrating the time, vertex, and frequency features to locate the anomalies.
1 code implementation • 11 Aug 2021 • Baoquan Zhang, Xutao Li, Yunming Ye, Shanshan Feng
In this paper, 1) we figure out the reason, i. e., in the pre-trained feature space, the base classes already form compact clusters while novel classes spread as groups with large variances, which implies that fine-tuning feature extractor is less meaningful; 2) instead of fine-tuning feature extractor, we focus on estimating more representative prototypes.
1 code implementation • 26 Mar 2021 • Baoquan Zhang, Xutao Li, Shanshan Feng, Yunming Ye, Rui Ye
Although the existing meta-optimizers can also be adapted to our framework, they all overlook a crucial gradient bias issue, \emph{i. e.}, the mean-based gradient estimation is also biased on sparse data.
1 code implementation • CVPR 2021 • Baoquan Zhang, Xutao Li, Yunming Ye, Zhichao Huang, Lisai Zhang
To avoid the prototype completion error caused by primitive knowledge noises or class differences, we further develop a Gaussian based prototype fusion strategy that combines the mean-based and completed prototypes by exploiting the unlabeled samples.
1 code implementation • 6 Aug 2020 • Yuan Yao, Xutao Li, Yu Zhang, Yunming Ye
In reality, however, it is not uncommon to obtain samples from multiple heterogeneous domains.
no code implementations • 5 Jul 2020 • Baoquan Zhang, Ka-Cheong Leung, Yunming Ye, Xutao Li
To this end, we propose a novel meta-learning framework, called MetaConcept, which learns to abstract concepts via the concept graph.
no code implementations • ACL 2020 • Bowen Zhang, Min Yang, Xutao Li, Yunming Ye, Xiaofei Xu, Kuai Dai
Specifically, a semantic-emotion heterogeneous graph is constructed from external semantic and emotion lexicons, which is then fed into a graph convolutional network to learn multi-hop semantic connections between words and emotion tags.
no code implementations • 25 Apr 2020 • Feng Liu, Weiwen Liu, Xutao Li, Yunming Ye
Then, based on the inter-sequence correlation encoder, we build GRU network and attention network in the intra-sequence correlation encoder to model the item sequential correlation within each individual sequence and temporal dynamics for predicting users' preferences over candidate items.
no code implementations • 28 Aug 2019 • Yuan Yao, Yu Zhang, Xutao Li, Yunming Ye
Heterogeneous domain adaptation (HDA) aims to facilitate the learning task in a target domain by borrowing knowledge from a heterogeneous source domain.
5 code implementations • 29 Oct 2018 • Feng Liu, Ruiming Tang, Xutao Li, Wei-Nan Zhang, Yunming Ye, Haokun Chen, Huifeng Guo, Yuzhou Zhang
The DRR framework treats recommendation as a sequential decision making procedure and adopts an "Actor-Critic" reinforcement learning scheme to model the interactions between the users and recommender systems, which can consider both the dynamic adaptation and long-term rewards.