Shanshan Feng

Shanshan Feng

Auto-generated profile, based on publicly available information

Shanshan Feng

Wuhan University, Wuhan, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 November 2020 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
JLJing Li
Jing Li
BCBilly Chiu
Billy Chiu
SFShanshan Feng
Shanshan Feng
HWHao Wang
Hao Wang
Few-shot learning under the $N$ -way $K$ -shot setting (i.e., $K$ annotated samples for each of $N$ classes) has been widely studied in relation extraction (e.g., FewRel) and image classification (e.g., Mini-ImageNet). Named entity recognition (NER) is typically framed as a sequence labeling problem where the entity classes are inherently entangled together because the entity number and classes in a sentence are not known in advance, leaving the $N$ -way $K$ -shot NER problem so far unexplored. In this paper, we first formally define a more suitable $N$ -way $K$ -shot setting for NER. Then we propose FewNER , a novel meta-learning approach for few-shot NER. FewNER separates the entire network into a task-independent part and a task-specific part. During training in FewNER , the task-independent part is meta-learned across multiple tasks and the task-specific part is learned for each individual task in a low-dimensional space. At test time, FewNER keeps the task-independent part fixed and adapts to a new task via gradient descent by updating only the task-specific part, resulting in it being less prone to overfitting and more computationally efficient. Compared with pre-trained language models (e.g., BERT and ELMo) which obtain the transferability in an implicit manner (i.e., relying on large-scale corpora), FewNER explicitly optimizes the capability of “learning to adapt quickly” through meta-learning. The results demonstrate that FewNER achieves state-of-the-art performance against nine baseline methods by significant margins on three adaptation experiments (i.e., intra-domain cross-type, cross-domain intra-type and cross-domain cross-type).

1 March 2022 in Knowledge-Based Systems
Verified
Journal Article
Closed access
YSYuxi Sun
Yuxi Sun
YYYunming Ye
Yunming Ye
XLXutao Li
Xutao Li
SFShanshan Feng
Shanshan Feng
BZBowen Zhang
Bowen Zhang
KDKuai Dai
Kuai Dai

9 January 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
QLQingli Liu
Qingli Liu
Fan LiFan Li
Fan Li
KNKam K.H. Ng
Kam K.H. Ng
JHJiashu Han
Jiashu Han
SFShanshan Feng
Shanshan Feng

8 June 2022 in IEEE Transactions on Smart Grid
Verified
Journal Article
Closed access
SCShibo Chen
Shibo Chen
SFShanshan Feng
Shanshan Feng
ZGZhenwei Guo
Zhenwei Guo
ZYZaiyue Yang
Zaiyue Yang
We study the competitive pricing problem of electric vehicle charging station (EVCS). The EVCS determines its optimal pricing strategy considering the competition from the other EVCS and the impact of charging loads on the distribution locational marginal price (DLMP) of the power network. A trilevel optimization model is proposed, where the upper and middle level capture the profit maximization problems of this EVCS and its competitor respectively, while the lower level represents the optimal power flow problem of distribution network. Due to its computational challenge, this model is reformulated into a single level one, and their equivalence is rigorously proved. Furthermore, we develop an exact algorithm to achieve the global optimal solution, and also prove its finite convergence. Finally, numerical results validate our trilevel model and exact algorithm, and demonstrate their merits in increasing profits for the EVCS.

22 August 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YSYuxi Sun
Yuxi Sun
YYYunming Ye
Yunming Ye
Jian KangJian Kang
Jian Kang
RFRuben Fernandez-Beltran
Ruben Fernandez-Beltran
SFShanshan Feng
Shanshan Feng
Antonio PlazaAntonio Plaza
Antonio Plaza
Cross-view geo-localization is a critical task in various applications, such as smart city management and disaster monitoring. Current methods typically divide a satellite image into patches and use these patches to identify the geographic location of a query image. However, these methods can only provide the location of an image rather than the location of a specific object of interest. This makes it difficult to link these methods to GeoDatabases to obtain detailed information about a target object, such as its name and construction time. To overcome this limitation, we propose a novel problem of cross-view object geo-localization in a local region with high-resolution satellite images. This problem includes two main challenges: accurately identifying the location of an object and distinguishing the target object from others in satellite images. To address these challenges, we present a new Detection-based Geo-localization method called DetGeo, which consists of an object detection-based framework with a two-branch encoder and a query-aware cross-view fusion module. DetGeo uses cross-view images as input to the detector to provide object-level geo-localization. The fusion module employs cross-view spatial attention to focus on relevant areas of target objects during cross-view feature fusion. To evaluate our method, we constructed a new Cross-View Object Geo-Localization dataset called CVOGL, which comprises ground-view or drone-view images as query images and satellite-view images as geo-tagged reference images. Comprehensive experiments are conducted to demonstrate the effectiveness of our method on CVOGL. https://github.com/sunyuxi/DetGeo.

29 August 2022 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
BZBaoquan Zhang
Baoquan Zhang
SFShanshan Feng
Shanshan Feng
Xutao LiXutao Li
Xutao Li
YYYunming Ye
Yunming Ye
RYRui Ye
Rui Ye
HJHao Jiang
Hao Jiang
Few-shot remote sensing scene classification (FSRSSC) is an important task, which aims to recognize novel scene classes with few examples. Recently, several studies attempt to address the FSRSSC problem by following few-shot natural image classification methods. These existing methods have made promising progress and achieved superior performance. However, they all overlook two unique characteristics of remote sensing images: 1) object cooccurrence that multiple objects tend to appear together in a scene image and 2) object spatial correlation that these cooccurrence objects are distributed in the scene image following some spatial structure patterns. Such unique characteristics are very beneficial for FSRSSC, which can effectively alleviate the scarcity issue of labeled remote sensing images since they can provide more refined descriptions for each scene class. To fully exploit these characteristics, we propose a novel scene-graph-matching-based meta-learning framework for FSRSSC, called SGMNet. 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 cooccurrence objects; meanwhile, the edges capture the spatial correlations between these cooccurrence objects. Then, a scene graph matching module is further developed to evaluate the similarity score between each test remote sensing image and each scene class. Finally, based on the similarity scores, we perform the scene class prediction via a nearest neighbor classifier. We conduct extensive experiments on the UCMercedLandUse, WHU19, AID, and NWPU-RESISC45 datasets. The experimental results show that our method obtains superior performance over the previous state-of-the-art methods.