Meina Kan

Dr. Meina Kan


Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications

5 August 2020 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
NLNan Lai
Nan Lai
MKMeina Kan
Meina Kan
CHChunrui Han
Chunrui Han
XSXingguang Song
Xingguang Song
SSShiguang Shan
Shiguang Shan
Few-shot learning aims to learn a well-performing model from a few labeled examples. Recently, quite a few works propose to learn a predictor to directly generate model parameter weights with episodic training strategy of meta-learning and achieve fairly promising performance. However, the predictor in these works is task-agnostic, which means that the predictor cannot adjust to novel tasks in the testing phase. In this article, we propose a novel meta-learning method to learn how to learn task-adaptive classifier-predictor to generate classifier weights for few-shot classification. Specifically, a meta classifier-predictor module, (MPM) is introduced to learn how to adaptively update a task-agnostic classifier-predictor to a task-specialized one on a novel task with a newly proposed center-uniqueness loss function. Compared with previous works, our task-adaptive classifier-predictor can better capture characteristics of each category in a novel task and thus generate a more accurate and effective classifier. Our method is evaluated on two commonly used benchmarks for few-shot classification, i.e., miniImageNet and tieredImageNet. Ablation study verifies the necessity of learning task-adaptive classifier-predictor and the effectiveness of our newly proposed center-uniqueness loss. Moreover, our method achieves the state-of-the-art performance on both benchmarks, thus demonstrating its superiority.

31 December 2013 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
MKMeina Kan
Meina Kan
JWJunting Wu
Junting Wu
SSShiguang Shan
Shiguang Shan
XCXilin Chen
Xilin Chen

5 October 2018
Verified
Book Chapter
Closed access
PDF file
CHChunrui Han
Chunrui Han
SSShiguang Shan
Shiguang Shan
MKMeina Kan
Meina Kan
SWShuzhe Wu
Shuzhe Wu
XCXilin Chen
Xilin Chen

1 March 2011
Verified
Conference Paper
Closed access
MKMeina Kan
Meina Kan
SSShiguang Shan
Shiguang Shan
YSYu Su
Yu Su
XCXilin Chen
Xilin Chen
WGWen Gao
Wen Gao
Discriminant analysis, especially Fisherface and its numerous variants, have achieved great success in face recognition. However, these methods fail to work for face recognition from Single Sample per Person (SSPP), since they need more than one sample per person to estimate the within-class scatter matrix. To break this inability of traditional discriminant analysis, our paper proposes Adaptive Discriminant Analysis (ADA). In our method, the within-class scatter matrix of each enrolled subject is estimated from his/her single sample, by inferring from a generic training set with multiple samples per person. The inference is inspired by a simple intuition that similar person follows similar within-class variations. Specifically, both kNN regression and Lasso regression are explored for this purpose. We evaluate our method on FERET database and a large real-world face database. The results are very impressive compared with dominant traditional solutions to SSPP problem.

21 August 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
YWYude Wang
Yude Wang
JZJie Zhang
Jie Zhang
MKMeina Kan
Meina Kan
SSShiguang Shan
Shiguang Shan
XCXilin Chen
Xilin Chen
Scribble-supervised semantic segmentation is an appealing weakly supervised technique with low labeling cost. Existing approaches mainly consider diffusing the labeled region of scribble by low-level feature similarity to narrow the supervision gap between scribble labels and mask labels. In this study, we observe an annotation bias between scribble and object mask, i.e., label workers tend to scribble on the spacious region instead of corners. This label preference makes the model learn well on those frequently labeled regions but poor on rarely labeled pixels. Therefore, we propose BLPSeg to balance the label preference for complete segmentation. Specifically, the BLPSeg first predicts an annotation probability map to evaluate the rarity of labels on each image, then utilizes a novel BLP loss to balance the model training by up-weighting those rare annotations. Additionally, to further alleviate the impact of label preference, we design a local aggregation module (LAM) to propagate supervision from labeled to unlabeled regions in gradient backpropagation. We conduct extensive experiments to illustrate the effectiveness of our BLPSeg. Our single-stage method even outperforms other advanced multi-stage methods and achieves state-of-the-art performance.