1 code implementation • 28 Apr 2024 • Yong Dai, Xiaopeng Hong, Yabin Wang, Zhiheng Ma, Dongmei Jiang, YaoWei Wang
In contrast to conventional methods that employ hard prompt selection, PGM assigns different coefficients to prompts from a fixed-sized pool of prompts and generates tailored prompts.
no code implementations • 27 Mar 2024 • Shenxing Wei, Xing Wei, Zhiheng Ma, Songlin Dong, Shaochen Zhang, Yihong Gong
Recent research in this domain has emphasized the necessity of a large volume of training data, overlooking the practical scenario where, post-deployment of the model, unlabeled data containing both normal and abnormal samples can be utilized to enhance the model's performance.
no code implementations • 23 Feb 2024 • Hui Lin, Zhiheng Ma, Rongrong Ji, YaoWei Wang, Zhou Su, Xiaopeng Hong, Deyu Meng
This paper focuses on semi-supervised crowd counting, where only a small portion of the training data are labeled.
1 code implementation • 8 Jan 2024 • Hui Lin, Zhiheng Ma, Xiaopeng Hong, Qinnan Shangguan, Deyu Meng
The graph is building upon the dissimilarities between patches, modulating the attention in an anti-similarity fashion.
1 code implementation • 4 Jan 2024 • Yabin Wang, Zhiwu Huang, Zhiheng Ma, Xiaopeng Hong
The two distinguished features enable DFLIP-3K to develop a benchmark that promotes progress in linguistic profiling of deepfakes, which includes three sub-tasks namely deepfake detection, model identification, and prompt prediction.
1 code implementation • 21 Apr 2023 • Zhiheng Ma, Xiaopeng Hong, Qinnan Shangguan
Meta AI recently released the Segment Anything model (SAM), which has garnered attention due to its impressive performance in class-agnostic segmenting.
1 code implementation • 24 Mar 2023 • Zhiheng Ma, Xiaopeng Hong, Beinan Liu, Yabin Wang, Pinyue Guo, Huiyun Li
It mimics the feature distribution of the target old class on the old model using only samples of new classes.
1 code implementation • 12 Mar 2023 • Yabin Wang, Xiaopeng Hong, Zhiheng Ma, Tiedong Ma, Baoxing Qin, Zhou Su
Task allocation plays a vital role in multi-robot autonomous cleaning systems, where multiple robots work together to clean a large area.
1 code implementation • 29 Nov 2022 • Yabin Wang, Zhiheng Ma, Zhiwu Huang, YaoWei Wang, Zhou Su, Xiaopeng Hong
To avoid obvious stage learning bottlenecks, we propose a brand-new stage-isolation based incremental learning framework, which leverages a series of stage-isolated classifiers to perform the learning task of each stage without the interference of others.
1 code implementation • 7 Sep 2022 • Hui Lin, Zhiheng Ma, Xiaopeng Hong, YaoWei Wang, Zhou Su
In this paper, we propose a new agency-guided semi-supervised counting approach.
1 code implementation • CVPR 2022 • Hui Lin, Zhiheng Ma, Rongrong Ji, YaoWei Wang, Xiaopeng Hong
Secondly, we design the Local Attention Regularization to supervise the training of LRA by minimizing the deviation among the attention for different feature locations.
1 code implementation • 21 Jul 2021 • Ning li, Kaitao Jiang, Zhiheng Ma, Xing Wei, Xiaopeng Hong, Yihong Gong
Anomaly detection plays a key role in industrial manufacturing for product quality control.
Ranked #46 on Anomaly Detection on MVTec AD
no code implementations • 4 Jul 2021 • Hui Lin, Xiaopeng Hong, Zhiheng Ma, Xing Wei, Yunfeng Qiu, YaoWei Wang, Yihong Gong
Second, we derive a semi-balanced form of Sinkhorn divergence, based on which a Sinkhorn counting loss is designed for measure matching.
no code implementations • ICCV 2021 • Zhiheng Ma, Xiaopeng Hong, Xing Wei, Yunfeng Qiu, Yihong Gong
This paper proposes to handle the practical problem of learning a universal model for crowd counting across scenes and datasets.
3 code implementations • ICCV 2019 • Zhiheng Ma, Xing Wei, Xiaopeng Hong, Yihong Gong
In crowd counting datasets, each person is annotated by a point, which is usually the center of the head.