no code implementations • 11 Dec 2024 • Zhiyan Wang, Deyin Liu, Lin Yuanbo Wu, Song Wang, Xin Guo, Lin Qi
Additionally, this paper extends these modules to a lightweight segmentation network, achieving an mIoU of 82. 5% on the Cityscapes validation set with only 137. 9 GFLOPs.
no code implementations • 13 Nov 2024 • ChengYuan Zhang, Yilin Zhang, Lei Zhu, Deyin Liu, Lin Wu, Bo Li, Shichao Zhang, Mohammed Bennamoun, Farid Boussaid
This paper introduces a novel framework for unified incremental few-shot object detection (iFSOD) and instance segmentation (iFSIS) using the Transformer architecture.
no code implementations • 5 Sep 2024 • Deyin Liu, Lin Yuanbo Wu, Xianghua Xie
First, although existing methods attempt to focus on local area editing by a pre-defined mask, the preservation of the outside-area background is non-ideal due to the spatially entire generation of each frame.
no code implementations • 3 Jul 2024 • Hanxi Li, Jingqi Wu, Lin Yuanbo Wu, Hao Chen, Deyin Liu, Chunhua Shen
By fine-tuning the ADClick-Seg model using the weak labels inferred by ADClick, we establish the state-of-the-art performances in supervised AD tasks (AP $= 86. 4\%$ on MVTec AD and AP $= 78. 4\%$, PRO $= 98. 6\%$ on KSDD2).
Ranked #3 on
Supervised Anomaly Detection
on MVTec AD
(using extra training data)
1 code implementation • 29 Feb 2024 • Hanxi Li, Zhengxun Zhang, Hao Chen, Lin Wu, Bo Li, Deyin Liu, Mingwen Wang
Effectively addressing the challenge of industrial Anomaly Detection (AD) necessitates an ample supply of defective samples, a constraint often hindered by their scarcity in industrial contexts.
no code implementations • 6 Jun 2023 • Hanxi Li, Jingqi Wu, Deyin Liu, Lin Wu, Hao Chen, Mingwen Wang, Chunhua Shen
To leverage this feature, we adapt the Swin Transformer for enhanced anomaly detection and localization.
Ranked #1 on
Unsupervised Anomaly Detection
on KolektorSDD2
(using extra training data)
no code implementations • 4 Feb 2023 • Feng Xue, Yu Li, Deyin Liu, Yincen Xie, Lin Wu, Richang Hong
However, generalizing these methods to unseen speakers incurs catastrophic performance degradation due to the limited number of speakers in training bank and the evident visual variations caused by the shape/color of lips for different speakers.
1 code implementation • 26 Nov 2022 • Zhong Ji, Junhua Hu, Deyin Liu, Lin Yuanbo Wu, Ye Zhao
To implement this task, one needs to extract multi-scale features from both image and text domains, and then perform the cross-modal alignment.
1 code implementation • 18 Aug 2022 • Deyin Liu, Lin Yuanbo Wu, Bo Li, ZongYuan Ge
Our architecture is orthogonal to StackGAN++ , and focuses on person image generation, with all of them together to enrich the spectrum of GANs for the image generation task.
no code implementations • 9 Jul 2022 • Deyin Liu, Lin Wu, Haifeng Zhao, Farid Boussaid, Mohammed Bennamoun, Xianghua Xie
Moreover, adversarially training a defense model in general cannot produce interpretable predictions towards the inputs with perturbations, whilst a highly interpretable robust model is required by different domain experts to understand the behaviour of a DNN.
no code implementations • 9 Jul 2022 • Lin Wu, Deyin Liu, Wenying Zhang, Dapeng Chen, ZongYuan Ge, Farid Boussaid, Mohammed Bennamoun, Jialie Shen
In this paper, we present a pseudo-pair based self-similarity learning approach for unsupervised person re-ID without human annotations.
no code implementations • 22 Mar 2020 • Deyin Liu, Xu Chen, Zhi Zhou, Qing Ling
We develop a novel \textit{hybrid parallelism} method, which is the key to HierTrain, to adaptively assign the DNN model layers and the data samples across the three levels of edge device, edge server and cloud center.
no code implementations • 14 Nov 2019 • Deyin Liu, Lin Wu, Xue Li
In this paper, we present an effective deep prediction framework based on robust recurrent neural networks (RNNs) to predict the likely therapeutic classes of medications a patient is taking, given a sequence of diagnostic billing codes in their record.