no code implementations • 28 Apr 2024 • Zhaoning Shi, Meng Xiang, Zhaoyang Hai, Xiabi Liu, Yan Pei
We design a directed multipartite graph encapsulating the solution space, called RGGR, where each node corresponds to a gene in the solution and the edge represents the relationship between adjacent nodes.
no code implementations • 22 Aug 2023 • Xin Duan, Yan Yang, Liyuan Pan, Xiabi Liu
With a backbone segmentation network that independently processes each image from the set, we introduce semantics from CLIP into the backbone features, refining them in a coarse-to-fine manner with three key modules: i) an image set feature correspondence module, encoding global consistent semantic information of the image set; ii) a CLIP interaction module, using CLIP-mined common semantics of the image set to refine the backbone feature; iii) a CLIP regularization module, drawing CLIP towards this co-segmentation task, identifying the best CLIP semantic and using it to regularize the backbone feature.
no code implementations • CVPR 2023 • Mengqiao Han, Liyuan Pan, Xiabi Liu
Then, with the astrocytes, we propose an AstroNet that can adaptively optimize neuron connections and therefore achieves structure learning to achieve higher accuracy and efficiency.
no code implementations • 12 Apr 2022 • Xin Duan, Xiabi Liu, Xiaopeng Gong, Mengqiao Han
For the image co-segmentation problem, we propose a collaborative RL algorithm based on the A3C model.
no code implementations • 20 Nov 2021 • Zhaoyang Hai, Xiabi Liu, Yuchen Ren, Nouman Q. Soomro
In this paper, we propose a meta-learning approach based on randomly generated meta-learning tasks to obtain a parametric loss for classification learning based on big data.
no code implementations • 11 Oct 2021 • Mengqiao Han, Xiabi Liu, Zhaoyang Hai, Xin Duan
We introduce a switcher neural network (SNN) that uses as inputs the weights of a task-specific neural network (called TNN for short).
no code implementations • 21 Sep 2021 • Weihua Liu, Xiabi Liu
More specifically, we reconstruct the structure of the deep neural network, and optimize the new network using traditional gradient descent (GD).
no code implementations • 17 Aug 2021 • Xi Liu, Xiabi Liu, Huiyu Li, Xiaopeng Gong
In this paper, we propose a new approach to image co-segmentation through introducing the dense connections into the decoder path of Siamese U-net and presenting a new edge enhanced 3D IOU loss measured over distance maps.
no code implementations • 26 Mar 2021 • Mengqiao Han, Xiabi Liu, Zhaoyang Hai, Zhengwen Li
We design a switcher neural network (SNN) to optimize the structure of the task neural network (TNN).
no code implementations • 19 Mar 2021 • Zhengwen Li, Xiabi Liu
Finally, the IS-Triplet loss is combined with 3 traditional image segmentation losses to perform image segmentation.
Ranked #1 on Semantic Segmentation on SBCoseg
no code implementations • 15 Mar 2021 • Zhaoyang Hai, Xiabi Liu
The MLN is evolved with the Evolutionary Strategy algorithm (ES) to an optimized loss function, such that a classifier, which optimized to minimize this loss, will achieve a good generalization effect.
no code implementations • 10 Mar 2021 • Songxiao Yang, Xiabi Liu, Zhongshu Zheng, Wei Wang, Xiaohong Ma
Current Computer-Aided Diagnosis (CAD) methods mainly depend on medical images.
no code implementations • 27 Jul 2020 • Weihua Liu, Xiabi Liu, Murong Wang, Ling Ma
The experiments on various classification applications, including handwritten digit recognition, lung nodule classification, face verification and face recognition, demonstrate that the proposed approach is promising to effectively deal with the problem of learning on the data with different quality and leads to the significant and stable improvements in the classification accuracy.
no code implementations • 11 May 2020 • Said Boumaraf, Xiabi Liu, Chokri Ferkous, Xiaohong Ma
Finally, a back-propagation neural network (BPN) is employed for classification, and its accuracy is used as the fitness in GA. A set of 500 mammogram images from the digital database of screening mammography (DDSM) is used for evaluation.
no code implementations • 18 Nov 2019 • Xiabi Liu, Xin Duan
Then we describe the traditional methods in three categories of object elements based, object regions/contours based, common object model based.
1 code implementation • 17 Oct 2019 • Huiyu Li, Xiabi Liu, Said Boumaraf, Weihua Liu, Xiaopeng Gong, Xiaohong Ma
The learning in the first stage is performed on the whole input to obtain an initial deep network for tumor segmenta-tion.