Search Results for author:
Found 16 papers, 1 papers with code
GARA: A novel approach to Improve Genetic Algorithms' Accuracy and Efficiency by Utilizing Relationships among Genes
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.
LCCo: Lending CLIP to Co-Segmentation
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.
AstroNet: When Astrocyte Meets Artificial Neural Network
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.
RL-CoSeg : A Novel Image Co-Segmentation Algorithm with Deep Reinforcement Learning
For the image co-segmentation problem, we propose a collaborative RL algorithm based on the A3C model.
Generating meta-learning tasks to evolve parametric loss for classification learning
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.
Mining the Weights Knowledge for Optimizing Neural Network Structures
We introduce a switcher neural network (SNN) that uses as inputs the weights of a task-specific neural network (called TNN for short).
A Novel Structured Natural Gradient Descent for Deep Learning
More specifically, we reconstruct the structure of the deep neural network, and optimize the new network using traditional gradient descent (GD).
A Dense Siamese U-Net trained with Edge Enhanced 3D IOU Loss for Image Co-segmentation
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.
Explore the Knowledge contained in Network Weights to Obtain Sparse Neural Networks
We design a switcher neural network (SNN) to optimize the structure of the task neural network (TNN).
Improving Image co-segmentation via Deep Metric Learning
Finally, the IS-Triplet loss is combined with 3 traditional image segmentation losses to perform image segmentation.
Ranked #1 on
Semantic Segmentation
on SBCoseg
Evolving parametrized Loss for Image Classification Learning on Small Datasets
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.
Fusing Medical Image Features and Clinical Features with Deep Learning for Computer-Aided Diagnosis
Current Computer-Aided Diagnosis (CAD) methods mainly depend on medical images.
Contraction Mapping of Feature Norms for Classifier Learning on the Data with Different Quality
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.
A New Computer-Aided Diagnosis System with Modified Genetic Feature Selection for BI-RADS Classification of Breast Masses in Mammograms
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.
Automatic Image Co-Segmentation: A Survey
Then we describe the traditional methods in three categories of object elements based, object regions/contours based, common object model based.
A New Three-stage Curriculum Learning Approach to Deep Network Based Liver Tumor Segmentation
The learning in the first stage is performed on the whole input to obtain an initial deep network for tumor segmenta-tion.
