Human-Object Interaction (HOI), as an important problem in computer vision, requires locating the human-object pair and identifying the interactive relationships between them. The HOI instance has a greater span in spatial, scale, and task than the individual object instance, making its detection more susceptible to noisy backgrounds. To alleviate the disturbance of noisy backgrounds on HOI detection, it is necessary to consider the input image information to generate fine-grained anchors which are then leveraged to guide the detection of HOI instances. However, it has the following challenges. $i)$ how to extract pivotal features from the images with complex background information is still an open question. $ii)$ how to semantically align the extracted features and query embeddings is also a difficult issue. In this paper, a novel end-to-end transformer-based framework (FGAHOI) is proposed to alleviate the above problems. FGAHOI comprises three dedicated components namely, multi-scale sampling (MSS) , hierarchical spatial-aware merging (HSAM) and task-aware merging mechanism (TAM) . MSS extracts features of humans, objects and interaction areas from noisy backgrounds for HOI instances of various scales. HSAM and TAM semantically align and merge the extracted features and query embeddings in the hierarchical spatial and task perspectives in turn. In the meanwhile, a novel training strategy Stage-wise Training Strategy is designed to reduce the training pressure caused by overly complex tasks done by FGAHOI. In addition, we propose two ways to measure the difficulty of HOI detection and a novel dataset, $i.e.$ , HOI-SDC for the two challenges ( Uneven Distributed Area in Human-Object Pairs and Long Distance Visual Modeling of Human-Object Pairs ) of HOI instances detection. Experiments are conducted on three benchmarks: HICO-DET, HOI-SDC and V-COCO. Our model outperforms the state-of-the-art HOI detection methods, and the extensive ablations reveal the merits of our proposed contribution. The code is available at https://github.com/xiaomabufei/FGAHOI .
In lung cancer computer-aided detection/diagnosis (CAD) systems, classification of regions of interest (ROI) is often used to detect/diagnose lung nodule accurately. However, problems of unbalanced datasets often have detrimental effects on the performance of classification. In this paper, both minority and majority classes are resampled to increase the generalization ability. We propose a novel SVM classifier combined with random undersampling (RU) and SMOTE for lung nodule recognition. The combinations of the two resampling methods not only achieve a balanced training samples but also remove noise and duplicate information in the training sample and retain useful information to improve the effective data utilization, hence improving performance of SVM algorithm for pulmonary nodules classification under the unbalanced data. Eight features including 2D and 3D features are extracted for training and classification. Experimental results show that for different sizes of training datasets our RU-SMOTE-SVM classifier gets the highest classification accuracy among the four kinds of classifiers, and the average classification accuracy is more than 92.94%.
Alzheimer’s disease (AD) is a common progressive neurodegenerative disease in the elderly. Mild cognitive impairment (MCI) is the symptomatic predementia stage of AD. Accurately distinguishing AD and MCI patients from normal people is the first step of the disease diagnosis. Several studies have demonstrated the potential of deep learning in the automatic diagnosis of AD and MCI using T1-weighted magnetic resonance imaging (MRI) images. In this article, we proposed an automatic classification method of AD versus normal control (NC) and MCI versus NC based on MRI images. This method used the 3-D convolutional neural network and took the whole 3-D MRI image as the input, which can obtain image information to the greatest extent. In addition, the multichannel contrastive learning strategy based on multiple data transformation methods (e.g., add noise) can combine the supervised classification loss with the unsupervised contrastive loss, which can further improve the classification accuracy and generalization ability of the network. To verify the effectiveness of our method, a large number of experiments were implemented on the ADNI dataset. The results show that our method can achieve excellent performance in accurate diagnosis of AD and MCI; the multichannel contrastive learning strategy can greatly improve the classification accuracy (AD versus NC: 4.19%; MCI versus NC: 4.57%) and generalization ability of the network.