Aiming at the problems such as small object size， arbitrary object direction and complex background of remote sensing images， on the basis of YOLOv5 （You Only Look Once version 5） algorithm， an algorithm involved with geometric adaptation and global perception was proposed. Firstly， deformable convolutions and adaptive spatial attention modules were stacked alternately in series through dense connections. As a result， a Dense Context-Aware Module （DenseCAM） which can model local geometric features was constructed on the basis of taking full advantage of different levels of semantic and location information. Secondly， by introducing Transformer in the end of the backbone network， the global perception ability of the model was enhanced at a low cost and the relationships between objects and scenario content were modeled. On UCAS-AOD and RSOD datasets， compared with YOLOv5s6 algorithm， the proposed algorithm has the mean Average Precision （mAP） increased by 1.8 percentage points and 1.5 percentage points， respectively. Experimental results show that the proposed algorithm can effectively improve the precision of object detection in remote sensing images.

In the field of deep learning， a large number of correctly labeled samples are essential for model training. However， in practical applications， labeling data requires high labeling cost. At the same time， the quality of labeled samples is affected by subjective factors or tool and technology of manual labeling， which inevitably introduces label noise in the annotation process. Therefore， existing training data available for practical applications is subject to a certain amount of label noise. How to effectively train training data with label noise has become a research hotspot. Aiming at label noise learning algorithms based on deep learning， firstly， the source， classification and impact of label noise learning strategies were elaborated； secondly， four label noise learning strategies based on data， loss function， model and training method were analyzed according to different elements of machine learning； then， a basic framework for learning label noise in various application scenarios was provided； finally， some optimization ideas were given， and challenges and future development directions of label noise learning algorithms were proposed.

Aiming at the problems of computational redundancy and difficulty in segmenting fine structures of the original U-Net in medical image segmentation tasks， an improved U-Net algorithm based on attention mechanism and multi-scale fusion was proposed. Firstly， by integrating channel attention mechanism into the skip connections， the channels containing more important information were focused by the network， thereby reducing computational resource cost and improving computational efficiency. Secondly， the feature fusion strategy was added to increase the contextual information for the feature maps passed to the decoder， which realized the complementary and multiple utilization among the features. Finally， the joint optimization was performed by using Dice loss and binary cross entropy loss， so as to handle with the problem of dramatic oscillations of loss function that may occur in fine structure segmentation. Experimental validation results on Kvasir_seg and DRIVE datasets show that compared with the original U-Net algorithm， the proposed improved algorithm has the Dice coefficient increased by 1.82 and 0.82 percentage points， the SEnsitivity （SE） improved by 1.94 and 3.53 percentage points， and the Accuracy （Acc） increased by 1.62 and 0.04 percentage points， respectively. It can be seen that the proposed improved algorithm can enhance performance of the original U-Net for fine structure segmentation.