An Object Detection Method Combining Circular Extractor and Self Distillation
In the era of deep learning,object detection methods are constantly developing and have reached a high level in a good visual environment.However,the detection performance of conventional target detection methods in adverse weather conditions has significantly decreased or even failed,and driving safety in adverse weather environments has always been a widespread concern in society.In order to solve the above problems,we mainly design a model of the target detector,which is an improved YOLO model that introduces cyclic-dis-entanglement and self-distillation methods.In the cyclic disentanglement module,domain invariant features are extracted from the input image in a cyclic manner.Through cyclic operations,the ability to unwrap image domain features and domain invariant features can be improved without relying on domain related annotations;in the self-distillation module,the extracted domain invariant features are used as the teacher's object to further improve generalization ability.Moreover,the detector performs well in many untrained target domains even when trained in only one source domain,improving its robustness in the unknown domain.The experiment verifies the effectiveness of the model in detecting urban scene targets under various weather conditions.The experimental data show that the proposed method outperforms the baseline by about 8 percentage points and achieves performance improvement compared to the baseline method.
deep learningobject detectionadverse weathercyclic-disentangledself-distillationdomain-invariant representations
万方数据
维普
