Understanding Deep Convolutional Networks through Gestalt Theory
The superior performance of deep convolutional networks over high-dimensional problems have made them very popular for several applications. Despite their wide adoption, their underlying mechanisms still remain unclear with their improvement procedures still relying mainly on a trial and error process. We introduce a novel sensitivity analysis based on the Gestalt theory for giving insights into the classifier function and intermediate layers. Since Gestalt psychology stipulates that perception can be a product of complex interactions among several elements, we perform an ablation study based on this concept to discover which principles and image context significantly contribute in the network classification. Our results reveal that ConvNets follow most of the visual cortical perceptual mechanisms defined by the Gestalt principles at several levels. The proposed framework stimulates specific feature maps in classification problems and reveal important network attributes that can produce more explainable network models.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationSimilar Papers 제목 키워드 기반
Modelling the Human Intuition to Complete the Missing Information in Images for Convolutional Neural Networks
In this study, we attempt to model intuition and incorporate this formalism to improve the performance of the Convolutional Neural Networks. Despite decades of research, ambiguities persist on principles of intuition. Ex…
Gestalt-Guided Image Understanding for Few-Shot Learning
Due to the scarcity of available data, deep learning does not perform well on few-shot learning tasks. However, human can quickly learn the feature of a new category from very few samples. Nevertheless, previous work has…
Few-Shot LearningHow intelligent are convolutional neural networks?
Motivated by the Gestalt pattern theory, and the Winograd Challenge for language understanding, we design synthetic experiments to investigate a deep learning algorithm's ability to infer simple (at least for human) visu…
Mixed Evidence for Gestalt Grouping in Deep Neural Networks
Gestalt psychologists have identified a range of conditions in which humans organize elements of a scene into a group or whole, and perceptual grouping principles play an essential role in scene perception and object ide…
Object RecognitionRepresenting Classical Compositions through Implication-Realization Temporal-Gestalt Graphs
Understanding the structural and cognitive underpinnings of musical compositions remains a key challenge in music theory and computational musicology. While traditional methods focus on harmony and rhythm, cognitive mode…