Surround Modulation: A Bio-inspired Connectivity Structure for Convolutional Neural Networks
Numerous neurophysiological studies have revealed that a large number of the primary visual cortex neurons operate in a regime called surround modulation. Surround modulation has a substantial effect on various perceptual tasks, and it also plays a crucial role in the efficient neural coding of the visual cortex. Inspired by the notion of surround modulation, we designed new excitatory-inhibitory connections between a unit and its surrounding units in the convolutional neural network (CNN) to achieve a more biologically plausible network. Our experiments show that this simple mechanism can considerably improve both the performance and training speed of traditional CNNs in visual tasks. We further explore additional outcomes of the proposed structure. We first evaluate the model under several visual challenges, such as the presence of clutter or change in lighting conditions and show its superior generalization capability in handling these challenging situations. We then study possible changes in the statistics of neural activities such as sparsity and decorrelation and provide further insight into the underlying efficiencies of surround modulation. Experimental results show that importing surround modulation into the convolutional layers ensues various effects analogous to those derived by surround modulation in the visual cortex.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Contour Integration using Graph-Cut and Non-Classical Receptive Field
Many edge and contour detection algorithms give a soft-value as an output and the final binary map is commonly obtained by applying an optimal threshold. In this paper, we propose a novel method to detect image contours …
Contour DetectionCDRL: A Reinforcement Learning Framework Inspired by Cerebellar Circuits and Dendritic Computational Strategies
Reinforcement learning (RL) has achieved notable performance in high-dimensional sequential decision-making tasks, yet remains limited by low sample efficiency, sensitivity to noise, and weak generalization under partial…
Representation LearningReinforcement LearningV1Net: A computational model of cortical horizontal connections
The primate visual system builds robust, multi-purpose representations of the external world in order to support several diverse downstream cortical processes. Such representations are required to be invariant to the sen…
Boundary DetectionmodelObject RecognitionConnectivity-Inspired Network for Context-Aware Recognition
The aim of this paper is threefold. We inform the AI practitioner about the human visual system with an extensive literature review; we propose a novel biologically motivated neural network for image classification; and,…
Biologically-plausible TrainingCausal DiscoveryFunctional Connectivityimage-classification+1Biologically Inspired Mechanisms for Facilitating Grokking in Multilayer Perceptrons
Grokking is a delayed transition from memorization to generalization that is often accompanied by substantial reorganization of internal representations. This paper studies whether biologically inspired mechanisms, many …