Unsupervised 3D Object Learning through Neuron Activity aware Plasticity
This work improves unsupervised learning for 3D object recognition, which is incremental as it builds on Hebbian learning methods.
The paper tackles the problem of unsupervised 3D object classification by addressing the loss of local features in conventional Hebbian learning, resulting in higher accuracy compared to other Hebbian variants and supervised models when training data is limited.
We present an unsupervised deep learning model for 3D object classification. Conventional Hebbian learning, a well-known unsupervised model, suffers from loss of local features leading to reduced performance for tasks with complex geometric objects. We present a deep network with a novel Neuron Activity Aware (NeAW) Hebbian learning rule that dynamically switches the neurons to be governed by Hebbian learning or anti-Hebbian learning, depending on its activity. We analytically show that NeAW Hebbian learning relieves the bias in neuron activity, allowing more neurons to attend to the representation of the 3D objects. Empirical results show that the NeAW Hebbian learning outperforms other variants of Hebbian learning and shows higher accuracy over fully supervised models when training data is limited.