Emergent Neural Network Mechanisms for Generalization to Objects in Novel Orientations

[Submitted on 28 Sep 2021 (v1), last revised 11 Aug 2026 (this version, v3)]

View PDF HTML (experimental)

Abstract:The capability of Deep Neural Networks (DNNs) to recognize objects in orientations outside the distribution of the training data is not well understood. We present evidence that DNNs are capable of generalizing to objects in novel orientations by disseminating orientation-invariance obtained from familiar objects seen from many viewpoints. This capability strengthens when training the DNN with an increasing number of familiar objects, but only in orientations that involve 2D rotations of familiar orientations. We show that this dissemination is achieved via neurons tuned to common features between familiar and unfamiliar objects. These results implicate brain-like neural mechanisms for generalization.

Submission history

From: Avraham Cooper [view email]
[v1] Tue, 28 Sep 2021 02:48:00 UTC (16,065 KB)
[v2] Thu, 13 Jul 2023 04:23:23 UTC (44,959 KB)
[v3] Tue, 11 Aug 2026 15:26:10 UTC (35,950 KB)