Deep Psychovisual Image Representations

Researchers have developed Deep Visual Coding, a frequency-domain representation inspired by 1990s image codes that creates psychovisual-style abstractions for deep learning. The approach enables the first psychovisual-based deep learning framework, producing highly interpretable object parts compared to the amorphous regions from regular Convolutional Neural Networks. The findings demonstrate that psychovisual coding offers a path toward more efficient and transparent vision models that are less depth dependent than standard CNNs.

arXiv:2605.29260v1 Announce Type: new Abstract: Psychovisual models suggest human vision decouples low-level feature extraction from higher cognition by first forming intermediate abstractions. In contrast, deep learning-based vision models routinely extract and aggregate features using homogeneous stacks of spatial layers, rendering their decision-making processes opaque. In this paper, we propose Deep Visual Coding, a learned frequency-domain representation inspired by 1990s image codes that quantised perceptually salient frequencies, which together with complex-valued image representations produces psychovisual-style abstractions. This approach enables the first psychovisual-based deep learning framework, utilizing data-driven spectral filters that learn to encode task-relevant semantic structures within distinct frequency sub-bands. Salience analyses reveal that our psychovisual models extract highly interpretable object parts compared to the amorphous regions produced by regular Convolutional Neural Networks CNNs . Furthermore, we find that our models are less depth dependent than CNNs for model scaling, since our complex-valued representations and learned abstractions subsume the role of the deep spatial layers. Together, these findings demonstrate that psychovisual coding provides a promising path toward more efficient and transparent vision models.