From Images to Perception: Emergence of Perceptual Properties by Reconstructing Images
A number of scientists suggested that human visual perception may emerge from image statistics, shaping efficient neural representations in early vision. In this work, a bio-inspired architecture that can accommodate several known facts in the retina-V1 cortex, the PerceptNet, has been end-to-end optimized for different tasks related to image reconstruction: autoencoding, denoising, deblurring, and sparsity regularization. Our results show that the encoder stage (V1-like layer) consistently exhibits the highest correlation with human perceptual judgments on image distortion despite not using perceptual information in the initialization or training. This alignment exhibits an optimum for moderate noise, blur and sparsity. These findings suggest that the visual system may be tuned to remove those particular levels of distortion with that level of sparsity and that biologically inspired models can learn perceptual metrics without human supervision.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ReconstructionSimilar Papers 제목 키워드 기반
Natural and Realistic Single Image Super-Resolution with Explicit Natural Manifold Discrimination
Recently, many convolutional neural networks for single image super-resolution (SISR) have been proposed, which focus on reconstructing the high-resolution images in terms of objective distortion measures. However, the n…
Image Super-ResolutionSuper-ResolutionImportant Clues that Facilitate Visual Emergence: Three Psychological Experiments
Visual emergence is the phenomenon in which the visual system obtains a holistic perception after grouping and reorganizing local signals. The picture Dalmatian dog is known for its use in explaining visual emergence. Th…
Seeing through the Brain: Image Reconstruction of Visual Perception from Human Brain Signals
Seeing is believing, however, the underlying mechanism of how human visual perceptions are intertwined with our cognitions is still a mystery. Thanks to the recent advances in both neuroscience and artificial intelligenc…
EEGImage ReconstructionTime SeriesAnomaly localization by modeling perceptual features
Although unsupervised generative modeling of an image dataset using a Variational AutoEncoder (VAE) has been used to detect anomalous images, or anomalous regions in images, recent works have shown that this method often…
Anomaly DetectionAnomaly LocalizationLatent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping
Humans are able to segment images effortlessly without supervision using perceptual grouping. Here, we propose a counter-intuitive computational approach to solving unsupervised perceptual grouping and segmentation: that…
SegmentationSemantic Segmentation