REVIEW 6 cited by
Density Modeling of Images using a Generalized Normalization Transformation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We introduce a parametric nonlinear transformation that is well-suited for Gaussianizing data from natural images. The data are linearly transformed, and each component is then normalized by a pooled activity measure, computed by exponentiating a weighted sum of rectified and exponentiated components and a constant. We optimize the parameters of the full transformation (linear transform, exponents, weights, constant) over a database of natural images, directly minimizing the negentropy of the responses. The optimized transformation substantially Gaussianizes the data, achieving a significantly smaller mutual information between transformed components than alternative methods including ICA and radial Gaussianization. The transformation is differentiable and can be efficiently inverted, and thus induces a density model on images. We show that samples of this model are visually similar to samples of natural image patches. We demonstrate the use of the model as a prior probability density that can be used to remove additive noise. Finally, we show that the transformation can be cascaded, with each layer optimized using the same Gaussianization objective, thus offering an unsupervised method of optimizing a deep network architecture.
Forward citations
Cited by 6 Pith papers
-
Hadamard-Domain Model Quantization for Learned Image Coding
Uniform INT8 quantization of learned image codecs becomes more accurate when tensors are first re-expressed in a layer-adaptive Hadamard basis.
-
LANCE: Locally Adaptive Neural Context Estimation for Overfitted Image Compression
LANCE extends OIC frameworks with a spatial hyperprior and predictive coding scheme, reporting BD-rate gains of 1.4-3% over Cool-Chic 4.0 on Kodak and CLIC.
-
Rethink Before You Execute: Adaptive Execution for World Action Models
TempoWAM adapts the replanning frequency of world action models based on an online estimate of task progress, reducing inference calls on easy tasks and improving success on hard tasks.
-
Versatile Volumetric Medical Image Coding for Human-Machine Vision
A learned volumetric medical image codec transfers inter-slice latent features across slices so a single compressed stream supports both image reconstruction and direct organ segmentation.
-
Cross-Layer Encrypted Semantic Communication Framework for Panoramic Video Transmission
A cross-layer framework integrates Deep JSCC semantic coding with encryption, CRC, LDPC, and retransmission, adapting error protection to semantic importance for panoramic video.
-
Binocular Rivalry Oriented Predictive Auto-Encoding Network for Blind Stereoscopic Image Quality Measurement
PAD-Net, a Siamese encoder-decoder with a ResNet-18 quality regressor, predicts no-reference stereoscopic image quality by modeling binocular rivalry through likelihood and prior maps, and reports state-of-the-art res...
Discussion (0). Continue with ORCID to comment.