For stationary image datasets and standard augmentations, the optimal contrastive representation is partial whitening of DFT power, implemented by a CNN with sinusoidal first-layer filters and a waterfilling weight allocation.
Title resolution pending
5 Pith papers cite this work, alongside 3,269 external citations. Polarity classification is still indexing.
5
Pith papers citing it
3,269
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
Under a shared-head/disjoint-tail assumption, multi-domain loss decomposes into a capacity-competition term c_i x_i^*(h)^{-b_i} plus a per-domain noise term A_i(Dh_i)^{-a_i}, and the fitted law extrapolates optimal mixtures to unseen scales.
STAL transfers spectral tail uplift cues via a frequency teacher to train a spatial detector for AI-generated images, discarding frequency modules at inference for strong cross-generator generalization.
Introduces DCD, a wavelet-based stage-wise distillation technique that preserves structural details in efficient 3D multi-modal MRI segmentation models.
Joint sparse coding and temporal dynamics in mPFC and computational networks reduce cross-context interference and enhance separability, enabling better retention in lifelong learning without extra heuristics.
citing papers explorer
-
A Theory of Contrastive Learning with Natural Images
For stationary image datasets and standard augmentations, the optimal contrastive representation is partial whitening of DFT power, implemented by a CNN with sinusoidal first-layer filters and a waterfilling weight allocation.
-
Explaining Data Mixing Scaling Laws
Under a shared-head/disjoint-tail assumption, multi-domain loss decomposes into a capacity-competition term c_i x_i^*(h)^{-b_i} plus a per-domain noise term A_i(Dh_i)^{-a_i}, and the fitted law extrapolates optimal mixtures to unseen scales.
-
Spectral Tail Auxiliary Learning for AI-Generated Image Detection
STAL transfers spectral tail uplift cues via a frequency teacher to train a spatial detector for AI-generated images, discarding frequency modules at inference for strong cross-generator generalization.
-
Detail Consistent Stage-Wise Distillation for Efficient 3D MRI Segmentation
Introduces DCD, a wavelet-based stage-wise distillation technique that preserves structural details in efficient 3D multi-modal MRI segmentation models.
-
Joint sparse coding and temporal dynamics support context reconfiguration
Joint sparse coding and temporal dynamics in mPFC and computational networks reduce cross-context interference and enhance separability, enabling better retention in lifelong learning without extra heuristics.