RIDE applies Retinex-based homogeneous decomposition to improve foreground-background discriminability in concealed object segmentation tasks across multiple domains.
Fast fourier convolution.Advances in Neural Information Processing Systems, 33:4479–4488, 2020
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RIDE: Retinex-Informed Decoupling for Exposing Concealed Objects
RIDE applies Retinex-based homogeneous decomposition to improve foreground-background discriminability in concealed object segmentation tasks across multiple domains.