Searcharxiv⌕ Search

arXiv subjects

Gene Cheung

Publications and source records attributed to Gene Cheung.

At least 19 recordsLinked to original sources

Deep Unrolling of Lanczos-based Laplacian Eigensolver for Crop Classification in Satellite Images

Per-pixel crop classification in satellite images is an important pre-processing step in remote crop monitoring. Leveraging progress in signed graph signal processing, we build an interpretable and lightweight neural network for binary crop classification (e.g., corn versus non-corn) in two stages: i) learn a signed graph from data, and ii) unroll a Lanczos-based eigensolver to compute the eigenvector $\u_1$ associated with the smallest eigenvalue of a hybrid graph Laplacian $\cL$ for spectral clustering. Specifically, we first construct a near-balanced signed graph $\cG^s$, where signed edge weights $w_{i,j}\in(-1,1)$ are computed from learned feature distances $d_{i,j}$ via a hyperbolic tangent mapping. Given $\cG^s$, we estimate $\u_1$ by unrolling the Lanczos algorithm and use $\mathrm{sign}(\u_1)$ for binary classification. Mathematically, we develop a theorem establishing conditions under which $\u_1$ can be well approximated after finite Lanczos iterations. Motivated by this theorem, we relax the classical Lanczos orthogonality constraints during unrolling and optimize end-to-end classification performance while promoting the derived conditions for accurate eigenvector approximation. Experiments on real-world Harmonized Landsat-Sentinel imagery show classification performance comparable to state-of-the-art deep learning models while reducing parameters by up to two orders of magnitude.

eess.SP↗

TSGL: Teacher-Student Graph Learning for 3DGS Compression

3D Gaussian Splatting (3DGS) is a popular representation for novel view synthesis. However, 3DGS contains millions of Gaussian primitives, each with rich attributes, resulting in large file sizes. We propose a novel 3DGS compression method based on Teacher-Student Graph Learning (TSGL) that operates directly on a trained model, without 3DGS retraining or access to training images. Specifically, for each block of Gaussian primitives, using decoded positions and DC spherical harmonic (SH) coefficients as predictors, we learn a signal-dependent geometry graph G encoding the pairwise similarities between neighbouring Gaussians via a teacher-student model. Given G, we perform Graph Fourier Transform (GFT) on the remaining attributes, so that signal energies are predominantly projected into the low-frequency coefficients for compact representation. On three standard benchmarks, the method reaches 27x to 33x compression with less than 0.6 dB of PSNR loss, improving on recent post-training compression methods in both size and rendering quality.

eess.IV↗

Unrolling Lanczos for Ideal Low-pass Graph Filter Approximation

Low-pass (LP) filtering is a fundamental operation in graph signal processing (GSP). Among finite-order nodal-domain methods, Lanczos-based filtering provides more accurate approximations of ideal LP filters than Chebyshev polynomial methods. We show that the approximation of Lanczos filtering can be further improved through algorithm unrolling and data-driven parameter learning. The key insight is that, because ideal LP filtering is a projection operation into the low-frequency eigen-subspace $\cS_K$, instead of approximating individual eigen-pairs of a graph Laplacian $Ł$ as done in classical Lanczos, an unrolled Lanczos network can directly approximate $\cS_K$. Specifically, we first establish a theorem identifying properties of the Lanczos tridiagonal matrix $\T_m$ that promote accurate approximation of the low-frequency eigen-subspace $\cS_K$. Guided by this theory, we relax the orthogonality constraint on Lanczos vectors, resulting in Ritz vectors that better span $\cS_K$. To ensure numerical stability, we constrain $\T_m$ to be similar to a symmetric matrix, thereby guaranteeing real-valued eigenvalues. Experimental results on random graphs and learned graphs in two natural language processing (NLP) tasks show that our unrolled Lanczos network achieves superior ideal LP filter approximation compared to the classical Lanczos method.

eess.SP↗

Graph Learning with Spectral Connectivity Priors for Scarce Data

Learning a sparse graph from scarce data is practically important but challenging. Motivated by the desirable combination of local sparsity and strong global connectivity exhibited by expander-like graphs, we propose spectral connectivity-regularized graph learning (SCoGL), a framework that incorporates a family of Laplacian spectral priors to explicitly promote global connectivity. Specifically, SCoGL augments a combinatorial-Laplacian-constrained graphical lasso (GLASSO) objective over a target adjacency matrix $\mathbf{W}$ with a general connectivity prior computed from Laplacian eigenvalues. We derive gradients for several representative connectivity priors and develop a projected gradient descent (PGD) algorithm with Armijo backtracking to efficiently optimize $\mathbf{W}$. Experiments show that the proposed SCoGL variants improve graph recovery and enhance downstream tasks such as graph signal denoising when signal observations are scarce.

cs.LG↗

Transforming harmonic coefficients for 3D splat compression

We address the problem of color attribute compression for 3D splats. We show that all images generated by 3D splats are linear in the coefficients for each color channel, each spherical harmonic, and each splat, and we identify a basis for the space of all such images. We identify an inner product for the coefficient space that induces the squared error loss on images. We show that orthonormalizing the coefficients with respect to this innner product before coding can yield over 2 dB gain.

eess.SP↗

Efficient Learning of Balanced Signed Graphs via Sparse Linear Programming

Signed graphs are equipped with both positive and negative edge weights, encoding pairwise correlations as well as anti-correlations in data. A balanced signed graph is a signed graph with no cycles containing an odd number of negative edges. Laplacian of a balanced signed graph has eigenvectors that map via a simple linear transform to ones in a corresponding positive graph Laplacian, thus enabling reuse of spectral filtering tools designed for positive graphs. We propose an efficient computation method to learn a balanced signed graph Laplacian directly from data. Specifically, extending a previous linear programming (LP) based sparse inverse covariance estimation method called CLIME, we formulate a new LP problem for each Laplacian column $i$, where the linear constraints restrict weight signs of edges stemming from node $i$, so that nodes of same / different polarities are connected by positive / negative edges. We derive a feasible CLIME parameter $ρ_i$ for each sign-constrained column problem. We solve the LP problem efficiently by tailoring a sparse LP method based on ADMM. We theoretically prove that the row / column updates produce a non-increasing objective sequence, and show that the iterations are terminated in a finite number of steps. Extensive experimental results on synthetic and real-world datasets show that our balanced graph learning method outperforms competing methods and enables reuse of spectral filters, wavelets, and graph neural nets (GNN) constructed for positive graphs.

cs.LG↗

Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding

Given encoded 3D point cloud geometry available at the decoder, we study the problem of lossy attribute compression in a multi-resolution B-spline projection framework. A target continuous 3D attribute function is first projected onto a sequence of nested subspaces $\mathcal{F}^{(p)}_{l_0} \subseteq \cdots \subseteq \mathcal{F}^{(p)}_{L}$, where $\mathcal{F}^{(p)}_{l}$ is a family of functions spanned by a B-spline basis function of order $p$ at a chosen scale and its integer shifts. The projected low-pass coefficients $F_l^*$ are computed by variable-complexity unrolling of a rate-distortion (RD) optimization algorithm into a feed-forward network, where the rate term is the sparsity-promoting $\ell_1$-norm. Thus, the projection operation is end-to-end differentiable. For a chosen coarse-to-fine predictor, the coefficients are then adjusted to account for the prediction from a lower-resolution to a higher-resolution, which is also optimized in a data-driven manner.

eess.IV↗

Graph Unfolding and Sampling for Transitory Video Keyframe Selection via Gershgorin Disc Alignment

User-generated videos (UGVs) uploaded from mobile phones to social media sites like YouTube and TikTok are short and non-repetitive. We summarize a transitory UGV into several keyframes in linear-time via fast graph sampling based on Gershgorin disc alignment (GDA). Specifically, we first model a sequence of $N$ frames in a UGV as an $M$-hop path graph $\cG^o$ for $M \ll N$, where the similarity between two frames within $M$ time instants is encoded as a positive edge based on feature similarity. Towards efficient sampling, we then ``unfold'' $\cG^o$ to a $1$-hop path graph $\cG$, specified by a generalized graph Laplacian matrix $\cL$, via one of two graph unfolding procedures with provable performance bounds. We show that maximizing the smallest eigenvalue $λ_{\min}(\B)$ of a coefficient matrix $\B = \diag{\h} + μ\cL$, where $\h$ is the binary keyframe selection vector, is equivalent to minimizing a worst-case signal reconstruction error. We maximize instead the Gershgorin circle theorem (GCT) lower bound $λ^-_{\min}(\B)$ by choosing $\h$ via a new fast graph sampling algorithm that iteratively aligns left-ends of Gershgorin discs for all graph nodes (frames). Experiments on multiple short video datasets show that our algorithm achieves comparable or better keyframe selection performance compared to state-of-the-art methods, at a substantially reduced complexity.

cs.CV↗

Low-rank Updates in Slowly Time-varying Graphs for Spatial-Temporal Signal Interpolation

A crucial assumption in graph signal processing (GSP) is the existence of an underlying graph that captures the pairwise similarities between nodes, allowing filters to be designed based on this graph for tasks such as denoising. For spatial-temporal data in which node-to-node similarities evolve over time, a static spatial graph is insufficient. In this paper, to represent slowly time-varying pairwise relationships, we model the graph changes in two consecutive adjacency matrices $P = W^{(2)} - W^{(1)}$ across time as a low-rank matrix. % Specifically, given an initial adjacency matrix $W^{(1)}$ at time $t=1$, we jointly interpolate a signal $x_2$ and estimate $W^{(2)}$ at $t=2$ using both a graph signal smoothness prior for $x_2$ and a low-rank prior on $¶$. We alternate optimization steps. With $W^{(2)}$ fixed, $x_2$ is interpolated by solving a linear system. Alternatively, holding $x_2$ fixed, $W^{(2)}$ is updated via proximal gradient descent (PGD). The proximal mapping of the rank term $Gamma(W^{(2)} - W^{(1)})$ is approximated in linear time using a fast orthogonal matching pursuit (OMP) algorithm that selects a sparse combination of atoms from a dictionary $cR$ formed by the outer products of $W^{(1)}$'s eigenvectors. We unroll iterations of our algorithm into layers to build a lightweight neural network for limited data-driven parameter tuning. Experiments show that our joint optimization achieves better signal interpolation compared to existing time-varying graph models.

eess.SP↗

Lightweight and Interpretable Transformer via Mixed Graph Algorithm Unrolling for Traffic Forecast

Unlike conventional "black-box" transformers with classical self-attention mechanism, we build a lightweight and interpretable transformer-like neural net by unrolling a mixed-graph-based optimization algorithm to forecast traffic with spatial and temporal dimensions. We construct two graphs: an undirected graph $\mathcal{G}^u$ capturing spatial correlations across geography, and a directed graph $\mathcal{G}^d$ capturing sequential relationships over time. We predict future samples of signal $\mathbf{x}$, assuming it is "smooth" with respect to both $\mathcal{G}^u$ and $\mathcal{G}^d$, where we design new $\ell_2$ and $\ell_1$-norm variational terms to quantify and promote signal smoothness (low-frequency reconstruction) on a directed graph. We design an iterative algorithm based on alternating direction method of multipliers (ADMM), and unroll it into a feed-forward network for data-driven parameter learning. We periodically insert graph learning modules for $\mathcal{G}^u$ and $\mathcal{G}^d$ that play the role of self-attention. Experiments show that our unrolled networks achieve competitive traffic forecast performance as state-of-the-art prediction schemes, while reducing parameter counts drastically.

cs.LG↗

Sparse Graph Learning from Sparse Data via Fiedler Number Maximization

We aim to learn a sparse and connected graph from sparse data, where the number of observations K can be substantially smaller than the signal dimension N for signals x in R^N, and the underlying distribution is unknown. In this severely ill-posed setting, we incorporate Fiedler number (the second eigenvalue of the graph Laplacian matrix that quantifies connectedness) as a robust regularization term in the sparse graph learning objective. We first develop a greedy algorithm that iteratively selects one edge globally for weakening/removal to reduce the objective, leveraging eigenvalue perturbation theorems that bound the adverse effect of an edge change to the Fiedler number. Next, we design a parallel variant, based on the Cheeger's inequality, that recursively partitions an input graph into two sub-graphs using an approximate Cheeger cut to distributedly find an optimal edge. Simulation experiments show that Fiedler number maximization robustifies sparse graph estimates, outperforming previous sparse graph learning algorithms.

eess.SP↗

Unrolling Graph-based Douglas-Rachford Algorithm for Image Interpolation with Informed Initialization

Conventional deep neural nets (DNNs) initialize network parameters at random and then optimize each one via stochastic gradient descent (SGD), resulting in substantial risk of poor-performing local minima. Focusing on image interpolation and leveraging a recent theorem that maps a (pseudo-)linear interpolator Θ to a directed graph filter that is a solution to a corresponding MAP problem with a graph shift variation (GSV) prior, we first initialize a directed graph adjacency matrix A given a known interpolator Θ, establishing a baseline performance. Then, towards further gain, we learn perturbation matrices P and P(2) from data to augment A, whose restoration effects are implemented progressively via Douglas-Rachford (DR) iterations, which we unroll into a lightweight and interpretable neural net. Experiments on different image interpolation scenarios demonstrate state-of-the-art performance, while drastically reducing network parameters and inference complexity.

cs.CV↗

Lightweight Transformer for EEG Classification via Balanced Signed Graph Algorithm Unrolling

Samples of brain signals collected by EEG sensors have inherent anti-correlations that are well modeled by negative edges in a finite graph. To differentiate epilepsy patients from healthy subjects using collected EEG signals, we build lightweight and interpretable transformer-like neural nets by unrolling a spectral denoising algorithm for signals on a balanced signed graph -- graph with no cycles of odd number of negative edges. A balanced signed graph has well-defined frequencies that map to a corresponding positive graph via similarity transform of the graph Laplacian matrices. We implement an ideal low-pass filter efficiently on the mapped positive graph via Lanczos approximation, where the optimal cutoff frequency is learned from data. Given that two balanced signed graph denoisers learn posterior probabilities of two different signal classes during training, we evaluate their reconstruction errors for binary classification of EEG signals. Experiments show that our method achieves classification performance comparable to representative deep learning schemes, while employing dramatically fewer parameters.

cs.LG↗

Unrolling Nonconvex Graph Total Variation for Image Denoising

Conventional model-based image denoising optimizations employ convex regularization terms, such as total variation (TV) that convexifies the $\ell_0$-norm to promote sparse signal representation. Instead, we propose a new non-convex total variation term in a graph setting (NC-GTV), such that when combined with an $\ell_2$-norm fidelity term for denoising, leads to a convex objective with no extraneous local minima. We define NC-GTV using a new graph variant of the Huber function, interpretable as a Moreau envelope. The crux is the selection of a parameter $a$ characterizing the graph Huber function that ensures overall objective convexity; we efficiently compute $a$ via an adaptation of Gershgorin Circle Theorem (GCT). To minimize the convex objective, we design a linear-time algorithm based on Alternating Direction Method of Multipliers (ADMM) and unroll it into a lightweight feed-forward network for data-driven parameter learning. Experiments show that our method outperforms unrolled GTV and other representative image denoising schemes, while employing far fewer network parameters.

eess.IV↗

Unrolling Plug-and-Play Gradient Graph Laplacian Regularizer for Image Restoration

Generic deep learning (DL) networks for image restoration like denoising and interpolation lack mathematical interpretability, require voluminous training data to tune a large parameter set, and are fragile in the face of covariate shift. To address these shortcomings, we build interpretable networks by unrolling variants of a graph-based optimization algorithm of different complexities. Specifically, for a general linear image formation model, we first formulate a convex quadratic programming (QP) problem with a new $\ell_2$-norm graph smoothness prior called gradient graph Laplacian regularizer (GGLR) that promotes piecewise planar (PWP) signal reconstruction. To solve the posed unconstrained QP problem, instead of computing a linear system solution straightforwardly, we introduce a variable number of auxiliary variables and correspondingly design a family of ADMM algorithms. We then unroll them into variable-complexity feed-forward networks, amenable to parameter tuning via back-propagation. More complex unrolled networks require more labeled data to train more parameters, but have better overall performance. The unrolled networks have periodic insertions of a graph learning module, akin to a self-attention mechanism in a transformer architecture, to learn pairwise similarity structure inherent in data. Experimental results show that our unrolled networks perform competitively to generic DL networks in image restoration quality while using only a fraction of parameters, and demonstrate improved robustness to covariate shift.

eess.IV↗

Mixed Graph Signal Analysis of Joint Image Denoising / Interpolation

A noise-corrupted image often requires interpolation. Given a linear denoiser and a linear interpolator, when should the operations be independently executed in separate steps, and when should they be combined and jointly optimized? We study joint denoising / interpolation of images from a mixed graph filtering perspective: we model denoising using an undirected graph, and interpolation using a directed graph. We first prove that, under mild conditions, a linear denoiser is a solution graph filter to a maximum a posteriori (MAP) problem regularized using an undirected graph smoothness prior, while a linear interpolator is a solution to a MAP problem regularized using a directed graph smoothness prior. Next, we study two variants of the joint interpolation / denoising problem: a graph-based denoiser followed by an interpolator has an optimal separable solution, while an interpolator followed by a denoiser has an optimal non-separable solution. Experiments show that our joint denoising / interpolation method outperformed separate approaches noticeably.

eess.IV↗

Interpretable Lightweight Transformer via Unrolling of Learned Graph Smoothness Priors

We build interpretable and lightweight transformer-like neural networks by unrolling iterative optimization algorithms that minimize graph smoothness priors -- the quadratic graph Laplacian regularizer (GLR) and the $\ell_1$-norm graph total variation (GTV) -- subject to an interpolation constraint. The crucial insight is that a normalized signal-dependent graph learning module amounts to a variant of the basic self-attention mechanism in conventional transformers. Unlike "black-box" transformers that require learning of large key, query and value matrices to compute scaled dot products as affinities and subsequent output embeddings, resulting in huge parameter sets, our unrolled networks employ shallow CNNs to learn low-dimensional features per node to establish pairwise Mahalanobis distances and construct sparse similarity graphs. At each layer, given a learned graph, the target interpolated signal is simply a low-pass filtered output derived from the minimization of an assumed graph smoothness prior, leading to a dramatic reduction in parameter count. Experiments for two image interpolation applications verify the restoration performance, parameter efficiency and robustness to covariate shift of our graph-based unrolled networks compared to conventional transformers.

cs.LG↗

Learned Nonlinear Predictor for Critically Sampled 3D Point Cloud Attribute Compression

We study 3D point cloud attribute compression via a volumetric approach: assuming point cloud geometry is known at both encoder and decoder, parameters $θ$ of a continuous attribute function $f: \mathbb{R}^3 \mapsto \mathbb{R}$ are quantized to $\hatθ$ and encoded, so that discrete samples $f_{\hatθ}(\mathbf{x}_i)$ can be recovered at known 3D points $\mathbf{x}_i \in \mathbb{R}^3$ at the decoder. Specifically, we consider a nested sequences of function subspaces $\mathcal{F}^{(p)}_{l_0} \subseteq \cdots \subseteq \mathcal{F}^{(p)}_L$, where $\mathcal{F}_l^{(p)}$ is a family of functions spanned by B-spline basis functions of order $p$, $f_l^*$ is the projection of $f$ on $\mathcal{F}_l^{(p)}$ represented as low-pass coefficients $F_l^*$, and $g_l^*$ is the residual function in an orthogonal subspace $\mathcal{G}_l^{(p)}$ (where $\mathcal{G}_l^{(p)} \oplus \mathcal{F}_l^{(p)} = \mathcal{F}_{l+1}^{(p)}$) represented as high-pass coefficients $G_l^*$. In this paper, to improve coding performance over \cite{do2023volumetric}, we study predicting $f_{l+1}^*$ at level $l+1$ given $f_l^*$ at level $l$ and encoding of $G_l^*$ for the $p=1$ case (RAHT($1$)). For the prediction, we formalize RAHT(1) linear prediction in MPEG-PCC in a theoretical framework, and propose a new nonlinear predictor using a polynomial of bilateral filter. We derive equations to efficiently compute the critically sampled high-pass coefficients $G_l^*$ amenable to encoding. We optimize parameters in our resulting feed-forward network on a large training set of point clouds by minimizing a rate-distortion Lagrangian. Experimental results show that our improved framework outperforms the MPEG G-PCC predictor by $11\%$--$12\%$ in bit rate.

eess.IV↗