Generalized Lasso based Approximation of Sparse Coding for Visual Recognition
Sparse coding, a method of explaining sensory data with as few dictionary bases as possible, has attracted much attention in computer vision. For visual object category recognition, L1 regularized sparse coding is combined with spatial pyramid representation to obtain state-of-the-art performance. However, because of its iterative optimization, applying sparse coding onto every local feature descriptor extracted from an image database can become a major bottleneck. To overcome this computational challenge, this paper presents "Generalized Lasso based Approximation of Sparse coding" (GLAS). By representing the distribution of sparse coefficients with slice transform, we fit a piece-wise linear mapping function with generalized lasso. We also propose an efficient post-refinement procedure to perform mutual inhibition between bases which is essential for an overcomplete setting. The experiments show that GLAS obtains comparable performance to L1 regularized sparse coding, yet achieves significant speed up demonstrating its effectiveness for large-scale visual recognition problems.
Code (0)
등록된 구현이 없습니다.
Tasks
Object RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
The Trimmed Lasso: Sparse Recovery Guarantees and Practical Optimization by the Generalized Soft-Min Penalty
We present a new approach to solve the sparse approximation or best subset selection problem, namely find a $k$-sparse vector ${\bf x}\in\mathbb{R}^d$ that minimizes the $\ell_2$ residual $\lVert A{\bf x}-{\bf y} \rVert_…
Bayesian generalized fused lasso modeling via NEG distribution
The fused lasso penalizes a loss function by the $L_1$ norm for both the regression coefficients and their successive differences to encourage sparsity of both. In this paper, we propose a Bayesian generalized fused lass…
regressionError Bounds for Generalized Group Sparsity
In high-dimensional statistical inference, sparsity regularizations have shown advantages in consistency and convergence rates for coefficient estimation. We consider a generalized version of Sparse-Group Lasso which cap…
Dictionary-based Low-Rank Approximations and the Mixed Sparse Coding problem
Constrained tensor and matrix factorization models allow to extract interpretable patterns from multiway data. Therefore identifiability properties and efficient algorithms for constrained low-rank approximations are now…
The False Positive Control Lasso
In high dimensional settings where a small number of regressors are expected to be important, the Lasso estimator can be used to obtain a sparse solution vector with the expectation that most of the non-zero coefficients…