Integrating Convolution and Sparse Coding for Learning Low-Dimensional Discriminative Image Representations
- 18 September 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (7) , 12483-12496
Abstract
This work investigates the problem of efficiently learning discriminative low-dimensional (LD) representations of multiclass image objects. We propose a generic end-to-end approach that jointly optimizes sparse dictionary and convolutions for learning LOW-dimensional discriminative image representations, named SparConvLow, taking advantage of c onvolutional n eural n etworks ( CNN s), dictionary learning, and orthogonal projections. The whole learning process can be summarized as follows. First, a CNN module is employed to extract high-dimensional (HD) preliminary convolutional features. Second, to avoid the high computational cost of direct sparse coding on HD CNN features, we learn sparse representation (SR) over a task-driven dictionary in the space with the feature being orthogonally projected. We then exploit the discriminative projection on SR. The whole learning process is consistently treated as an end-to-end joint optimization problem of trace quotient maximization. The cost function is well-defined on the product of the CNN parameters space, the Stiefel manifold, the Oblique manifold, and the Grassmann manifold. By using the explicit gradient delivery, the cost function is optimized via a geometrical stochastic gradient descent (SGD) algorithm along with the chain rule and the backpropagation. The experimental results show that the proposed method can achieve a highly competitive performance with the state-of-the-art (SOTA) image classification, object categorization, and face recognition methods, under both supervised and semi-supervised settings. The code is available at https://github.com/MVPR-Group/SparConvLow.Keywords
Funding Information
- National Natural Science Foundation of China (62272170, 42130112)
- General Program of Shanghai Natural Science Foundation (23ZR1419300)
- Science and Technology Commission of Shanghai Municipality (22DZ2229004)
- “Digital Silk Road” Shanghai International Joint Laboratory of Trustworthy Intelligent Software (22510750100)
- Shanghai Trusted Industry Internet Software Collaborative Innovation Center
This publication has 53 references indexed in Scilit:
- Visual tracking using convolutional features with sparse codingArtificial Intelligence Review, 2020
- Identity Mappings in Deep Residual Networks2016
- Supervised dictionary learning with multiple classifier integrationPattern Recognition, 2016
- Sparse Coding for Classification via Discrimination Ensemble2016
- Equiangular Kernel Dictionary Learning with Applications to Dynamic Texture Analysis2016
- Sparse Coding and Dictionary Learning with Linear Dynamical Systems2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Flexible orthogonal semisupervised learning for dimension reduction with image classificationNeurocomputing, 2014
- Trace optimization and eigenproblems in dimension reduction methodsNumerical Linear Algebra with Applications, 2010
- Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categoriesComputer Vision and Image Understanding, 2007