Learning Partial Correlation based Deep Visual Representation for Image Classification

• URL: http://arxiv.org/abs/2304.11597v2
• Date: Wed, 26 Apr 2023 07:00:11 GMT
• Title: Learning Partial Correlation based Deep Visual Representation for Image Classification
• Authors: Saimunur Rahman and Piotr Koniusz and Lei Wang and Luping Zhou and Peyman Moghadam and Changming Sun
• Abstract summary: We formulate sparse inverse covariance estimation (SICE) as a novel structured layer of CNN. Our work obtains a partial correlation based deep visual representation and mitigates the small sample problem. Experiments show the efficacy and superior classification performance of our model.
• Score: 61.0532370259644
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual representation based on covariance matrix has demonstrates its efficacy for image classification by characterising the pairwise correlation of different channels in convolutional feature maps. However, pairwise correlation will become misleading once there is another channel correlating with both channels of interest, resulting in the ``confounding'' effect. For this case, ``partial correlation'' which removes the confounding effect shall be estimated instead. Nevertheless, reliably estimating partial correlation requires to solve a symmetric positive definite matrix optimisation, known as sparse inverse covariance estimation (SICE). How to incorporate this process into CNN remains an open issue. In this work, we formulate SICE as a novel structured layer of CNN. To ensure end-to-end trainability, we develop an iterative method to solve the above matrix optimisation during forward and backward propagation steps. Our work obtains a partial correlation based deep visual representation and mitigates the small sample problem often encountered by covariance matrix estimation in CNN. Computationally, our model can be effectively trained with GPU and works well with a large number of channels of advanced CNNs. Experiments show the efficacy and superior classification performance of our deep visual representation compared to covariance matrix based counterparts.

Related papers

• Canonical Correlation Guided Deep Neural Network [14.188285111418516]
  We present a canonical correlation guided learning framework, which allows to be realized by deep neural networks (CCDNN) In the proposed method, the optimization formulation is not restricted to maximize correlation, instead we make canonical correlation as a constraint. To reduce the redundancy induced by correlation, a redundancy filter is designed.
  arXiv  Detail & Related papers  (2024-09-28T16:08:44Z)
• Efficient Similarity-based Passive Filter Pruning for Compressing CNNs [23.661189257759535]
  Convolution neural networks (CNNs) have shown great success in various applications. computational complexity and memory storage of CNNs is a bottleneck for their deployment on resource-constrained devices. Recent efforts towards reducing the computation cost and the memory overhead of CNNs involve similarity-based passive filter pruning methods.
  arXiv  Detail & Related papers  (2022-10-27T09:57:47Z)
• Large-Margin Representation Learning for Texture Classification [67.94823375350433]
  This paper presents a novel approach combining convolutional layers (CLs) and large-margin metric learning for training supervised models on small datasets for texture classification. The experimental results on texture and histopathologic image datasets have shown that the proposed approach achieves competitive accuracy with lower computational cost and faster convergence when compared to equivalent CNNs.
  arXiv  Detail & Related papers  (2022-06-17T04:07:45Z)
• Disentangled Representation Learning for Text-Video Retrieval [51.861423831566626]
  Cross-modality interaction is a critical component in Text-Video Retrieval (TVR) We study the interaction paradigm in depth, where we find that its computation can be split into two terms. We propose a disentangled framework to capture a sequential and hierarchical representation.
  arXiv  Detail & Related papers  (2022-03-14T13:55:33Z)
• Semantic Correspondence with Transformers [68.37049687360705]
  We propose Cost Aggregation with Transformers (CATs) to find dense correspondences between semantically similar images. We include appearance affinity modelling to disambiguate the initial correlation maps and multi-level aggregation. We conduct experiments to demonstrate the effectiveness of the proposed model over the latest methods and provide extensive ablation studies.
  arXiv  Detail & Related papers  (2021-06-04T14:39:03Z)
• ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution [57.635467829558664]
  We introduce a structural regularization across convolutional kernels in a CNN. We show that CNNs now maintain performance with dramatic reduction in parameters and computations.
  arXiv  Detail & Related papers  (2020-09-04T20:41:47Z)
• Out-of-distribution Generalization via Partial Feature Decorrelation [72.96261704851683]
  We present a novel Partial Feature Decorrelation Learning (PFDL) algorithm, which jointly optimize a feature decomposition network and the target image classification model. The experiments on real-world datasets demonstrate that our method can improve the backbone model's accuracy on OOD image classification datasets.
  arXiv  Detail & Related papers  (2020-07-30T05:48:48Z)
• Domain Siamese CNNs for Sparse Multispectral Disparity Estimation [15.065764374430783]
  We propose a new CNN architecture able to do disparity estimation between images from different spectrum. Our method was tested using the publicly available LITIV 2014 and LITIV 2018 datasets.
  arXiv  Detail & Related papers  (2020-04-30T20:29:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.