CORE: Learning Consistent Ordinal REpresentations for Image Ordinal Estimation

• URL: http://arxiv.org/abs/2301.06122v1
• Date: Sun, 15 Jan 2023 15:42:26 GMT
• Title: CORE: Learning Consistent Ordinal REpresentations for Image Ordinal Estimation
• Authors: Yiming Lei, Zilong Li, Yangyang Li, Junping Zhang, Hongming Shan
• Abstract summary: This paper proposes learning intrinsic Consistent Ordinal REpresentations (CORE) from ordinal relations residing in groundtruth labels. CORE can accurately construct an ordinal latent space and significantly enhance existing deep ordinal regression methods to achieve better results.
• Score: 35.39143939072549
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The goal of image ordinal estimation is to estimate the ordinal label of a given image with a convolutional neural network. Existing methods are mainly based on ordinal regression and particularly focus on modeling the ordinal mapping from the feature representation of the input to the ordinal label space. However, the manifold of the resultant feature representations does not maintain the intrinsic ordinal relations of interest, which hinders the effectiveness of the image ordinal estimation. Therefore, this paper proposes learning intrinsic Consistent Ordinal REpresentations (CORE) from ordinal relations residing in groundtruth labels while encouraging the feature representations to embody the ordinal low-dimensional manifold. First, we develop an ordinal totally ordered set (toset) distribution (OTD), which can (i) model the label embeddings to inherit ordinal information and measure distances between ordered labels of samples in a neighborhood, and (ii) model the feature embeddings to infer numerical magnitude with unknown ordinal information among the features of different samples. Second, through OTD, we convert the feature representations and labels into the same embedding space for better alignment, and then compute the Kullback Leibler (KL) divergence between the ordinal labels and feature representations to endow the latent space with consistent ordinal relations. Third, we optimize the KL divergence through ordinal prototype-constrained convex programming with dual decomposition; our theoretical analysis shows that we can obtain the optimal solutions via gradient backpropagation. Extensive experimental results demonstrate that the proposed CORE can accurately construct an ordinal latent space and significantly enhance existing deep ordinal regression methods to achieve better results.

Related papers

• Learning Ordinality in Semantic Segmentation [3.017721041662511]
  It is known that the pupil is inside the iris, and the lane markings are inside the road. Conventional deep learning models do not take advantage of ordinal relations that might exist in the domain at hand. This paper proposes pixel-wise ordinal segmentation methods, which treat each pixel as an independent observation and promote ordinality in its representation.
  arXiv  Detail & Related papers  (2024-07-30T16:36:15Z)
• Deep Diversity-Enhanced Feature Representation of Hyperspectral Images [87.47202258194719]
  We rectify 3D convolution by modifying its topology to enhance the rank upper-bound. We also propose a novel diversity-aware regularization (DA-Reg) term that acts on the feature maps to maximize independence among elements. To demonstrate the superiority of the proposed Re$3$-ConvSet and DA-Reg, we apply them to various HS image processing and analysis tasks.
  arXiv  Detail & Related papers  (2023-01-15T16:19:18Z)
• Multilevel orthogonal Bochner function subspaces with applications to robust machine learning [1.533771872970755]
  We consider the data as instances of a random field within a relevant Bochner space. Our key observation is that the classes can predominantly reside in two distinct subspaces.
  arXiv  Detail & Related papers  (2021-10-04T22:01:01Z)
• Articulated Shape Matching Using Laplacian Eigenfunctions and Unsupervised Point Registration [38.16866987817019]
  Spectral graph theory can be used to map these graphs onto lower dimensional spaces and match shapes by aligning their embeddings. We derive a new formulation that finds the best alignment between two congruent $K$-dimensional sets of points by selecting the best subset of eigenfunctions of the Laplacian matrix.
  arXiv  Detail & Related papers  (2020-12-14T08:49:25Z)
• Convolutional Ordinal Regression Forest for Image Ordinal Estimation [52.67784321853814]
  We propose a novel ordinal regression approach, termed Convolutional Ordinal Regression Forest or CORF, for image ordinal estimation. The proposed CORF integrates ordinal regression and differentiable decision trees with a convolutional neural network for obtaining precise and stable global ordinal relationships. The effectiveness of the proposed CORF is verified on two image ordinal estimation tasks, showing significant improvements and better stability over the state-of-the-art ordinal regression methods.
  arXiv  Detail & Related papers  (2020-08-07T10:41:17Z)
• 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)
• Self-Supervised Tuning for Few-Shot Segmentation [82.32143982269892]
  Few-shot segmentation aims at assigning a category label to each image pixel with few annotated samples. Existing meta-learning method tends to fail in generating category-specifically discriminative descriptor when the visual features extracted from support images are marginalized in embedding space. This paper presents an adaptive framework tuning, in which the distribution of latent features across different episodes is dynamically adjusted based on a self-segmentation scheme.
  arXiv  Detail & Related papers  (2020-04-12T03:53:53Z)
• Supervised Learning for Non-Sequential Data: A Canonical Polyadic Decomposition Approach [85.12934750565971]
  Efficient modelling of feature interactions underpins supervised learning for non-sequential tasks. To alleviate this issue, it has been proposed to implicitly represent the model parameters as a tensor. For enhanced expressiveness, we generalize the framework to allow feature mapping to arbitrarily high-dimensional feature vectors.
  arXiv  Detail & Related papers  (2020-01-27T22:38:40Z)

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.