On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition

• URL: http://arxiv.org/abs/2205.13282v1
• Date: Thu, 26 May 2022 11:41:36 GMT
• Title: On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition
• Authors: Yue Song, Nicu Sebe, Wei Wang
• Abstract summary: We show that truncating small eigenvalues of the Global Covariance Pooling (GCP) can attain smoother gradient. On fine-grained datasets, truncating the small eigenvalues would make the model fail to converge. Inspired by this observation, we propose a network branch dedicated to magnifying the importance of small eigenvalues.
• Score: 65.67315418971688
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The Fine-Grained Visual Categorization (FGVC) is challenging because the subtle inter-class variations are difficult to be captured. One notable research line uses the Global Covariance Pooling (GCP) layer to learn powerful representations with second-order statistics, which can effectively model inter-class differences. In our previous conference paper, we show that truncating small eigenvalues of the GCP covariance can attain smoother gradient and improve the performance on large-scale benchmarks. However, on fine-grained datasets, truncating the small eigenvalues would make the model fail to converge. This observation contradicts the common assumption that the small eigenvalues merely correspond to the noisy and unimportant information. Consequently, ignoring them should have little influence on the performance. To diagnose this peculiar behavior, we propose two attribution methods whose visualizations demonstrate that the seemingly unimportant small eigenvalues are crucial as they are in charge of extracting the discriminative class-specific features. Inspired by this observation, we propose a network branch dedicated to magnifying the importance of small eigenvalues. Without introducing any additional parameters, this branch simply amplifies the small eigenvalues and achieves state-of-the-art performances of GCP methods on three fine-grained benchmarks. Furthermore, the performance is also competitive against other FGVC approaches on larger datasets. Code is available at \href{https://github.com/KingJamesSong/DifferentiableSVD}{https://github.com/KingJamesSong/DifferentiableSVD}.

Related papers

• Eigen-Cluster VIS: Improving Weakly-supervised Video Instance Segmentation by Leveraging Spatio-temporal Consistency [9.115508086522887]
  This work introduces a novel weakly-supervised method called Eigen-cluster VIS. It achieves competitive accuracy compared to other VIS approaches without requiring any mask annotations. It is evaluated on the YouTube-VIS21 and OVIS 2019/20 datasets.
  arXiv  Detail & Related papers  (2024-08-29T16:05:05Z)
• Regularized Contrastive Partial Multi-view Outlier Detection [76.77036536484114]
  We propose a novel method named Regularized Contrastive Partial Multi-view Outlier Detection (RCPMOD) In this framework, we utilize contrastive learning to learn view-consistent information and distinguish outliers by the degree of consistency. Experimental results on four benchmark datasets demonstrate that our proposed approach could outperform state-of-the-art competitors.
  arXiv  Detail & Related papers  (2024-08-02T14:34:27Z)
• Fine-grained Recognition with Learnable Semantic Data Augmentation [68.48892326854494]
  Fine-grained image recognition is a longstanding computer vision challenge. We propose diversifying the training data at the feature-level to alleviate the discriminative region loss problem. Our method significantly improves the generalization performance on several popular classification networks.
  arXiv  Detail & Related papers  (2023-09-01T11:15:50Z)
• Boosting Differentiable Causal Discovery via Adaptive Sample Reweighting [62.23057729112182]
  Differentiable score-based causal discovery methods learn a directed acyclic graph from observational data. We propose a model-agnostic framework to boost causal discovery performance by dynamically learning the adaptive weights for the Reweighted Score function, ReScore.
  arXiv  Detail & Related papers  (2023-03-06T14:49:59Z)
• R2-Trans:Fine-Grained Visual Categorization with Redundancy Reduction [21.11038841356125]
  Fine-grained visual categorization (FGVC) aims to discriminate similar subcategories, whose main challenge is the large intraclass diversities and subtle inter-class differences. We present a novel approach for FGVC, which can simultaneously make use of partial yet sufficient discriminative information in environmental cues and also compress the redundant information in class-token with respect to the target.
  arXiv  Detail & Related papers  (2022-04-21T13:35:38Z)
• Multi-scale Interactive Network for Salient Object Detection [91.43066633305662]
  We propose the aggregate interaction modules to integrate the features from adjacent levels. To obtain more efficient multi-scale features, the self-interaction modules are embedded in each decoder unit. Experimental results on five benchmark datasets demonstrate that the proposed method without any post-processing performs favorably against 23 state-of-the-art approaches.
  arXiv  Detail & Related papers  (2020-07-17T15:41:37Z)
• Supervised Visualization for Data Exploration [9.742277703732187]
  We describe a novel supervised visualization technique based on random forest proximities and diffusion-based dimensionality reduction. Our approach is robust to noise and parameter tuning, thus making it simple to use while producing reliable visualizations for data exploration.
  arXiv  Detail & Related papers  (2020-06-15T19:10:17Z)
• DHOG: Deep Hierarchical Object Grouping [0.0]
  We show that greedy or local methods of maximising mutual information (such as gradient optimisation) discover local optima of the mutual information criterion. We introduce deep hierarchical object grouping (DHOG) that computes a number distinct discrete representations of images in a hierarchical order. We find that these representations align better with the downstream task of grouping into underlying object classes.
  arXiv  Detail & Related papers  (2020-03-13T14:11:48Z)
• Diversity inducing Information Bottleneck in Model Ensembles [73.80615604822435]
  In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction. We explicitly optimize a diversity inducing adversarial loss for learning latent variables and thereby obtain diversity in the output predictions necessary for modeling multi-modal data. Compared to the most competitive baselines, we show significant improvements in classification accuracy, under a shift in the data distribution.
  arXiv  Detail & Related papers  (2020-03-10T03:10:41Z)

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.