Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification

• URL: http://arxiv.org/abs/2105.09684v1
• Date: Thu, 20 May 2021 11:54:05 GMT
• Title: Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification
• Abstract summary: We propose ColorCount, a novel CNN-based approach by combining self-supervised transfer colorization learning and global prior classification. We conduct extensive experiments on four challenging benchmarks. ColorCount achieves much better performance as compared with other unsupervised approaches.
• Score: 2.0088802641040604
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Labeled crowd scene images are expensive and scarce. To significantly reduce the requirement of the labeled images, we propose ColorCount, a novel CNN-based approach by combining self-supervised transfer colorization learning and global prior classification to leverage the abundantly available unlabeled data. The self-supervised colorization branch learns the semantics and surface texture of the image by using its color components as pseudo labels. The classification branch extracts global group priors by learning correlations among image clusters. Their fused resultant discriminative features (global priors, semantics and textures) provide ample priors for counting, hence significantly reducing the requirement of labeled images. We conduct extensive experiments on four challenging benchmarks. ColorCount achieves much better performance as compared with other unsupervised approaches. Its performance is close to the supervised baseline with substantially less labeled data (10\% of the original one).

Related papers

• Accuracy Improvement of Semi-Supervised Segmentation Using Supervised ClassMix and Sup-Unsup Feature Discriminator [17.179617344873275]
  A conventional semi-supervised learning method, ClassMix, pastes class labels predicted from unlabeled images onto other images.<n>We propose a method where class labels from labeled images, along with the corresponding image regions, are pasted onto unlabeled images and their pseudo-labeled images.<n>We introduce a method that trains the model to make predictions on unlabeled images more similar to those on labeled images.
  arXiv  Detail & Related papers  (2026-04-08T14:18:00Z)
• Leveraging the Powerful Attention of a Pre-trained Diffusion Model for Exemplar-based Image Colorization [4.233370898095789]
  Exemplar-based image colorization aims to colorize a grayscale image using a reference color image.<n>We propose a novel, fine-tuning-free approach based on a pre-trained diffusion model.<n>Our experimental results demonstrate that our method outperforms existing techniques in terms of image quality and fidelity to the reference.
  arXiv  Detail & Related papers  (2025-05-21T17:59:40Z)
• Mixed Supervision Learning for Whole Slide Image Classification [88.31842052998319]
  We propose a mixed supervision learning framework for super high-resolution images. During the patch training stage, this framework can make use of coarse image-level labels to refine self-supervised learning. A comprehensive strategy is proposed to suppress pixel-level false positives and false negatives.
  arXiv  Detail & Related papers  (2021-07-02T09:46:06Z)
• Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization [112.68171734288237]
  We propose a novel framework for discriminative pixel-level tasks using a generative model of both images and labels. We learn a generative adversarial network that captures the joint image-label distribution and is trained efficiently using a large set of unlabeled images. We demonstrate strong in-domain performance compared to several baselines, and are the first to showcase extreme out-of-domain generalization.
  arXiv  Detail & Related papers  (2021-04-12T21:41:25Z)
• Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels [34.13899937264952]
  ImageNet has been arguably the most popular image classification benchmark, but it is also the one with a significant level of label noise. Recent studies have shown that many samples contain multiple classes, despite being assumed to be a single-label benchmark. We argue that the mismatch between single-label annotations and effectively multi-label images is equally, if not more, problematic in the training setup, where random crops are applied.
  arXiv  Detail & Related papers  (2021-01-13T11:55:58Z)
• Coarse to Fine: Multi-label Image Classification with Global/Local Attention [19.532952411766168]
  We propose a global/local attention method that can recognize an image from coarse to fine. Specifically, our global/local attention method first concentrates on the whole image, and then focuses on local specific objects in the image. We also propose a joint max-margin objective function, which enforces that the minimum score of positive labels should be larger than the maximum score of negative labels horizontally and vertically.
  arXiv  Detail & Related papers  (2020-12-26T02:36:04Z)
• Grafit: Learning fine-grained image representations with coarse labels [114.17782143848315]
  This paper tackles the problem of learning a finer representation than the one provided by training labels. By jointly leveraging the coarse labels and the underlying fine-grained latent space, it significantly improves the accuracy of category-level retrieval methods.
  arXiv  Detail & Related papers  (2020-11-25T19:06:26Z)
• Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge [36.04579549557464]
  Multi-label zero-shot classification aims to predict multiple unseen class labels for an input image. This paper introduces a novel multi-label zero-shot classification framework by learning to transfer from external knowledge.
  arXiv  Detail & Related papers  (2020-07-30T17:26:46Z)
• SCAN: Learning to Classify Images without Labels [73.69513783788622]
  We advocate a two-step approach where feature learning and clustering are decoupled. A self-supervised task from representation learning is employed to obtain semantically meaningful features. We obtain promising results on ImageNet, and outperform several semi-supervised learning methods in the low-data regime.
  arXiv  Detail & Related papers  (2020-05-25T18:12:33Z)
• Focus Longer to See Better:Recursively Refined Attention for Fine-Grained Image Classification [148.4492675737644]
  Deep Neural Network has shown great strides in the coarse-grained image classification task. In this paper, we try to focus on these marginal differences to extract more representative features. Our network repetitively focuses on parts of images to spot small discriminative parts among the classes.
  arXiv  Detail & Related papers  (2020-05-22T03:14:18Z)
• RGB-based Semantic Segmentation Using Self-Supervised Depth Pre-Training [77.62171090230986]
  We propose an easily scalable and self-supervised technique that can be used to pre-train any semantic RGB segmentation method. In particular, our pre-training approach makes use of automatically generated labels that can be obtained using depth sensors. We show how our proposed self-supervised pre-training with HN-labels can be used to replace ImageNet pre-training.
  arXiv  Detail & Related papers  (2020-02-06T11:16:24Z)

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.