Leveraging Unlabeled Data for Sketch-based Understanding

• URL: http://arxiv.org/abs/2204.12522v1
• Date: Tue, 26 Apr 2022 18:13:30 GMT
• Title: Leveraging Unlabeled Data for Sketch-based Understanding
• Authors: Javier Morales, Nils Murrugarra-Llerena and Jose M. Saavedra
• Abstract summary: We present a study about the use of unlabeled data to improve a sketch-based model. Our results show the superiority of sketch-BYOL, which outperforms other self-supervised approaches.
• Score: 11.95015190261688
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Sketch-based understanding is a critical component of human cognitive learning and is a primitive communication means between humans. This topic has recently attracted the interest of the computer vision community as sketching represents a powerful tool to express static objects and dynamic scenes. Unfortunately, despite its broad application domains, the current sketch-based models strongly rely on labels for supervised training, ignoring knowledge from unlabeled data, thus limiting the underlying generalization and the applicability. Therefore, we present a study about the use of unlabeled data to improve a sketch-based model. To this end, we evaluate variations of VAE and semi-supervised VAE, and present an extension of BYOL to deal with sketches. Our results show the superiority of sketch-BYOL, which outperforms other self-supervised approaches increasing the retrieval performance for known and unknown categories. Furthermore, we show how other tasks can benefit from our proposal.

Related papers

• Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph Propagation [68.13453771001522]
  We propose a multimodal intensive ZSL framework that matches regions of images with corresponding semantic embeddings. We conduct extensive experiments and evaluate our model on large-scale real-world data.
  arXiv  Detail & Related papers  (2023-06-14T13:07:48Z)
• SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning [12.783251612977299]
  In contrastive learning, the choice of view'' controls the information that the representation captures and influences the performance of the model. An anchor view that maintains the essential information of input graphs for contrastive learning has been hardly investigated. We extensively validate the proposed anchor view on various benchmarks regarding graph classification under unsupervised, semi-supervised, and transfer learning.
  arXiv  Detail & Related papers  (2023-05-08T06:52:02Z)
• Bridging the visual gap in VLN via semantically richer instructions [3.5789352263336847]
  We show that state-of-the-art models are not severely affected when they receive just limited or even no visual data. We propose a new data augmentation method that fosters the inclusion of more explicit visual information.
  arXiv  Detail & Related papers  (2022-10-27T15:58:07Z)
• Exploring CLIP for Assessing the Look and Feel of Images [87.97623543523858]
  We introduce Contrastive Language-Image Pre-training (CLIP) models for assessing both the quality perception (look) and abstract perception (feel) of images in a zero-shot manner. Our results show that CLIP captures meaningful priors that generalize well to different perceptual assessments.
  arXiv  Detail & Related papers  (2022-07-25T17:58:16Z)
• I Know What You Draw: Learning Grasp Detection Conditioned on a Few Freehand Sketches [74.63313641583602]
  We propose a method to generate a potential grasp configuration relevant to the sketch-depicted objects. Our model is trained and tested in an end-to-end manner which is easy to be implemented in real-world applications.
  arXiv  Detail & Related papers  (2022-05-09T04:23:36Z)
• Graph Few-shot Class-incremental Learning [25.94168397283495]
  The ability to incrementally learn new classes is vital to all real-world artificial intelligence systems. In this paper, we investigate the challenging yet practical problem, Graph Few-shot Class-incremental (Graph FCL) problem. We put forward a Graph Pseudo Incremental Learning paradigm by sampling tasks recurrently from the base classes. We present a task-sensitive regularizer calculated from task-level attention and node class prototypes to mitigate overfitting onto either novel or base classes.
  arXiv  Detail & Related papers  (2021-12-23T19:46:07Z)
• Towards Unsupervised Sketch-based Image Retrieval [126.77787336692802]
  We introduce a novel framework that simultaneously performs unsupervised representation learning and sketch-photo domain alignment. Our framework achieves excellent performance in the new unsupervised setting, and performs comparably or better than state-of-the-art in the zero-shot setting.
  arXiv  Detail & Related papers  (2021-05-18T02:38:22Z)
• Self-supervised on Graphs: Contrastive, Generative,or Predictive [25.679620842010422]
  Self-supervised learning (SSL) is emerging as a new paradigm for extracting informative knowledge through well-designed pretext tasks. We divide existing graph SSL methods into three categories: contrastive, generative, and predictive. We also summarize the commonly used datasets, evaluation metrics, downstream tasks, and open-source implementations of various algorithms.
  arXiv  Detail & Related papers  (2021-05-16T03:30:03Z)
• Visual Distant Supervision for Scene Graph Generation [66.10579690929623]
  Scene graph models usually require supervised learning on large quantities of labeled data with intensive human annotation. We propose visual distant supervision, a novel paradigm of visual relation learning, which can train scene graph models without any human-labeled data. Comprehensive experimental results show that our distantly supervised model outperforms strong weakly supervised and semi-supervised baselines.
  arXiv  Detail & Related papers  (2021-03-29T06:35:24Z)
• Deep Self-Supervised Representation Learning for Free-Hand Sketch [51.101565480583304]
  We tackle the problem of self-supervised representation learning for free-hand sketches. Key for the success of our self-supervised learning paradigm lies with our sketch-specific designs. We show that the proposed approach outperforms the state-of-the-art unsupervised representation learning methods.
  arXiv  Detail & Related papers  (2020-02-03T16:28:29Z)

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.