• Home
  • Search
  • Representation Learning by Learning to Count
  • Open Access IconOpen Access
  • Cite Icon459
  • https://doi.org/10.1109/iccv.2017.628Copy DOI Icon

Representation Learning by Learning to Count

  • Oct 1, 2017
  • Mehdi Noroozi +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

We introduce a novel method for representation learning that uses an artificial supervision signal based on counting visual primitives. This supervision signal is obtained from an equivariance relation, which does not require any manual annotation. We relate transformations of images to transformations of the representations. More specifically, we look for the representation that satisfies such relation rather than the transformations that match a given representation. In this paper, we use two image transformations in the context of counting: scaling and tiling. The first transformation exploits the fact that the number of visual primitives should be invariant to scale. The second transformation allows us to equate the total number of visual primitives in each tile to that in the whole image. These two transformations are combined in one constraint and used to train a neural network with a contrastive loss. The proposed task produces representations that perform on par or exceed the state of the art in transfer learning benchmarks.

Similar Papers
  • Research Article
  • Citations11

Recent Advances in Representation Learning for Electronic Health Records: A Systematic Review

  • Feb 01, 2022
  • Journal of Physics: Conference Series
  • Xiaocong Liu +4
  • Research Article
  • Citations4

Using Language Representation Learning Approach to Efficiently Identify Protein Complex Categories in Electron Transport Chain.

  • Jul 16, 2020
  • Molecular Informatics
  • Trinh‐Trung‐Duong Nguyen +4
  • Research Article
  • Citations13

Geographical Supervision Correction for Remote Sensing Representation Learning

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Wenyuan Li +2
  • Research Article

A multi-view representation learning framework for commonsense knowledge bases

  • May 09, 2024
  • Information Sciences
  • Weiyan Zhang +5
  • Book Chapter
  • Citations13

A Study of Representation Learning for Handwritten Numeral Recognition of Multilingual Data Set

  • Nov 08, 2017
  • Solley Thomas
  • Conference Article
  • Citations289

Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification

  • Jun 01, 2021
  • Peng Wang +4
  • Research Article
  • Citations1

Representation Learning in PET Scans Enhanced by Semantic and 3D Position Specific Characteristics.

  • Sep 01, 2025
  • IEEE transactions on medical imaging
  • Theodoros P Vagenas +4
  • Book Chapter

A Survey of Literature Analysis Methods Based on Representation Learning

  • Jan 01, 2022
  • Qinghui Zhang +1
  • Research Article
  • Citations35

Representation Learning With Class Level Autoencoder for Intelligent Fault Diagnosis

  • Oct 01, 2019
  • IEEE Signal Processing Letters
  • Hui Yu +3
  • Conference Article
  • Citations3

Self-Supervised Mutual Learning for Video Representation Learning

  • Jul 05, 2021
  • Jinpeng Wang +4
  • Book Chapter
  • Citations44

Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations

  • Jan 01, 2022
  • Atsuhiro Noguchi +3
  • Research Article
  • Citations5

Structure-Driven Representation Learning for Deep Clustering

  • Oct 16, 2023
  • ACM Transactions on Knowledge Discovery from Data
  • Xiang Wang +3
  • Research Article
  • Citations4

DCRL-KG: Distributed Multi-Modal Knowledge Graph Retrieval Platform Based on Collaborative Representation Learning

  • Jan 01, 2023
  • Intelligent Automation & Soft Computing
  • Leilei Li +8
  • PDF
  • Research Article
  • Citations4

Learning Universal Trajectory Representation via a Siamese Geography-Aware Transformer

  • Feb 20, 2024
  • ISPRS International Journal of Geo-Information
  • Chenhao Wu +4
  • Research Article
  • Citations2

Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning

  • Mar 24, 2024
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Ruiqian Nai +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.