• Home
  • Search
  • Learn to Predict Sets Using Feed-Forward Neural Networks.
  • Open Access IconOpen Access
  • Cite Icon15
  • https://doi.org/10.1109/tpami.2021.3122970Copy DOI Icon

Learn to Predict Sets Using Feed-Forward Neural Networks.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

This paper addresses the task of set prediction using deep feed-forward neural networks. A set is a collection of elements which is invariant under permutation and the size of a set is not fixed in advance. Many real-world problems, such as image tagging and object detection, have outputs that are naturally expressed as sets of entities. This creates a challenge for traditional deep neural networks which naturally deal with structured outputs such as vectors, matrices or tensors. We present a novel approach for learning to predict sets with unknown permutation and cardinality using deep neural networks. In our formulation we define a likelihood for a set distribution represented by a) two discrete distributions defining the set cardinally and permutation variables, and b) a joint distribution over set elements with a fixed cardinality. Depending on the problem under consideration, we define different training models for set prediction using deep neural networks. We demonstrate the validity of our set formulations on relevant vision problems such as: 1) multi-label image classification where we outperform the other competing methods on the PASCAL VOC and MS COCO datasets, 2) object detection, for which our formulation outperforms popular state-of-the-art detectors, and 3) a complex CAPTCHA test, where we observe that, surprisingly, our set-based network acquired the ability of mimicking arithmetics without any rules being coded.

Similar Papers
  • Research Article
  • Citations55

A feedforward deep neural network for predicting the state-of-charge of lithium-ion battery in electric vehicles

  • Jun 01, 2023
  • Decision Analytics Journal
  • Bukola Peter Adedeji +1
  • Research Article
  • Citations29

Combining local and global hypotheses in deep neural network for multi-label image classification

  • Dec 25, 2016
  • Neurocomputing
  • Qinghua Yu +4
  • Conference Article
  • Citations31

Towards Twitter hashtag recommendation using distributed word representations and a deep feed forward neural network

  • Sep 01, 2014
  • Abhineshwar Tomar +4
  • Research Article
  • Citations479

A comprehensive review of object detection with deep learning

  • Nov 08, 2022
  • Digital Signal Processing
  • Ravpreet Kaur +1
  • Research Article
  • Citations190

Off-target predictions in CRISPR-Cas9 gene editing using deep learning.

  • Sep 01, 2018
  • Bioinformatics
  • Jiecong Lin +1
  • Research Article
  • Citations110

Deep Learning and Machine Learning with Grid Search to Predict Later Occurrence of Breast Cancer Metastasis Using Clinical Data

  • Sep 29, 2022
  • Journal of Clinical Medicine
  • Xia Jiang +1
  • Research Article
  • Citations7

Jaya-Mutated Leader Algorithm Based Deep Feed Forward Neural Network for Intrusion Detection Using Cloud Computing

  • Dec 14, 2022
  • Cybernetics and Systems
  • Kirti Mahajan +4
  • Conference Article
  • Citations39

Object detection using deep neural networks

  • Jun 01, 2017
  • Malay Shah +1
  • Research Article
  • Citations9

Joint Learning of Set Cardinality and State Distribution

  • Apr 29, 2018
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • S Hamid Rezatofighi +4
  • Research Article
  • Citations22

Deep Neural Network Based Linearization and Cold Junction Compensation of Thermocouple

  • Jan 01, 2022
  • IEEE Transactions on Instrumentation and Measurement
  • Ramya Anandanatarajan +2
  • Research Article
  • Citations18

Medium-term water consumption forecasting based on deep neural networks

  • Jan 24, 2024
  • Expert Systems with Applications
  • A Gil-Gamboa +3
  • PDF
  • Research Article
  • Citations16

An Interactive Visualization for Feature Localization in Deep Neural Networks

  • Jul 23, 2020
  • Frontiers in Artificial Intelligence
  • Martin Zurowietz +1
  • Research Article

Saleh Assisted Deep Neural Network Behavioral Model of Radio Frequency Power Amplifiers

  • Jan 01, 2025
  • Journal of Applied Mathematics and Physics
  • Zhe Jin
  • Book Chapter
  • Citations1

Handwritten Digit Recognition Using Very Deep Convolutional Neural Network

  • Jan 01, 2022
  • M Dhilsath Fathima +2
  • Research Article
  • Citations37

Fooling deep neural detection networks with adaptive object-oriented adversarial perturbation

  • Feb 20, 2021
  • Pattern Recognition
  • Yatie Xiao +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.