• Home
  • Search
  • Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom Up
  • Open Access IconOpen Access
  • Cite Icon348
  • https://doi.org/10.1109/cvpr.2019.00315Copy DOI Icon

Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom Up

  • Jun 1, 2019
  • Weifeng Ge +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Given a training dataset composed of images and corresponding category labels, deep convolutional neural networks show a strong ability in mining discriminative parts for image classification. However, deep convolutional neural networks trained with image level labels only tend to focus on the most discriminative parts while missing other object parts, which could provide complementary information. In this paper, we approach this problem from a different perspective. We build complementary parts models in a weakly supervised manner to retrieve information suppressed by dominant object parts detected by convolutional neural networks. Given image level labels only, we first extract rough object instances by performing weakly supervised object detection and instance segmentation using Mask R-CNN and CRF-based segmentation. Then we estimate and search for the best parts model for each object instance under the principle of preserving as much diversity as possible. In the last stage, we build a bi-directional long short-term memory (LSTM) network to fuze and encode the partial information of these complementary parts into a comprehensive feature for image classification. Experimental results indicate that the proposed method not only achieves significant improvement over our baseline models, but also outperforms state-of-the-art algorithms by a large margin (6.7%, 2.8%, 5.2% respectively) on Stanford Dogs 120, Caltech-UCSD Birds 2011-200 and Caltech 256.

Similar Papers
  • Research Article
  • Citations103

Maxout neurons for deep convolutional and LSTM neural networks in speech recognition

  • Dec 17, 2015
  • Speech Communication
  • Meng Cai +1
  • Book Chapter
  • Citations1

Analysis of Influential Features with Spectral Features for Modeling Dialectal Variation in Malayalam Speech Using Deep Neural Networks

  • Jan 01, 2023
  • Rizwana Kallooravi Thandil +1
  • Conference Article
  • Citations34

Diabetic Retinopathy Detection Based on Deep Convolutional Neural Networks for Localization of Discriminative Regions

  • Oct 01, 2018
  • Pan Junjun +3
  • Conference Article
  • Citations1

DEEP LEARNING FRAMEWORK FOR WOVEN COMPOSITE ANALYSIS

  • Sep 20, 2021
  • Haotian Feng +2
  • PDF
  • Research Article
  • Citations26

Crop Organ Segmentation and Disease Identification Based on Weakly Supervised Deep Neural Network

  • Nov 10, 2019
  • Agronomy
  • Yang Wu +1
  • Research Article
  • Citations19

Mitigation of SOA-Induced Nonlinearity With the Aid of Deep Learning Neural Networks

  • Feb 15, 2022
  • Journal of Lightwave Technology
  • Kaihui Wang +4
  • Research Article
  • Citations38

Trajectory-level fog detection based on in-vehicle video camera with TensorFlow deep learning utilizing SHRP2 naturalistic driving data

  • May 11, 2020
  • Accident Analysis & Prevention
  • Md Nasim Khan +1
  • Research Article
  • Citations4

A convolutional-LSTM model for nitrogen oxide emission forecasting in FCC unit

  • Jan 01, 2020
  • Journal of Intelligent & Fuzzy Systems
  • Beng Wu +4
  • Research Article
  • Citations7

SAR Target Detection Network via Semi-supervised Learning

  • Jan 21, 2020
  • 电子与信息学报
  • Lan Du +3
  • PDF
  • Research Article
  • Citations16

Instance Segmentation Based on Deep Convolutional Neural Networks and Transfer Learning for Unconstrained Psoriasis Skin Images

  • Apr 01, 2021
  • Applied Sciences
  • Guo-Shiang Lin +4
  • PDF
  • Research Article
  • Citations73

Evaluation of Deep Learning Architectures for Complex Immunofluorescence Nuclear Image Segmentation.

  • Mar 30, 2021
  • IEEE transactions on medical imaging
  • Florian Kromp +8
  • Conference Article

Absolute distance measurement based on laser self-mixing interferometry and deep neural network

  • Dec 27, 2022
  • Jinyuan Yuan +2
  • Book Chapter
  • Citations1

Handwritten Digit Recognition Using Very Deep Convolutional Neural Network

  • Jan 01, 2022
  • M Dhilsath Fathima +2
  • Research Article
  • Citations96

Anomaly detection in ad-hoc networks based on deep learning model: A plug and play device

  • Sep 25, 2018
  • Ad Hoc Networks
  • Fang Feng +4
  • Conference Article
  • Citations4

Hybrid Deep Learning for Channel Estimation and Power Allocation for MISO-NOMA System

  • Oct 01, 2022
  • Mohamed Gaballa +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.