• Home
  • Search
  • FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning
  • Cite Icon3
  • https://doi.org/10.1609/aaai.v37i2.25303Copy DOI Icon

FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning

  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

Recently, webly supervised learning (WSL) has been studied to leverage numerous and accessible data from the Internet. Most existing methods focus on learning noise-robust models from web images while neglecting the performance drop caused by the differences between web domain and real-world domain. However, only by tackling the performance gap above can we fully exploit the practical value of web datasets. To this end, we propose a Few-shot guided Prototypical (FoPro) representation learning method, which only needs a few labeled examples from reality and can significantly improve the performance in the real-world domain. Specifically, we initialize each class center with few-shot real-world data as the ``realistic" prototype. Then, the intra-class distance between web instances and ``realistic" prototypes is narrowed by contrastive learning. Finally, we measure image-prototype distance with a learnable metric. Prototypes are polished by adjacent high-quality web images and involved in removing distant out-of-distribution samples. In experiments, FoPro is trained on web datasets with a few real-world examples guided and evaluated on real-world datasets. Our method achieves the state-of-the-art performance on three fine-grained datasets and two large-scale datasets. Compared with existing WSL methods under the same few-shot settings, FoPro still excels in real-world generalization. Code is available at https://github.com/yuleiqin/fopro.

Similar Papers
  • Dissertation

2D and 3D visual understanding with limited supervision

  • Jan 01, 2023
  • Zhonghua Wu
  • Research Article
  • Citations15

Boosting Robust Learning Via Leveraging Reusable Samples in Noisy Web Data

  • Jan 01, 2023
  • IEEE Transactions on Multimedia
  • Zeren Sun +5
  • Conference Article
  • Citations4

CyEvent2vec: Attributed Heterogeneous Information Network based Event Embedding Framework for Cyber Security Events Analysis

  • Jul 18, 2022
  • Xiu Ma +5
  • Conference Article
  • Citations19

Inpatient2Vec: Medical Representation Learning for Inpatients

  • Nov 01, 2019
  • Ying Wang +5
  • Research Article
  • Citations1

Watch and learn: leveraging expert knowledge and language for surgical video understanding.

  • Jul 02, 2025
  • International journal of computer assisted radiology and surgery
  • David Gastager +2
  • Research Article
  • Citations37

Self-supervised learning–based underwater acoustical signal classification via mask modeling

  • Jul 01, 2023
  • The Journal of the Acoustical Society of America
  • Kele Xu +6
  • Research Article
  • Citations14

Dynamic Weighted Combiner for Mixed-Modal Image Retrieval

  • Mar 24, 2024
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Fuxiang Huang +3
  • Book Chapter
  • Citations6

Split Balancing (sBal)—A Data Preprocessing Sampling Technique for Ensemble Methods for Binary Classification in Imbalanced Datasets

  • Jan 01, 2021
  • Chongomweru Halimu +1
  • Research Article
  • Citations1

Trajectory Representation Learning on Grids and Road Networks with Spatio-Temporal Dynamics

  • Aug 07, 2025
  • ACM Transactions on Intelligent Systems and Technology
  • Stefan Schestakov +1
  • Research Article
  • Citations66

Web-Supervised Network with Softly Update-Drop Training for Fine-Grained Visual Classification

  • Apr 03, 2020
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Chuanyi Zhang +8
  • Research Article
  • Citations8

Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction

  • Jun 28, 2022
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Ta-Ying Cheng +4
  • Research Article
  • Citations124

Deep CNNs With Spatially Weighted Pooling for Fine-Grained Car Recognition

  • Nov 01, 2017
  • IEEE Transactions on Intelligent Transportation Systems
  • Qichang Hu +3
  • Book Chapter
  • Citations3

An Online Competence-Based Concept Drift Detection Algorithm

  • Jan 01, 2016
  • Anjin Liu +4
  • Research Article
  • Citations2

Mutual calibration training: Training deep neural networks with noisy labels using dual-models

  • Sep 13, 2021
  • Computer Vision and Image Understanding
  • Rui Liu +3
  • Research Article
  • Citations12

Tolerant Self-Distillation for image classification

  • Feb 28, 2024
  • Neural Networks
  • Mushui Liu +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.