mlsanityData to 7 Oct 2026

A patch-based architecture for multi-label classification from single label annotations

arXiv 2209.06530 ↗First posted 14 Sep 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a patch-based architecture for multi-label classification problems where only a single positive label is observed in images of the dataset. Our contributions are twofold. First, we introduce a light patch architecture based on the attention mechanism. Next, leveraging on patch embedding self-similarities, we provide a novel strategy for estimating negative examples and deal with positive and unlabeled learning problems. Experiments demonstrate that our architecture can be trained from scratch, whereas pre-training on similar databases is required for related methods from the literature.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 37 references that are in the map. First posted on arXiv 14 Sep 2022.

Builds on

27 of 37 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2017Mask R-CNNcited by 7,259
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  7. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  9. 2017Deep Setscited by 1,394
  10. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  11. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  12. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
15 more
  1. 2019Large Batch Optimization for Deep Learning: Training BERT in 76 minutescited by 671
  2. 2013Network In Networkcited by 600
  3. 2021Early Convolutions Help Transformers See Bettercited by 395
  4. 2018Learning from positive and unlabeled data: a surveycited by 218
  5. 2022Patches Are All You Need?cited by 201
  6. 2016Multiple Instance Learning: A Survey of Problem Characteristics and Applicationscited by 163
  7. 2020General Multi-label Image Classification with Transformerscited by 126
  8. 2019Presence-Only Geographical Priors for Fine-Grained Image Classificationcited by 109
  9. 2020Feature Pyramid Transformercited by 94
  10. 2017Learning from Complementary Labelscited by 88
  11. 2021Multi-Label Learning from Single Positive Labelscited by 81
  12. 2018From BoW to CNN: Two Decades of Texture Representation for Texture Classificationcited by 39
  13. 2022Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotationscited by 17
  14. 2022CodedVTR: Codebook-based Sparse Voxel Transformer with Geometric Guidancecited by 7
  15. 2017Nonconvex penalties with analytical solutions for one-bit compressive sensingcited by 1

Built on by

Not cited yet.