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

arXiv: https://arxiv.org/abs/2209.06530 · HTML: https://mlsanity.com/paper/2209.06530/

## Key facts

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

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Large Batch Optimization for Deep Learning: Training BERT in 76 minutes](https://mlsanity.com/paper/1904.00962/) (2019)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [Early Convolutions Help Transformers See Better](https://mlsanity.com/paper/2106.14881/) (2021)
- [Learning from positive and unlabeled data: a survey](https://mlsanity.com/paper/1811.04820/) (2018)
- [Patches Are All You Need?](https://mlsanity.com/paper/2201.09792/) (2022)
- [Multiple Instance Learning: A Survey of Problem Characteristics and Applications](https://mlsanity.com/paper/1612.03365/) (2016)
- [General Multi-label Image Classification with Transformers](https://mlsanity.com/paper/2011.14027/) (2020)
- [Presence-Only Geographical Priors for Fine-Grained Image Classification](https://mlsanity.com/paper/1906.05272/) (2019)
- [Feature Pyramid Transformer](https://mlsanity.com/paper/2007.09451/) (2020)
- [Learning from Complementary Labels](https://mlsanity.com/paper/1705.07541/) (2017)
- [Multi-Label Learning from Single Positive Labels](https://mlsanity.com/paper/2106.09708/) (2021)
- [From BoW to CNN: Two Decades of Texture Representation for Texture Classification](https://mlsanity.com/paper/1801.10324/) (2018)
- [Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations](https://mlsanity.com/paper/2203.06127/) (2022)
- [CodedVTR: Codebook-based Sparse Voxel Transformer with Geometric Guidance](https://mlsanity.com/paper/2203.09887/) (2022)
- [Nonconvex penalties with analytical solutions for one-bit compressive sensing](https://mlsanity.com/paper/1706.01014/) (2017)

## 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.