# Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image Classification

arXiv: https://arxiv.org/abs/2209.06585 · HTML: https://mlsanity.com/paper/2209.06585/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 14 Sep 2022.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Bag of Tricks for Image Classification with Convolutional Neural Networks](https://mlsanity.com/paper/1812.01187/) (2018)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay](https://mlsanity.com/paper/1803.09820/) (2018)
- [Query2Label: A Simple Transformer Way to Multi-Label Classification](https://mlsanity.com/paper/2107.10834/) (2021)
- [General Multi-label Image Classification with Transformers](https://mlsanity.com/paper/2011.14027/) (2020)
- [TResNet: High Performance GPU-Dedicated Architecture](https://mlsanity.com/paper/2003.13630/) (2020)
- [Multi-label Image Recognition by Recurrently Discovering Attentional Regions](https://mlsanity.com/paper/1711.02816/) (2017)
- [ML-Decoder: Scalable and Versatile Classification Head](https://mlsanity.com/paper/2111.12933/) (2021)
- [Residual Attention: A Simple but Effective Method for Multi-Label Recognition](https://mlsanity.com/paper/2108.02456/) (2021)
- [Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition](https://mlsanity.com/paper/2007.01755/) (2020)
- [SphereFace2: Binary Classification is All You Need for Deep Face Recognition](https://mlsanity.com/paper/2108.01513/) (2021)
- [Graph Attention Transformer Network for Multi-Label Image Classification](https://mlsanity.com/paper/2203.04049/) (2022)
- [Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning](https://mlsanity.com/paper/2003.07618/) (2020)
- [Language Models with Pre-Trained (GloVe) Word Embeddings](https://mlsanity.com/paper/1610.03759/) (2016)
- [Towards Efficient and Data Agnostic Image Classification Training Pipeline for Embedded Systems](https://mlsanity.com/paper/2108.07049/) (2021)

## Built on by (most cited first, 4 of 4)

- [Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning](https://mlsanity.com/paper/2305.02795/) (2023)
- [Towards Activated Muscle Group Estimation in the Wild](https://mlsanity.com/paper/2303.00952/) (2023)
- [Learning Object Focused Attention](https://mlsanity.com/paper/2504.08166/) (2025)
- [Supervised Multilabel Image Classification Using Residual Networks with Probabilistic Reasoning](https://mlsanity.com/paper/2511.12082/) (2025)

## Abstract (arXiv)

Multi-label image classification allows predicting a set of labels from a given image. Unlike multiclass classification, where only one label per image is assigned, such a setup is applicable for a broader range of applications. In this work we revisit two popular approaches to multilabel classification: transformer-based heads and labels relations information graph processing branches. Although transformer-based heads are considered to achieve better results than graph-based branches, we argue that with the proper training strategy, graph-based methods can demonstrate just a small accuracy drop, while spending less computational resources on inference. In our training strategy, instead of Asymmetric Loss (ASL), which is the de-facto standard for multilabel classification, we introduce its metric learning modification. In each binary classification sub-problem it operates with L2 normalized feature vectors coming from a backbone and enforces angles between the normalized representations of positive and negative samples to be as large as possible. This results in providing a better discrimination ability, than binary cross entropy loss does on unnormalized features. With the proposed loss and training strategy, we obtain SOTA results among single modality methods on widespread multilabel classification benchmarks such as MS-COCO, PASCAL-VOC, NUS-Wide and Visual Genome 500. Source code of our method is available as a part of the OpenVINO Training Extensions https://github.com/openvinotoolkit/deep-object-reid/tree/multilabel