# Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations

arXiv: https://arxiv.org/abs/2203.06127 · HTML: https://mlsanity.com/paper/2203.06127/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 71 references that are in the map.
- First posted on arXiv 11 Mar 2022.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Self-Supervised Learning of Pretext-Invariant Representations](https://mlsanity.com/paper/1912.01991/) (2019)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [ResNet strikes back: An improved training procedure in timm](https://mlsanity.com/paper/2110.00476/) (2021)
- [Are we done with ImageNet?](https://mlsanity.com/paper/2006.07159/) (2020)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [Semi-Supervised Learning with Ladder Networks](https://mlsanity.com/paper/1507.02672/) (2015)
- [Learning from positive and unlabeled data: a survey](https://mlsanity.com/paper/1811.04820/) (2018)

## Built on by (most cited first, 17 of 17)

- [Spatial Implicit Neural Representations for Global-Scale Species Mapping](https://mlsanity.com/paper/2306.02564/) (2023)
- [Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning](https://mlsanity.com/paper/2305.02795/) (2023)
- [GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learning](https://mlsanity.com/paper/2309.00923/) (2023)
- [Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training](https://mlsanity.com/paper/2404.06287/) (2024)
- [Dual-Perspective Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels](https://mlsanity.com/paper/2205.13092/) (2022)
- [Boosting Single Positive Multi-label Classification with Generalized Robust Loss](https://mlsanity.com/paper/2405.03501/) (2024)
- [Understanding Label Bias in Single Positive Multi-Label Learning](https://mlsanity.com/paper/2305.15584/) (2023)
- [Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification](https://mlsanity.com/paper/2503.16873/) (2025)
- [An Action Is Worth Multiple Words: Handling Ambiguity in Action Recognition](https://mlsanity.com/paper/2210.04933/) (2022)
- [Towards Diverse Temporal Grounding under Single Positive Labels](https://mlsanity.com/paper/2303.06545/) (2023)
- [Labeled-to-Unlabeled Distribution Alignment for Partially-Supervised Multi-Organ Medical Image Segmentation](https://mlsanity.com/paper/2409.03228/) (2024)
- [The Impact of the Single-Label Assumption in Image Recognition Benchmarking](https://mlsanity.com/paper/2412.18409/) (2024)
- [RS-MTDF: Multi-Teacher Distillation and Fusion for Remote Sensing Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2506.08772/) (2025)
- [Merlin L48 Spectrogram Dataset](https://mlsanity.com/paper/2511.00252/) (2025)
- [A patch-based architecture for multi-label classification from single label annotations](https://mlsanity.com/paper/2209.06530/) (2022)
- [Pseudo Labels for Single Positive Multi-Label Learning](https://mlsanity.com/paper/2306.01034/) (2023)
- [Unlocking ImageNet's Multi-Object Nature: Automated Large-Scale Multilabel Annotation](https://mlsanity.com/paper/2603.05729/) (2026)

## Abstract (arXiv)

As natural images usually contain multiple objects, multi-label image classification is more applicable "in the wild" than single-label classification. However, exhaustively annotating images with every object of interest is costly and time-consuming. We aim to train multi-label classifiers from single-label annotations only. We show that adding a consistency loss, ensuring that the predictions of the network are consistent over consecutive training epochs, is a simple yet effective method to train multi-label classifiers in a weakly supervised setting. We further extend this approach spatially, by ensuring consistency of the spatial feature maps produced over consecutive training epochs, maintaining per-class running-average heatmaps for each training image. We show that this spatial consistency loss further improves the multi-label mAP of the classifiers. In addition, we show that this method overcomes shortcomings of the "crop" data-augmentation by recovering correct supervision signal even when most of the single ground truth object is cropped out of the input image by the data augmentation. We demonstrate gains of the consistency and spatial consistency losses over the binary cross-entropy baseline, and over competing methods, on MS-COCO and Pascal VOC. We also demonstrate improved multi-label classification mAP on ImageNet-1K using the ReaL multi-label validation set.