# The Impact of the Single-Label Assumption in Image Recognition Benchmarking

arXiv: https://arxiv.org/abs/2412.18409 · HTML: https://mlsanity.com/paper/2412.18409/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 44 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks](https://mlsanity.com/paper/2103.14749/) (2021)
- [Are we done with ImageNet?](https://mlsanity.com/paper/2006.07159/) (2020)
- [BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers](https://mlsanity.com/paper/2208.06366/) (2022)
- [VOLO: Vision Outlooker for Visual Recognition](https://mlsanity.com/paper/2106.13112/) (2021)
- [All Tokens Matter: Token Labeling for Training Better Vision Transformers](https://mlsanity.com/paper/2104.10858/) (2021)
- [Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels](https://mlsanity.com/paper/2101.05022/) (2021)
- [Revisiting Weakly Supervised Pre-Training of Visual Perception Models](https://mlsanity.com/paper/2201.08371/) (2022)
- [From ImageNet to Image Classification: Contextualizing Progress on Benchmarks](https://mlsanity.com/paper/2005.11295/) (2020)
- [Multi-Label Learning from Single Positive Labels](https://mlsanity.com/paper/2106.09708/) (2021)
- [When does dough become a bagel? Analyzing the remaining mistakes on ImageNet](https://mlsanity.com/paper/2205.04596/) (2022)
- [DeepFix: A Fully Convolutional Neural Network for predicting Human Eye Fixations](https://mlsanity.com/paper/1510.02927/) (2015)
- [ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification](https://mlsanity.com/paper/2304.05538/) (2023)
- [Identifying Statistical Bias in Dataset Replication](https://mlsanity.com/paper/2005.09619/) (2020)
- [Bugs in the Data: How ImageNet Misrepresents Biodiversity](https://mlsanity.com/paper/2208.11695/) (2022)
- [End-to-End Saliency Mapping via Probability Distribution Prediction](https://mlsanity.com/paper/1804.01793/) (2018)

## Built on by (most cited first, 1 of 1)

- [Small Vision-Language Models: A Survey on Compact Architectures and Techniques](https://mlsanity.com/paper/2503.10665/) (2025)

## Abstract (arXiv)

Deep neural networks (DNNs) are typically evaluated under the assumption that each image has a single correct label. However, many images in benchmarks like ImageNet contain multiple valid labels, creating a mismatch between evaluation protocols and the actual complexity of visual data. This mismatch can penalize DNNs for predicting correct but unannotated labels, which may partly explain reported accuracy drops, such as the widely cited 11 to 14 percent top-1 accuracy decline on ImageNetV2, a replication test set for ImageNet. This raises the question: do such drops reflect genuine generalization failures or artifacts of restrictive evaluation metrics? We rigorously assess the impact of multi-label characteristics on reported accuracy gaps. To evaluate the multi-label prediction capability (MLPC) of single-label-trained models, we introduce a variable top-k evaluation, where k matches the number of valid labels per image. Applied to 315 ImageNet-trained models, our analyses demonstrate that conventional top-1 accuracy disproportionately penalizes valid but secondary predictions. We also propose Aggregate Subgroup Model Accuracy (ASMA) to better capture multi-label performance across model subgroups. Our results reveal wide variability in MLPC, with some models consistently ranking multiple correct labels higher. Under this evaluation, the perceived gap between ImageNet and ImageNetV2 narrows substantially. To further isolate multi-label recognition performance from contextual cues, we introduce PatchML, a synthetic dataset containing systematically combined object patches. PatchML demonstrates that many models trained with single-label supervision nonetheless recognize multiple objects. Altogether, these findings highlight limitations in single-label evaluation and reveal that modern DNNs have stronger multi-label capabilities than standard metrics suggest.