# Improving Pairwise Ranking for Multi-label Image Classification

arXiv: https://arxiv.org/abs/1704.03135 · HTML: https://mlsanity.com/paper/1704.03135/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2017.

## Built on by (most cited first, 30 of 40)

- [Learning to Predict Visual Attributes in the Wild](https://mlsanity.com/paper/2106.09707/) (2021)
- [Don't Forget to Connect! Improving RAG with Graph-based Reranking](https://mlsanity.com/paper/2405.18414/) (2024)
- [Rank-based Decomposable Losses in Machine Learning: A Survey](https://mlsanity.com/paper/2207.08768/) (2022)
- [Sum of Ranked Range Loss for Supervised Learning](https://mlsanity.com/paper/2106.03300/) (2021)
- [sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification](https://mlsanity.com/paper/2108.10566/) (2021)
- [Meta-Learning for Multi-Label Few-Shot Classification](https://mlsanity.com/paper/2110.13494/) (2021)
- [Deep Learning for Multi-Label Learning: A Comprehensive Survey](https://mlsanity.com/paper/2401.16549/) (2024)
- [Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark](https://mlsanity.com/paper/2103.10895/) (2021)
- [ZLPR: A Novel Loss for Multi-label Classification](https://mlsanity.com/paper/2208.02955/) (2022)
- [Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning](https://mlsanity.com/paper/2305.02795/) (2023)
- [A survey and taxonomy of loss functions in machine learning](https://mlsanity.com/paper/2301.05579/) (2023)
- [Multi-label Cluster Discrimination for Visual Representation Learning](https://mlsanity.com/paper/2407.17331/) (2024)
- [Multi-Label Continual Learning using Augmented Graph Convolutional Network](https://mlsanity.com/paper/2211.14763/) (2022)
- [Siamese Object Tracking for Unmanned Aerial Vehicle: A Review and Comprehensive Analysis](https://mlsanity.com/paper/2205.04281/) (2022)
- [A Unified Positive-Unlabeled Learning Framework for Document-Level Relation Extraction with Different Levels of Labeling](https://mlsanity.com/paper/2210.08709/) (2022)
- [None Class Ranking Loss for Document-Level Relation Extraction](https://mlsanity.com/paper/2205.00476/) (2022)
- [Data-free Multi-label Image Recognition via LLM-powered Prompt Tuning](https://mlsanity.com/paper/2403.01209/) (2024)
- [Rethinking Crowdsourcing Annotation: Partial Annotation with Salient Labels for Multi-Label Image Classification](https://mlsanity.com/paper/2109.02688/) (2021)
- [Dual-Encoders for Extreme Multi-Label Classification](https://mlsanity.com/paper/2310.10636/) (2023)
- [Ranking over Regression for Bayesian Optimization and Molecule Selection](https://mlsanity.com/paper/2410.09290/) (2024)
- [Relation-aware Hierarchical Attention Framework for Video Question Answering](https://mlsanity.com/paper/2105.06160/) (2021)
- [Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution](https://mlsanity.com/paper/2304.06305/) (2023)
- [Label Attention Network for Temporal Sets Prediction: You Were Looking at a Wrong Self-Attention](https://mlsanity.com/paper/2303.00280/) (2023)
- [ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling](https://mlsanity.com/paper/2408.04102/) (2024)
- [Prototypicality Bias Reveals Blindspots in Multimodal Evaluation Metrics](https://mlsanity.com/paper/2601.04946/) (2026)
- [GlideNet: Global, Local and Intrinsic based Dense Embedding NETwork for Multi-category Attributes Prediction](https://mlsanity.com/paper/2203.03079/) (2022)
- [Complementary to Multiple Labels: A Correlation-Aware Correction Approach](https://mlsanity.com/paper/2302.12987/) (2023)
- [AudioFormer: Audio Transformer learns audio feature representations from discrete acoustic codes](https://mlsanity.com/paper/2308.07221/) (2023)
- [Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-Label Classification](https://mlsanity.com/paper/2407.06709/) (2024)
- [Training Dense Retrievers with Multiple Positive Passages](https://mlsanity.com/paper/2602.12727/) (2026)

## Abstract (arXiv)

Learning to rank has recently emerged as an attractive technique to train deep convolutional neural networks for various computer vision tasks. Pairwise ranking, in particular, has been successful in multi-label image classification, achieving state-of-the-art results on various benchmarks. However, most existing approaches use the hinge loss to train their models, which is non-smooth and thus is difficult to optimize especially with deep networks. Furthermore, they employ simple heuristics, such as top-k or thresholding, to determine which labels to include in the output from a ranked list of labels, which limits their use in the real-world setting. In this work, we propose two techniques to improve pairwise ranking based multi-label image classification: (1) we propose a novel loss function for pairwise ranking, which is smooth everywhere and thus is easier to optimize; and (2) we incorporate a label decision module into the model, estimating the optimal confidence thresholds for each visual concept. We provide theoretical analyses of our loss function in the Bayes consistency and risk minimization framework, and show its benefit over existing pairwise ranking formulations. We demonstrate the effectiveness of our approach on three large-scale datasets, VOC2007, NUS-WIDE and MS-COCO, achieving the best reported results in the literature.