# Large-Scale Attribute-Object Compositions

arXiv: https://arxiv.org/abs/2105.11373 · HTML: https://mlsanity.com/paper/2105.11373/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 61 references that are in the map.
- First posted on arXiv 24 May 2021.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Learning Visual Features from Large Weakly Supervised Data](https://mlsanity.com/paper/1511.02251/) (2015)
- [Visual Translation Embedding Network for Visual Relation Detection](https://mlsanity.com/paper/1702.08319/) (2017)
- [Learning Visual N-Grams from Web Data](https://mlsanity.com/paper/1612.09161/) (2016)
- [Attribute2Image: Conditional Image Generation from Visual Attributes](https://mlsanity.com/paper/1512.00570/) (2015)
- [Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification](https://mlsanity.com/paper/1611.05377/) (2016)
- [Hard Mixtures of Experts for Large Scale Weakly Supervised Vision](https://mlsanity.com/paper/1704.06363/) (2017)
- [Pedestrian Attribute Recognition: A Survey](https://mlsanity.com/paper/1901.07474/) (2019)
- [Deep Attributes Driven Multi-Camera Person Re-identification](https://mlsanity.com/paper/1605.03259/) (2016)
- [A Large-scale Attribute Dataset for Zero-shot Learning](https://mlsanity.com/paper/1804.04314/) (2018)
- [Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning](https://mlsanity.com/paper/1610.04787/) (2016)
- [Learning the Latent "Look": Unsupervised Discovery of a Style-Coherent Embedding from Fashion Images](https://mlsanity.com/paper/1707.03376/) (2017)
- [Multilinear Latent Conditioning for Generating Unseen Attribute Combinations](https://mlsanity.com/paper/2009.04075/) (2020)
- [End-to-End Localization and Ranking for Relative Attributes](https://mlsanity.com/paper/1608.02676/) (2016)
- [Separating Self-Expression and Visual Content in Hashtag Supervision](https://mlsanity.com/paper/1711.09825/) (2017)
- [Walk and Learn: Facial Attribute Representation Learning from Egocentric Video and Contextual Data](https://mlsanity.com/paper/1604.06433/) (2016)
- [Neural Algebra of Classifiers](https://mlsanity.com/paper/1801.08676/) (2018)
- [Learning to Infer Unseen Single-/Multi-Attribute-Object Compositions with Graph Networks](https://mlsanity.com/paper/2010.14343/) (2020)

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

- [Revisiting Weakly Supervised Pre-Training of Visual Perception Models](https://mlsanity.com/paper/2201.08371/) (2022)
- [Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training](https://mlsanity.com/paper/2301.02280/) (2023)
- [Learning to Compose Soft Prompts for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2204.03574/) (2022)
- [COLA: A Benchmark for Compositional Text-to-image Retrieval](https://mlsanity.com/paper/2305.03689/) (2023)

## Abstract (arXiv)

We study the problem of learning how to predict attribute-object compositions from images, and its generalization to unseen compositions missing from the training data. To the best of our knowledge, this is a first large-scale study of this problem, involving hundreds of thousands of compositions. We train our framework with images from Instagram using hashtags as noisy weak supervision. We make careful design choices for data collection and modeling, in order to handle noisy annotations and unseen compositions. Finally, extensive evaluations show that learning to compose classifiers outperforms late fusion of individual attribute and object predictions, especially in the case of unseen attribute-object pairs.