mlsanityData to 14 Oct 2026

Large-Scale Attribute-Object Compositions

arXiv 2105.11373 ↗First posted 24 May 2021cs.CVcited by 4

Not on the map. Why?

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.

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

26 of 61 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  6. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  7. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,492
  8. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 919
  9. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 605
  10. 2015Learning Visual Features from Large Weakly Supervised Datacited by 165
  11. 2017Visual Translation Embedding Network for Visual Relation Detectioncited by 112
  12. 2016Learning Visual N-Grams from Web Datacited by 95
14 more
  1. 2015Attribute2Image: Conditional Image Generation from Visual Attributescited by 93
  2. 2016Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classificationcited by 93
  3. 2017Hard Mixtures of Experts for Large Scale Weakly Supervised Visioncited by 67
  4. 2019Pedestrian Attribute Recognition: A Surveycited by 50
  5. 2016Deep Attributes Driven Multi-Camera Person Re-identificationcited by 21
  6. 2018A Large-scale Attribute Dataset for Zero-shot Learningcited by 21
  7. 2016Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learningcited by 20
  8. 2017Learning the Latent "Look": Unsupervised Discovery of a Style-Coherent Embedding from Fashion Imagescited by 19
  9. 2020Multilinear Latent Conditioning for Generating Unseen Attribute Combinationscited by 14
  10. 2016End-to-End Localization and Ranking for Relative Attributescited by 9
  11. 2017Separating Self-Expression and Visual Content in Hashtag Supervisioncited by 9
  12. 2016Walk and Learn: Facial Attribute Representation Learning from Egocentric Video and Contextual Datacited by 7
  13. 2018Neural Algebra of Classifierscited by 7
  14. 2020Learning to Infer Unseen Single-/Multi-Attribute-Object Compositions with Graph Networkscited by 5

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2.

4 papers.

  1. 2022Revisiting Weakly Supervised Pre-Training of Visual Perception Modelscited by 116
  2. 2023Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Trainingcited by 91
  3. 2022Learning to Compose Soft Prompts for Compositional Zero-Shot Learningcited by 67
  4. 2023COLA: A Benchmark for Compositional Text-to-image Retrievalcited by 53