mlsanityData to 7 Oct 2026

Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images

arXiv 1612.06341 ↗First posted 19 Dec 2016cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

Distinguishing subtle differences in attributes is valuable, yet learning to make visual comparisons remains non-trivial. Not only is the number of possible comparisons quadratic in the number of training images, but also access to images adequately spanning the space of fine-grained visual differences is limited. We propose to overcome the sparsity of supervision problem via synthetically generated images. Building on a state-of-the-art image generation engine, we sample pairs of training images exhibiting slight modifications of individual attributes. Augmenting real training image pairs with these examples, we then train attribute ranking models to predict the relative strength of an attribute in novel pairs of real images. Our results on datasets of faces and fashion images show the great promise of bootstrapping imperfect image generators to counteract sample sparsity for learning to rank.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 13; 2022: 14; 2023: 9; 2024: 3; 2025: 4; 2026: 1.

45 papers.

Sort:

By area:

  1. 2021GAN Inversion: A Surveycited by 366
  2. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  3. 2021Open World Compositional Zero-Shot Learningcited by 100
  4. 2021Learning Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 49
  5. 2022KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learningcited by 41
  6. 2022Proactive Image Manipulation Detectioncited by 35
  7. 2023Learning Conditional Attributes for Compositional Zero-Shot Learningcited by 28
  8. 2022FHIST: A Benchmark for Few-shot Classification of Histological Imagescited by 20
  9. 2022Learning Attention Propagation for Compositional Zero-Shot Learningcited by 20
  10. 2021Free-form tumor synthesis in computed tomography images via richer generative adversarial networkcited by 16
  11. 2021Zero-Shot Compositional Concept Learningcited by 16
  12. 2024A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practicescited by 15
33 more
  1. 2022On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 13
  2. 2023Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learningcited by 11
  3. 2021Deep Image Synthesis from Intuitive User Input: A Review and Perspectivescited by 8
  4. 2021Learning Single/Multi-Attribute of Object with Symmetry and Groupcited by 8
  5. 2023CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learningcited by 7
  6. 2025A Survey on Large Language Models in Multimodal Recommender Systemscited by 7
  7. 2021Contextualizing Meta-Learning via Learning to Decomposecited by 5
  8. 2022Training and challenging models for text-guided fashion image retrievalcited by 5
  9. 2021Smart Fashion: A Review of AI Applications in the Fashion & Apparel Industrycited by 4
  10. 2021Lifelong Generative Modelling Using Dynamic Expansion Graph Modelcited by 4
  11. 2022Identifying Ambiguous Similarity Conditions via Semantic Matchingcited by 4
  12. 2018Give me a hint! Navigating Image Databases using Human-in-the-loop Feedbackcited by 3
  13. 2022LOCL: Learning Object-Attribute Composition using Localizationcited by 3
  14. 2022Mutual Balancing in State-Object Components for Compositional Zero-Shot Learningcited by 3
  15. 2022Multi-Attribute Open Set Recognitioncited by 2
  16. 2022Deception for Cyber Defence: Challenges and Opportunitiescited by 2
  17. 2023Multi-Similarity Contrastive Learningcited by 2
  18. 2021Directly Training Joint Energy-Based Models for Conditional Synthesis and Calibrated Prediction of Multi-Attribute Datacited by 1
  19. 2022Variational Transfer Learning using Cross-Domain Latent Modulationcited by 1
  20. 2022Instance-level Heterogeneous Domain Adaptation for Limited-labeled Sketch-to-Photo Retrievalcited by 1
  21. 2023An Extensible Multimodal Multi-task Object Dataset with Materialscited by 1
  22. 2023Recognizing Unseen States of Unknown Objects by Leveraging Knowledge Graphscited by 1
  23. 2023Unsupervised Landmark Discovery Using Consistency Guided Bottleneckcited by 1
  24. 2024Compositional Zero-Shot Learning with Contextualized Cues and Adaptive Contrastive Trainingcited by 1
  25. 2021Domain Adaptation for Learning Generator from Paired Few-Shot Datacited by 0
  26. 2022Simple Primitives with Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-shot Learningcited by 0
  27. 2023Fashionpedia-Taste: A Dataset towards Explaining Human Fashion Tastecited by 0
  28. 2023Fashionpedia-Ads: Do Your Favorite Advertisements Reveal Your Fashion Taste?cited by 0
  29. 2024Attention Based Simple Primitives for Open World Compositional Zero-Shot Learningcited by 0
  30. 2025Feasibility with Language Models for Open-World Compositional Zero-Shot Learningcited by 0
  31. 2025Generative Adversarial Networks Applied for Privacy Preservation in Biometric-Based Authentication and Identificationcited by 0
  32. 2025Embedding the Teacher: Distilling vLLM Preferences for Scalable Image Retrievalcited by 0
  33. 2026Stitching and dimensionality effects on large artificially generated volume datasetscited by 0