# Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images

arXiv: https://arxiv.org/abs/1612.06341 · HTML: https://mlsanity.com/paper/1612.06341/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2016.

## Built on by (most cited first, 30 of 45)

- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [Learning Graph Embeddings for Compositional Zero-shot Learning](https://mlsanity.com/paper/2102.01987/) (2021)
- [Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2101.12609/) (2021)
- [Learning Graph Embeddings for Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2105.01017/) (2021)
- [KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2205.06784/) (2022)
- [Proactive Image Manipulation Detection](https://mlsanity.com/paper/2203.15880/) (2022)
- [Learning Conditional Attributes for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.17940/) (2023)
- [FHIST: A Benchmark for Few-shot Classification of Histological Images](https://mlsanity.com/paper/2206.00092/) (2022)
- [Learning Attention Propagation for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2210.11557/) (2022)
- [Free-form tumor synthesis in computed tomography images via richer generative adversarial network](https://mlsanity.com/paper/2104.09701/) (2021)
- [Zero-Shot Compositional Concept Learning](https://mlsanity.com/paper/2107.05176/) (2021)
- [A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices](https://mlsanity.com/paper/2406.08787/) (2024)
- [On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2204.11848/) (2022)
- [Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learning](https://mlsanity.com/paper/2303.00404/) (2023)
- [Deep Image Synthesis from Intuitive User Input: A Review and Perspectives](https://mlsanity.com/paper/2107.04240/) (2021)
- [Learning Single/Multi-Attribute of Object with Symmetry and Group](https://mlsanity.com/paper/2110.04603/) (2021)
- [CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.16681/) (2023)
- [A Survey on Large Language Models in Multimodal Recommender Systems](https://mlsanity.com/paper/2505.09777/) (2025)
- [Contextualizing Meta-Learning via Learning to Decompose](https://mlsanity.com/paper/2106.08112/) (2021)
- [Training and challenging models for text-guided fashion image retrieval](https://mlsanity.com/paper/2204.11004/) (2022)
- [Smart Fashion: A Review of AI Applications in the Fashion & Apparel Industry](https://mlsanity.com/paper/2111.00905/) (2021)
- [Lifelong Generative Modelling Using Dynamic Expansion Graph Model](https://mlsanity.com/paper/2112.08370/) (2021)
- [Identifying Ambiguous Similarity Conditions via Semantic Matching](https://mlsanity.com/paper/2204.04053/) (2022)
- [Give me a hint! Navigating Image Databases using Human-in-the-loop Feedback](https://mlsanity.com/paper/1809.08714/) (2018)
- [LOCL: Learning Object-Attribute Composition using Localization](https://mlsanity.com/paper/2210.03780/) (2022)
- [Mutual Balancing in State-Object Components for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2211.10647/) (2022)
- [Multi-Attribute Open Set Recognition](https://mlsanity.com/paper/2208.06809/) (2022)
- [Deception for Cyber Defence: Challenges and Opportunities](https://mlsanity.com/paper/2208.07127/) (2022)
- [Multi-Similarity Contrastive Learning](https://mlsanity.com/paper/2307.02712/) (2023)
- [Directly Training Joint Energy-Based Models for Conditional Synthesis and Calibrated Prediction of Multi-Attribute Data](https://mlsanity.com/paper/2108.04227/) (2021)

## 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.