# Contrastive Visual Data Augmentation

arXiv: https://arxiv.org/abs/2502.17709 · HTML: https://mlsanity.com/paper/2502.17709/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 35 of its 47 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?](https://mlsanity.com/paper/2003.11539/) (2020)
- [Dynamic Few-Shot Visual Learning without Forgetting](https://mlsanity.com/paper/1804.09458/) (2018)
- [VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks](https://mlsanity.com/paper/2112.06825/) (2021)
- [A Baseline for Few-Shot Image Classification](https://mlsanity.com/paper/1909.02729/) (2019)
- [SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization](https://mlsanity.com/paper/2006.01791/) (2020)
- [Why are Visually-Grounded Language Models Bad at Image Classification?](https://mlsanity.com/paper/2405.18415/) (2024)
- [Image Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2204.08610/) (2022)
- [ALIP: Adaptive Language-Image Pre-training with Synthetic Caption](https://mlsanity.com/paper/2308.08428/) (2023)
- [MixGen: A New Multi-Modal Data Augmentation](https://mlsanity.com/paper/2206.08358/) (2022)
- [Matching Feature Sets for Few-Shot Image Classification](https://mlsanity.com/paper/2204.00949/) (2022)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [STaDA: Style Transfer as Data Augmentation](https://mlsanity.com/paper/1909.01056/) (2019)
- [Learning Multimodal Data Augmentation in Feature Space](https://mlsanity.com/paper/2212.14453/) (2022)
- [Synth2: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings](https://mlsanity.com/paper/2403.07750/) (2024)
- [Rethinking VLMs and LLMs for Image Classification](https://mlsanity.com/paper/2410.14690/) (2024)
- [Sample-Efficient Learning of Novel Visual Concepts](https://mlsanity.com/paper/2306.09482/) (2023)
- [Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge](https://mlsanity.com/paper/2310.15066/) (2023)

## Built on by (most cited first, 3 of 3)

- [EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation](https://mlsanity.com/paper/2512.24731/) (2025)
- [DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation](https://mlsanity.com/paper/2510.14949/) (2025)
- [Can Synthetic Images Serve as Effective and Efficient Class Prototypes?](https://mlsanity.com/paper/2512.17160/) (2025)

## Abstract (arXiv)

Large multimodal models (LMMs) often struggle to recognize novel concepts, as they rely on pre-trained knowledge and have limited ability to capture subtle visual details. Domain-specific knowledge gaps in training also make them prone to confusing visually similar, commonly misrepresented, or low-resource concepts. To help LMMs better align nuanced visual features with language, improving their ability to recognize and reason about novel or rare concepts, we propose a Contrastive visual Data Augmentation (CoDA) strategy. CoDA extracts key contrastive textual and visual features of target concepts against the known concepts they are misrecognized as, and then uses multimodal generative models to produce targeted synthetic data. Automatic filtering of extracted features and augmented images is implemented to guarantee their quality, as verified by human annotators. We show the effectiveness and efficiency of CoDA on low-resource concept and diverse scene recognition datasets including INaturalist and SUN. We additionally collect NovelSpecies, a benchmark dataset consisting of newly discovered animal species that are guaranteed to be unseen by LMMs. LLaVA-1.6 1-shot updating results on these three datasets show CoDA significantly improves SOTA visual data augmentation strategies by 12.3% (NovelSpecies), 5.1% (SUN), and 6.0% (iNat) absolute gains in accuracy.