# Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models

arXiv: https://arxiv.org/abs/2305.19595 · HTML: https://mlsanity.com/paper/2305.19595/

## Key facts

- Cited by 72 papers in the map (data through 14 Oct 2026).
- Builds on 69 of its 87 references that are in the map.
- First posted on arXiv 31 May 2023.

## Builds on (most cited first, 30 of 69)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)

## Built on by (most cited first, 30 of 72)

- [DOCCI: Descriptions of Connected and Contrasting Images](https://mlsanity.com/paper/2404.19753/) (2024)
- [Foundational Models Defining a New Era in Vision: A Survey and Outlook](https://mlsanity.com/paper/2307.13721/) (2023)
- [A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions](https://mlsanity.com/paper/2312.08578/) (2023)
- [TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives](https://mlsanity.com/paper/2411.02545/) (2024)
- [ImageInWords: Unlocking Hyper-Detailed Image Descriptions](https://mlsanity.com/paper/2405.02793/) (2024)
- [Revisiting the Role of Language Priors in Vision-Language Models](https://mlsanity.com/paper/2306.01879/) (2023)
- [Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding](https://mlsanity.com/paper/2306.08832/) (2023)
- [MoAI: Mixture of All Intelligence for Large Language and Vision Models](https://mlsanity.com/paper/2403.07508/) (2024)
- [CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples](https://mlsanity.com/paper/2402.13254/) (2024)
- [Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining](https://mlsanity.com/paper/2311.03964/) (2023)
- [Towards Multimodal In-Context Learning for Vision & Language Models](https://mlsanity.com/paper/2403.12736/) (2024)
- [VisMin: Visual Minimal-Change Understanding](https://mlsanity.com/paper/2407.16772/) (2024)
- [VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation](https://mlsanity.com/paper/2502.12782/) (2025)
- [The Hard Positive Truth about Vision-Language Compositionality](https://mlsanity.com/paper/2409.17958/) (2024)
- [Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences](https://mlsanity.com/paper/2506.02095/) (2025)
- [Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions](https://mlsanity.com/paper/2311.17048/) (2023)
- [ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs](https://mlsanity.com/paper/2406.08164/) (2024)
- [CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding](https://mlsanity.com/paper/2311.03354/) (2023)
- [UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks](https://mlsanity.com/paper/2507.11336/) (2025)
- [Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality](https://mlsanity.com/paper/2410.05210/) (2024)
- [Hyperbolic Learning with Synthetic Captions for Open-World Detection](https://mlsanity.com/paper/2404.05016/) (2024)
- [Object-centric Binding in Contrastive Language-Image Pretraining](https://mlsanity.com/paper/2502.14113/) (2025)
- [Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data](https://mlsanity.com/paper/2503.01167/) (2025)
- [TTRV: Test-Time Reinforcement Learning for Vision Language Models](https://mlsanity.com/paper/2510.06783/) (2025)
- [Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models](https://mlsanity.com/paper/2310.08577/) (2023)
- [Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning](https://mlsanity.com/paper/2405.13326/) (2024)
- [Unified Lexical Representation for Interpretable Visual-Language Alignment](https://mlsanity.com/paper/2407.17827/) (2024)
- [Decoupled Global-Local Alignment for Improving Compositional Understanding](https://mlsanity.com/paper/2504.16801/) (2025)
- [Removing Distributional Discrepancies in Captions Improves Image-Text Alignment](https://mlsanity.com/paper/2410.00905/) (2024)
- [Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions](https://mlsanity.com/paper/2407.06723/) (2024)

## Abstract (arXiv)

Vision and Language (VL) models offer an effective method for aligning representation spaces of images and text, leading to numerous applications such as cross-modal retrieval, visual question answering, captioning, and more. However, the aligned image-text spaces learned by all the popular VL models are still suffering from the so-called `object bias' - their representations behave as `bags of nouns', mostly ignoring or downsizing the attributes, relations, and states of objects described/appearing in texts/images. Although some great attempts at fixing these `compositional reasoning' issues were proposed in the recent literature, the problem is still far from being solved. In this paper, we uncover two factors limiting the VL models' compositional reasoning performance. These two factors are properties of the paired VL dataset used for finetuning and pre-training the VL model: (i) the caption quality, or in other words `image-alignment', of the texts; and (ii) the `density' of the captions in the sense of mentioning all the details appearing on the image. We propose a fine-tuning approach for automatically treating these factors leveraging a standard VL dataset (CC3M). Applied to CLIP, we demonstrate its significant compositional reasoning performance increase of up to ~27% over the base model, up to ~20% over the strongest baseline, and by 6.7% on average.