# Data-Efficient Generalization for Zero-shot Composed Image Retrieval

arXiv: https://arxiv.org/abs/2503.05204 · HTML: https://mlsanity.com/paper/2503.05204/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 49 of its 64 references that are in the map.
- First posted on arXiv 7 Mar 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 30 of 49)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [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)
- [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)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [SWAD: Domain Generalization by Seeking Flat Minima](https://mlsanity.com/paper/2102.08604/) (2021)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [A Fourier-based Framework for Domain Generalization](https://mlsanity.com/paper/2105.11120/) (2021)
- [Generalizing Across Domains via Cross-Gradient Training](https://mlsanity.com/paper/1804.10745/) (2018)
- [Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models](https://mlsanity.com/paper/2108.04024/) (2021)
- [Composing Text and Image for Image Retrieval - An Empirical Odyssey](https://mlsanity.com/paper/1812.07119/) (2018)
- [Zero-Shot Composed Image Retrieval with Textual Inversion](https://mlsanity.com/paper/2303.15247/) (2023)
- [Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval](https://mlsanity.com/paper/2302.03084/) (2023)
- [Finetune like you pretrain: Improved finetuning of zero-shot vision models](https://mlsanity.com/paper/2212.00638/) (2022)
- [Causality Inspired Representation Learning for Domain Generalization](https://mlsanity.com/paper/2203.14237/) (2022)
- [Domain Generalization by Mutual-Information Regularization with Pre-trained Models](https://mlsanity.com/paper/2203.10789/) (2022)
- [MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions](https://mlsanity.com/paper/2403.19651/) (2024)
- [ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference](https://mlsanity.com/paper/2407.12442/) (2024)
- [Vision-by-Language for Training-Free Compositional Image Retrieval](https://mlsanity.com/paper/2310.09291/) (2023)
- [CLIPood: Generalizing CLIP to Out-of-Distributions](https://mlsanity.com/paper/2302.00864/) (2023)

## Built on by (most cited first, 2 of 2)

- [Thinking Before Retrieving: Robust Zero-Shot Composed Image Retrieval via Strategic Planning and Self-Criticism](https://mlsanity.com/paper/2606.31222/) (2026)
- [From Transformation to Target State: Rethinking Query Representation for Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2610.05993/) (2026)

## Abstract (arXiv)

Zero-shot Composed Image Retrieval (ZS-CIR) aims to retrieve the target image based on a reference image and a text description without requiring in-distribution triplets for training. One prevalent approach follows the vision-language pretraining paradigm that employs a mapping network to transfer the image embedding to a pseudo-word token in the text embedding space. However, this approach tends to impede network generalization due to modality discrepancy and distribution shift between training and inference. To this end, we propose a Data-efficient Generalization (DeG) framework, including two novel designs, namely, Textual Supplement (TS) module and Semantic-Set (S-Set). The TS module exploits compositional textual semantics during training, enhancing the pseudo-word token with more linguistic semantics and thus mitigating the modality discrepancy effectively. The S-Set exploits the zero-shot capability of pretrained Vision-Language Models (VLMs), alleviating the distribution shift and mitigating the overfitting issue from the redundancy of the large-scale image-text data. Extensive experiments over four ZS-CIR benchmarks show that DeG outperforms the state-of-the-art (SOTA) methods with much less training data, and saves substantial training and inference time for practical usage.