# Modality and Task Adaptation for Enhanced Zero-shot Composed Image Retrieval

arXiv: https://arxiv.org/abs/2410.23736 · HTML: https://mlsanity.com/paper/2410.23736/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 31 Oct 2024.

## Placed in

- Mixture-of-experts / [Multimodal MoE models](https://mlsanity.com/moe/multimodal-moe-models/)

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [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)
- [Vision-by-Language for Training-Free Compositional Image Retrieval](https://mlsanity.com/paper/2310.09291/) (2023)
- ["This is my unicorn, Fluffy": Personalizing frozen vision-language representations](https://mlsanity.com/paper/2204.01694/) (2022)
- [CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion](https://mlsanity.com/paper/2303.11916/) (2023)
- [Sentence-level Prompts Benefit Composed Image Retrieval](https://mlsanity.com/paper/2310.05473/) (2023)
- [Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2309.16137/) (2023)
- [GeneCIS: A Benchmark for General Conditional Image Similarity](https://mlsanity.com/paper/2306.07969/) (2023)
- [Data Roaming and Quality Assessment for Composed Image Retrieval](https://mlsanity.com/paper/2303.09429/) (2023)
- [Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrieval](https://mlsanity.com/paper/2405.00571/) (2024)
- [Bi-directional Training for Composed Image Retrieval via Text Prompt Learning](https://mlsanity.com/paper/2303.16604/) (2023)
- [Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval](https://mlsanity.com/paper/2403.16005/) (2024)

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

- [Composed Multi-modal Retrieval: A Survey of Approaches and Applications](https://mlsanity.com/paper/2503.01334/) (2025)
- [Preserve-and-Compose Training for Composed Image Retrieval](https://mlsanity.com/paper/2609.31202/) (2026)

## Abstract (arXiv)

As a challenging vision-language task, Zero-Shot Composed Image Retrieval (ZS-CIR) is designed to retrieve target images using bi-modal (image+text) queries. Typical ZS-CIR methods employ an inversion network to generate pseudo-word tokens that effectively represent the input semantics. However, the inversion-based methods suffer from two inherent issues: First, the task discrepancy exists because inversion training and CIR inference involve different objectives. Second, the modality discrepancy arises from the input feature distribution mismatch between training and inference. To this end, we propose a lightweight post-hoc framework, consisting of two components: (1) A new text-anchored triplet construction pipeline leverages a large language model (LLM) to transform a standard image-text dataset into a triplet dataset, where a textual description serves as the target of each triplet. (2) The MoTa-Adapter, a novel parameter-efficient fine-tuning method, adapts the dual encoder to the CIR task using our constructed triplet data. Specifically, on the text side, multiple sets of learnable task prompts are integrated via a Mixture-of-Experts (MoE) layer to capture task-specific priors and handle different types of modifications. On the image side, MoTa-Adapter modulates the inversion network's input to better match the downstream text encoder. In addition, an entropy-based optimization strategy is proposed to assign greater weight to challenging samples, thus ensuring efficient adaptation. Experiments show that, with the incorporation of our proposed components, inversion-based methods achieve significant improvements, reaching state-of-the-art performance across four widely-used benchmarks. All data and code will be made publicly available.