# SAC: Semantic Attention Composition for Text-Conditioned Image Retrieval

arXiv: https://arxiv.org/abs/2009.01485 · HTML: https://mlsanity.com/paper/2009.01485/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2020.

## Built on by (most cited first, 23 of 23)

- [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)
- [Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features](https://mlsanity.com/paper/2308.11485/) (2023)
- [CoVR-2: Automatic Data Construction for Composed Video Retrieval](https://mlsanity.com/paper/2308.14746/) (2023)
- [Data Roaming and Quality Assessment for Composed Image Retrieval](https://mlsanity.com/paper/2303.09429/) (2023)
- [Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization](https://mlsanity.com/paper/2211.07394/) (2022)
- [Bi-directional Training for Composed Image Retrieval via Text Prompt Learning](https://mlsanity.com/paper/2303.16604/) (2023)
- [Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder](https://mlsanity.com/paper/2305.16304/) (2023)
- [Language-only Efficient Training of Zero-shot Composed Image Retrieval](https://mlsanity.com/paper/2312.01998/) (2023)
- [Composed Video Retrieval via Enriched Context and Discriminative Embeddings](https://mlsanity.com/paper/2403.16997/) (2024)
- [A Comprehensive Survey on Composed Image Retrieval](https://mlsanity.com/paper/2502.18495/) (2025)
- [Dynamic Weighted Combiner for Mixed-Modal Image Retrieval](https://mlsanity.com/paper/2312.06179/) (2023)
- [Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2311.07622/) (2023)
- [VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering](https://mlsanity.com/paper/2312.12273/) (2023)
- [Image Search with Text Feedback by Additive Attention Compositional Learning](https://mlsanity.com/paper/2203.03809/) (2022)
- [Beyond Simple Edits: Composed Video Retrieval with Dense Modifications](https://mlsanity.com/paper/2508.14039/) (2025)
- [Dual Relation Alignment for Composed Image Retrieval](https://mlsanity.com/paper/2309.02169/) (2023)
- [A Survey of Multimodal Composite Editing and Retrieval](https://mlsanity.com/paper/2409.05405/) (2024)
- [BOSS: Bottom-up Cross-modal Semantic Composition with Hybrid Counterfactual Training for Robust Content-based Image Retrieval](https://mlsanity.com/paper/2207.04211/) (2022)
- [Self-distilled Dynamic Fusion Network for Language-based Fashion Retrieval](https://mlsanity.com/paper/2405.15451/) (2024)
- [Composed Multi-modal Retrieval: A Survey of Approaches and Applications](https://mlsanity.com/paper/2503.01334/) (2025)
- [Decompose Semantic Shifts for Composed Image Retrieval](https://mlsanity.com/paper/2309.09531/) (2023)
- [Do Composed Image Retrieval Benchmarks Require Multimodal Composition?](https://mlsanity.com/paper/2605.14787/) (2026)

## Abstract (arXiv)

The ability to efficiently search for images is essential for improving the user experiences across various products. Incorporating user feedback, via multi-modal inputs, to navigate visual search can help tailor retrieved results to specific user queries. We focus on the task of text-conditioned image retrieval that utilizes support text feedback alongside a reference image to retrieve images that concurrently satisfy constraints imposed by both inputs. The task is challenging since it requires learning composite image-text features by incorporating multiple cross-granular semantic edits from text feedback and then applying the same to visual features. To address this, we propose a novel framework SAC which resolves the above in two major steps: "where to see" (Semantic Feature Attention) and "how to change" (Semantic Feature Modification). We systematically show how our architecture streamlines the generation of text-aware image features by removing the need for various modules required by other state-of-art techniques. We present extensive quantitative, qualitative analysis, and ablation studies, to show that our architecture SAC outperforms existing techniques by achieving state-of-the-art performance on 3 benchmark datasets: FashionIQ, Shoes, and Birds-to-Words, while supporting natural language feedback of varying lengths.