# Self-distilled Dynamic Fusion Network for Language-based Fashion Retrieval

arXiv: https://arxiv.org/abs/2405.15451 · HTML: https://mlsanity.com/paper/2405.15451/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 24 May 2024.

## Builds on (most cited first, 10 of 10)

- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [Composing Text and Image for Image Retrieval - An Empirical Odyssey](https://mlsanity.com/paper/1812.07119/) (2018)
- [ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity](https://mlsanity.com/paper/2203.08101/) (2022)
- [MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2006.15524/) (2020)
- [Modality-Agnostic Attention Fusion for visual search with text feedback](https://mlsanity.com/paper/2007.00145/) (2020)
- [Multimodal Residual Learning for Visual QA](https://mlsanity.com/paper/1606.01455/) (2016)
- [SAC: Semantic Attention Composition for Text-Conditioned Image Retrieval](https://mlsanity.com/paper/2009.01485/) (2020)
- [Self-Training Boosted Multi-Factor Matching Network for Composed Image Retrieval](https://mlsanity.com/paper/2305.09979/) (2023)
- [Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations](https://mlsanity.com/paper/2306.02092/) (2023)

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

- [A Comprehensive Survey on Composed Image Retrieval](https://mlsanity.com/paper/2502.18495/) (2025)
- [FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning](https://mlsanity.com/paper/2601.13578/) (2026)
- [FashionFAE: Fine-grained Attributes Enhanced Fashion Vision-Language Pre-training](https://mlsanity.com/paper/2412.19997/) (2024)

## Abstract (arXiv)

In the domain of language-based fashion image retrieval, pinpointing the desired fashion item using both a reference image and its accompanying textual description is an intriguing challenge. Existing approaches lean heavily on static fusion techniques, intertwining image and text. Despite their commendable advancements, these approaches are still limited by a deficiency in flexibility. In response, we propose a Self-distilled Dynamic Fusion Network to compose the multi-granularity features dynamically by considering the consistency of routing path and modality-specific information simultaneously. Two new modules are included in our proposed method: (1) Dynamic Fusion Network with Modality Specific Routers. The dynamic network enables a flexible determination of the routing for each reference image and modification text, taking into account their distinct semantics and distributions. (2) Self Path Distillation Loss. A stable path decision for queries benefits the optimization of feature extraction as well as routing, and we approach this by progressively refine the path decision with previous path information. Extensive experiments demonstrate the effectiveness of our proposed model compared to existing methods.