# SalientFusion: Context-Aware Compositional Zero-Shot Food Recognition

arXiv: https://arxiv.org/abs/2509.03873 · HTML: https://mlsanity.com/paper/2509.03873/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 23 references that are in the map.
- First posted on arXiv 4 Sep 2025.

## Builds on (most cited first, 15 of 15)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [Task-Driven Modular Networks for Zero-Shot Compositional Learning](https://mlsanity.com/paper/1905.05908/) (2019)
- [Bilateral Reference for High-Resolution Dichotomous Image Segmentation](https://mlsanity.com/paper/2401.03407/) (2024)
- [Symmetry and Group in Attribute-Object Compositions](https://mlsanity.com/paper/2004.00587/) (2020)
- [Large Scale Visual Food Recognition](https://mlsanity.com/paper/2103.16107/) (2021)
- [Learning to Compose Soft Prompts for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2204.03574/) (2022)
- [A Survey on Food Computing](https://mlsanity.com/paper/1808.07202/) (2018)
- [Disentangling Visual Embeddings for Attributes and Objects](https://mlsanity.com/paper/2205.08536/) (2022)
- [Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2206.14475/) (2022)
- [Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2211.10681/) (2022)
- [Learning Conditional Attributes for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.17940/) (2023)
- [Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2303.15230/) (2023)
- [SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection](https://mlsanity.com/paper/2310.04689/) (2023)

## Abstract (arXiv)

Food recognition has gained significant attention, but the rapid emergence of new dishes requires methods for recognizing unseen food categories, motivating Zero-Shot Food Learning (ZSFL). We propose the task of Compositional Zero-Shot Food Recognition (CZSFR), where cuisines and ingredients naturally align with attributes and objects in Compositional Zero-Shot learning (CZSL). However, CZSFR faces three challenges: (1) Redundant background information distracts models from learning meaningful food features, (2) Role confusion between staple and side dishes leads to misclassification, and (3) Semantic bias in a single attribute can lead to confusion of understanding. Therefore, we propose SalientFusion, a context-aware CZSFR method with two components: SalientFormer, which removes background redundancy and uses depth features to resolve role confusion; DebiasAT, which reduces the semantic bias by aligning prompts with visual features. Using our proposed benchmarks, CZSFood-90 and CZSFood-164, we show that SalientFusion achieves state-of-the-art results on these benchmarks and the most popular general datasets for the general CZSL. The code is avaliable at https://github.com/Jiajun-RUC/SalientFusion.