Papers › SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection

SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection

7 Oct 2023arXiv:2310.04689archive 2025-07-28

Pengfei Zhou, Weiqing Min, Yang Zhang, Jiajun Song, Ying Jin, Shuqiang Jiang

Food detection is becoming a fundamental task in food computing that supports various multimedia applications, including food recommendation and dietary monitoring. To deal with real-world scenarios, food detection needs to localize and recognize novel food objects that are not seen during training, demanding Zero-Shot Detection (ZSD). However, the complexity of semantic attributes and intra-class feature diversity poses challenges for ZSD methods in distinguishing fine-grained food classes. To tackle this, we propose the Semantic Separable Diffusion Synthesizer (SeeDS) framework for Zero-Shot Food Detection (ZSFD). SeeDS consists of two modules: a Semantic Separable Synthesizing Module (S³M) and a Region Feature Denoising Diffusion Model (RFDDM). The S³M learns the disentangled semantic representation for complex food attributes from ingredients and cuisines, and synthesizes discriminative food features via enhanced semantic information. The RFDDM utilizes a novel diffusion model to generate diversified region features and enhances ZSFD via fine-grained synthesized features. Extensive experiments show the state-of-the-art ZSFD performance of our proposed method on two food datasets, ZSFooD and UECFOOD-256. Moreover, SeeDS also maintains effectiveness on general ZSD datasets, PASCAL VOC and MS COCO. The code and dataset can be found at https://github.com/LanceZPF/SeeDS.

Paper PDF Code

Code

lancezpf/seeds officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Denoising Food recommendation Generalized Zero-Shot Object Detection Object Detection Zero-Shot Object Detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Zero-Shot Object Detection	MS-COCO	SeeDS	Recall	64	#2 of 9	Archive leaderboard	report
Zero-Shot Object Detection	MS-COCO	SeeDS	mAP	20.6	#2 of 9	Archive leaderboard	report
Zero-Shot Object Detection	PASCAL VOC'07	SeeDS	mAP	68.9	#1 of 7	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Attention Diffusion Linear Layer Multi-Head Attention Softmax Synthesizer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections