FDDet: Achieving Data-Efficient Food Defect Detection Under Real-World Scenarios

Ruihao Xu; Yong Liu; Yansong Tang

cs.CVMay 23, 2026

FDDet: Achieving Data-Efficient Food Defect Detection Under Real-World Scenarios

Authors: Ruihao Xu, Yong Liu, Yansong Tang

Organizations: Tsinghua Shenzhen International Graduate School, Tsinghua University

Abstract

Food defect detection is critical for automated quality control, yet existing studies lack unified benchmarks and suffer from data scarcity. We introduce FDD-48, a comprehensive dataset with fine-grained annotations across 13 food types and 48 defect categories under diverse real-world conditions. To improve detection with limited labeled data, we propose FDDet, a semi-supervised framework featuring two key components: (1) BBoxMixUp, a data augmentation technique that mixes same-category defect regions to reduce spurious feature associations, and (2) CGPC (Consistency-Guided Pseudo-Label Calibration), which filters pseudo-labels based on intra-sample consistency. Experiments show FDDet significantly outperforms mainstream detectors on FDD-48, demonstrating its effectiveness for food defect detection under data-limited scenarios.

Explore similar work

DishSeg24k: A Large-Scale Benchmark for Food Segmentation with Stochastic Expert Decoding
Jul 25, 2026Yilin Wang, Haochen Shi, Guanyu Chen +4Non-Destructive Frying Oil Oxidation Assessment Large-Scale Benchmark
Food Image Segmentation with LLM-Derived Ingredient Labels and Multimodal Fusion
Jul 28, 2026Jui-Feng Chi, Wei-Ta Chu, Sheng-Long LinMultimodal Fusion Swin
ICME 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing
Jul 6, 2026Wei Sun, Weixia Zhang, Linhan Cao +30Scalable Defect Detection Pixel-Level Annotation

Jul 25, 2026 · cs.CVJ/K move · Enter open · S save

DishSeg24k: A Large-Scale Benchmark for Food Segmentation with Stochastic Expert Decoding

Yilin Wang, Haochen Shi, Guanyu Chen, Weiqing Min+3

Food segmentation is essential for applications such as intelligent catering, dietary assessment, and recommendation. However, existing benchmarks fail to capture the complexity of real-world dining scenes. The challenges of dense inter-dish overlap, fine-grained class similarity, and extreme long-tail class distributions exceed the fidelity of current datasets. To fill this gap, we introduce \textbf{DishSeg24k}, a large-scale dish-level segmentation benchmark with 24,096 images, 112,281 instances, and 278 fine-grained categories in real-world dining environments. Based on DishSeg24k, we further propose \textbf{Food Expert-Adaptive Segmentation Transformers (FEAST)} to address these challenges. FEAST models query-based decoding as a Markov Decision Process (MDP), where each decoder layer update is treated as a sequential decision step that explores uncertainty along dish boundaries. We further redesign the decoder with a reinforcement learning (RL)-guided Mixture-of-Experts (MoE) module, in which a dual-critic decoupled optimization scheme separates task-oriented query refinement from structure-aware expert routing. This design promotes expert specialization and prevents expert collapse under long-tail category distributions. Finally, extensive experiments on DishSeg24k demonstrate the state-of-the-art performance of FEAST, which outperforms previous methods by {+3.21%} mIoU, {+3.68%} mDice, and {+4.00%} mAcc, respectively. We further validate the effectiveness of FEAST on FoodSeg103. The dataset and code will be publicly released.

Non-Destructive Frying Oil Oxidation Assessment Large-Scale Benchmark Real-World Environments Long-Tailed Distribution

Open paper Ask about it PDF

Abstract

Explore similar work

DishSeg24k: A Large-Scale Benchmark for Food Segmentation with Stochastic Expert Decoding

Food Image Segmentation with LLM-Derived Ingredient Labels and Multimodal Fusion

ICME 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing