Trend-Aware Fashion Recommendation with Visual Segmentation and Semantic Similarity

2025-06-09

AI Summary

This paper addresses two key challenges in fashion recommendation: weak trend awareness and insufficient fusion of multi-source features. To tackle these, we propose a trend-driven personalized recommendation method. Methodologically, we introduce the first integration of garment-aware visual segmentation with trend-guided synthetic user behavior modeling, establishing a triple-weighted fusion mechanism combining visual, semantic, and popularity signals. Specifically, fine-grained visual features are extracted using backbone networks (e.g., ResNet-50), fused with semantic segmentation masks and pre-trained CNN representations, and further enhanced by trend-weighted synthetic purchase behavior simulation. Evaluated on the DeepFashion dataset, our approach achieves a category similarity rate of 64.95% and the lowest popularity prediction MAE, while significantly improving gender alignment and category relevance. These results empirically validate the effectiveness of jointly modeling trend sensitivity and personalization.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Data Mining & Knowledge Management: Recommender Systems
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We introduce a trend-aware and visually-grounded fashion recommendation system that integrates deep visual representations, garment-aware segmentation, semantic category similarity and user behavior simulation. Our pipeline extracts focused visual embeddings by masking non-garment regions via semantic segmentation followed by feature extraction using pretrained CNN backbones (ResNet-50, DenseNet-121, VGG16). To simulate realistic shopping behavior, we generate synthetic purchase histories influenced by user-specific trendiness and item popularity. Recommendations are computed using a weighted scoring function that fuses visual similarity, semantic coherence and popularity alignment. Experiments on the DeepFashion dataset demonstrate consistent gender alignment and improved category relevance, with ResNet-50 achieving 64.95% category similarity and lowest popularity MAE. An ablation study confirms the complementary roles of visual and popularity cues. Our method provides a scalable framework for personalized fashion recommendations that balances individual style with emerging trends. Our implementation is available at https://github.com/meddjilani/FashionRecommender

Problem

• Integrates visual segmentation and semantic similarity for fashion recommendation
• Simulates user shopping behavior with trendiness and popularity factors
• Balances individual style and emerging trends in personalized recommendations

Innovation

• Uses garment-aware segmentation for focused visual embeddings
• Simulates shopping behavior with synthetic purchase histories
• Fuses visual similarity, semantic coherence, and popularity alignment