arXiv subjects

Waikeung Wong

Publications and source records attributed to Waikeung Wong.

8 recordsLinked to original sources

arXiv2026

Autonomous Fashion Outfit Composition via Unified Aesthetic Foresight Model

Fashion Outfit Composition (FOC) requires sequentially assembling fashion items into a stylistically cohesive ensemble. Existing works struggle to model this step-by-step process effectively, primarily because they fail to jointly optimize the two critical capabilities required for FOC: intermediate outfit value evaluation and complementary item prediction. This structural disconnect, compounded by the severe sparsity of step-wise aesthetic signals, leaves them without a mechanism to autonomously determine when to stop the composition process. To address these challenges, we introduce the Unified Aesthetic Foresight Model (UAFM), which seamlessly unifies both capabilities into a dual-head architecture over a shared backbone. Crucially, we formulate FOC as a deterministic Markov Decision Process and optimize a value head via a post-decision state temporal difference (TD) objective to recursively backpropagate sparse terminal aesthetic rewards to intermediate states. This enables the model to accurately estimate the potential of a partial outfit evolving into a compatible ensemble. Consequently, UAFM can compute step-wise marginal aesthetic gains for dynamic termination. Furthermore, this unified design strictly aligns aesthetic evaluation and complementary item prediction within a shared representation manifold, intrinsically regularizing the combinatorial search space. Extensive experiments on the Polyvore-Outfits dataset demonstrate that UAFM establishes a new state-of-the-art across both FOC and conventional fashion tasks. Extensive ablation studies further confirm that our post-decision state TD formulation provides the aesthetic value prediction necessary for autonomous dynamic termination, while validating the synergistic benefits of our unified dual-head architecture.

cs.LG↗

arXiv2026

Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and Accessories

Virtual try-on (VTON) has advanced single-garment visualization, yet real-world fashion centers on full outfits with multiple garments, accessories, fine-grained categories, layering, and diverse styling, remaining beyond current VTON systems. Existing datasets are category-limited and lack outfit diversity. We introduce Garments2Look, the first large-scale multimodal dataset for outfit-level VTON, comprising 80K many-garments-to-one-look pairs across 40 major categories and 300+ fine-grained subcategories. Each pair includes an outfit with 3-12 reference garment images (Average 4.48), a model image wearing the outfit, and detailed item and try-on textual annotations. To balance authenticity and diversity, we propose a synthesis pipeline. It involves heuristically constructing outfit lists before generating try-on results, with the entire process subjected to strict automated filtering and human validation to ensure data quality. To probe task difficulty, we adapt SOTA VTON methods and general-purpose image editing models to establish baselines. Results show current methods struggle to try on complete outfits seamlessly and to infer correct layering and styling, leading to misalignment and artifacts.

cs.CV↗

arXiv2025

Dress Well via Fashion Cognitive Learning

Fashion compatibility models enable online retailers to easily obtain a large number of outfit compositions with good quality. However, effective fashion recommendation demands precise service for each customer with a deeper cognition of fashion. In this paper, we conduct the first study on fashion cognitive learning, which is fashion recommendations conditioned on personal physical information. To this end, we propose a Fashion Cognitive Network (FCN) to learn the relationships among visual-semantic embedding of outfit composition and appearance features of individuals. FCN contains two submodules, namely outfit encoder and Multi-label Graph Neural Network (ML-GCN). The outfit encoder uses a convolutional layer to encode an outfit into an outfit embedding. The latter module learns label classifiers via stacked GCN. We conducted extensive experiments on the newly collected O4U dataset, and the results provide strong qualitative and quantitative evidence that our framework outperforms alternative methods.

cs.CV↗

arXiv2025

FashionM3: Multimodal, Multitask, and Multiround Fashion Assistant based on Unified Vision-Language Model

Fashion styling and personalized recommendations are pivotal in modern retail, contributing substantial economic value in the fashion industry. With the advent of vision-language models (VLM), new opportunities have emerged to enhance retailing through natural language and visual interactions. This work proposes FashionM3, a multimodal, multitask, and multiround fashion assistant, built upon a VLM fine-tuned for fashion-specific tasks. It helps users discover satisfying outfits by offering multiple capabilities including personalized recommendation, alternative suggestion, product image generation, and virtual try-on simulation. Fine-tuned on the novel FashionRec dataset, comprising 331,124 multimodal dialogue samples across basic, personalized, and alternative recommendation tasks, FashionM3 delivers contextually personalized suggestions with iterative refinement through multiround interactions. Quantitative and qualitative evaluations, alongside user studies, demonstrate FashionM3's superior performance in recommendation effectiveness and practical value as a fashion assistant.

cs.CV↗

arXiv2025

MVREC: A General Few-shot Defect Classification Model Using Multi-View Region-Context

Few-shot defect multi-classification (FSDMC) is an emerging trend in quality control within industrial manufacturing. However, current FSDMC research often lacks generalizability due to its focus on specific datasets. Additionally, defect classification heavily relies on contextual information within images, and existing methods fall short of effectively extracting this information. To address these challenges, we propose a general FSDMC framework called MVREC, which offers two primary advantages: (1) MVREC extracts general features for defect instances by incorporating the pre-trained AlphaCLIP model. (2) It utilizes a region-context framework to enhance defect features by leveraging mask region input and multi-view context augmentation. Furthermore, Few-shot Zip-Adapter(-F) classifiers within the model are introduced to cache the visual features of the support set and perform few-shot classification. We also introduce MVTec-FS, a new FSDMC benchmark based on MVTec AD, which includes 1228 defect images with instance-level mask annotations and 46 defect types. Extensive experiments conducted on MVTec-FS and four additional datasets demonstrate its effectiveness in general defect classification and its ability to incorporate contextual information to improve classification performance. Code: https://github.com/ShuaiLYU/MVREC

cs.CV↗

arXiv2024

REB: Reducing Biases in Representation for Industrial Anomaly Detection

Existing representation-based methods usually conduct industrial anomaly detection in two stages: obtain feature representations with a pre-trained model and perform distance measures for anomaly detection. Among them, K-nearest neighbor (KNN) retrieval-based anomaly detection methods show promising results. However, the features are not fully exploited as these methods ignore domain bias of pre-trained models and the difference of local density in feature space, which limits the detection performance. In this paper, we propose Reducing Biases (REB) in representation by considering the domain bias and building a self-supervised learning task for better domain adaption with a defect generation strategy (DefectMaker) that ensures a strong diversity in the synthetic defects. Additionally, we propose a local-density KNN (LDKNN) to reduce the local density bias in the feature space and obtain effective anomaly detection. The proposed REB method achieves a promising result of 99.5\% Im.AUROC on the widely used MVTec AD, with smaller backbone networks such as Vgg11 and Resnet18. The method also achieves an impressive 88.8\% Im.AUROC on the MVTec LOCO AD dataset and a remarkable 96.0\% on the BTAD dataset, outperforming other representation-based approaches. These results indicate the effectiveness and efficiency of REB for practical industrial applications. Code:https://github.com/ShuaiLYU/REB.

cs.CV↗

arXiv2021

fAshIon after fashion: A Report of AI in Fashion

In this independent report fAshIon after fashion, we examine the development of fAshIon (artificial intelligence (AI) in fashion) and explore its potentiality to become a major disruptor of the fashion industry in the near future. To do this, we investigate AI technologies used in the fashion industry through several lenses. We summarise fAshIon studies conducted over the past decade and categorise them into seven groups: Overview, Evaluation, Basic Tech, Selling, Styling, Design, and Buying. The datasets mentioned in fAshIon research have been consolidated on one GitHub page for ease of use. We analyse the authors' backgrounds and the geographic regions treated in these studies to determine the landscape of fAshIon research. The results of our analysis are presented with an aim to provide researchers with a holistic view of research in fAshIon. As part of our primary research, we also review a wide range of cases of applied fAshIon in the fashion industry and analyse their impact on the industry, markets and individuals. We also identify the challenges presented by fAshIon and suggest that these may form the basis for future research. We finally exhibit that many potential opportunities exist for the use of AI in fashion which can transform the fashion industry embedded with AI technologies and boost profits.

cs.CY↗

arXiv2020

Regularizing Reasons for Outfit Evaluation with Gradient Penalty

In this paper, we build an outfit evaluation system which provides feedbacks consisting of a judgment with a convincing explanation. The system is trained in a supervised manner which faithfully follows the domain knowledge in fashion. We create the EVALUATION3 dataset which is annotated with judgment, the decisive reason for the judgment, and all corresponding attributes (e.g. print, silhouette, and material \etc.). In the training process, features of all attributes in an outfit are first extracted and then concatenated as the input for the intra-factor compatibility net. Then, the inter-factor compatibility net is used to compute the loss for judgment. We penalize the gradient of judgment loss of so that our Grad-CAM-like reason is regularized to be consistent with the labeled reason. In inference, according to the obtained information of judgment, reason, and attributes, a user-friendly explanation sentence is generated by the pre-defined templates. The experimental results show that the obtained network combines the advantages of high precision and good interpretation.

cs.CV↗