Ziyue Liu

Federico Girella, Ziyue Liu, Franco Fummi et al.

Defect detection is the task of identifying defects in production samples. Usually, defect detection classifiers are trained on ground-truth data formed by normal samples (negative data) and samples with defects (positive data), where the latter are consistently fewer than normal samples. State-of-the-art data augmentation procedures add synthetic defect data by superimposing artifacts to normal samples to mitigate problems related to unbalanced training data. These techniques often produce out-of-distribution images, resulting in systems that learn what is not a normal sample but cannot accurately identify what a defect looks like. In this work, we introduce DIAG, a training-free Diffusion-based In-distribution Anomaly Generation pipeline for data augmentation. Unlike conventional image generation techniques, we implement a human-in-the-loop pipeline, where domain experts provide multimodal guidance to the model through text descriptions and region localization of the possible anomalies. This strategic shift enhances the interpretability of results and fosters a more robust human feedback loop, facilitating iterative improvements of the generated outputs. Remarkably, our approach operates in a zero-shot manner, avoiding time-consuming fine-tuning procedures while achieving superior performance. We demonstrate the efficacy and versatility of DIAG with respect to state-of-the-art data augmentation approaches on the challenging KSDD2 dataset, with an improvement in AP of approximately 18% when positive samples are available and 28% when they are missing. The source code is available at https://github.com/intelligolabs/DIAG.

Davide Talon, Federico Girella, Ziyue Liu et al.

Natural language goes beyond dryly describing visual content. It contains rich abstract concepts to express feeling, creativity and properties that cannot be directly perceived. Yet, current research in Vision Language Models (VLMs) has not shed light on abstract-oriented language. Our research breaks new ground by uncovering its wide presence and under-estimated value, with extensive analysis. Particularly, we focus our investigation on the fashion domain, a highly-representative field with abstract expressions. By analyzing recent large-scale multimodal fashion datasets, we find that abstract terms have a dominant presence, rivaling the concrete ones, providing novel information, and being useful in the retrieval task. However, a critical challenge emerges: current general-purpose or fashion-specific VLMs are pre-trained with databases that lack sufficient abstract words in their text corpora, thus hindering their ability to effectively represent abstract-oriented language. We propose a training-free and model-agnostic method, Abstract-to-Concrete Translator (ACT), to shift abstract representations towards well-represented concrete ones in the VLM latent space, using pre-trained models and existing multimodal databases. On the text-to-image retrieval task, despite being training-free, ACT outperforms the fine-tuned VLMs in both same- and cross-dataset settings, exhibiting its effectiveness with a strong generalization capability. Moreover, the improvement introduced by ACT is consistent with various VLMs, making it a plug-and-play solution.

Ziyue Liu, Federico Girella, Yiming Wang et al.

Despite the rapid advances in Text-to-Image (T2I) generation models, their evaluation remains challenging in domains like fashion, involving complex compositional generation. Recent automated T2I evaluation methods leverage pre-trained vision-language models to measure cross-modal alignment. However, our preliminary study reveals that they are still limited in assessing rich entity-attribute semantics, facing challenges in attribute confusion, i.e., when attributes are correctly depicted but associated to the wrong entities. To address this, we build on a Visual Question Answering (VQA) localization strategy targeting one single entity at a time across both visual and textual modalities. We propose a localized human evaluation protocol and introduce a novel automatic metric, Localized VQAScore (L-VQAScore), that combines visual localization with VQA probing both correct (reflection) and miss-localized (leakage) attribute generation. On a newly curated dataset featuring challenging compositional alignment scenarios, L-VQAScore outperforms state-of-the-art T2I evaluation methods in terms of correlation with human judgments, demonstrating its strength in capturing fine-grained entity-attribute associations. We believe L-VQAScore can be a reliable and scalable alternative to subjective evaluations.