← Back to all news
arXiv Computer Vision

Improving Semantic Coverage in AI Test & Evaluation through Generative Augmentation

The paper introduces a three‑stage generative AI pipeline to identify and fill semantic gaps in AI test datasets without requiring labeled data. First, vision‑language models zero‑shot label semantic factors and clustering highlights those most impacting model behavior. Second, diffusion‑based image‑to‑image models generate new images that preserve scene content while adding underrepresented semantics. Third, statistical checks confirm improved coverage before the synthetic images augment the test set. The method is validated on image classification and object detection tasks, showing that enriched test sets better differentiate models with or without exposure to missing semantics, leading to conclusions that align more closely with an ideally covered dataset.

Related stories

arXiv Computer Vision
Aug 31

Image Augmentation as Test Generation for Deep Learning-Based Image Retrieval Systems

The paper reviews 50 image augmentation and generation techniques, categorizing them into ten groups, and conducts a large‑scale empirical study to assess their effectiveness as test generators for embedding‑based image retrieval systems. Using Amazon Titan and OpenCLIP embeddings, the authors evaluate the techniques across four dimensions—embedding‑space similarity, embedding uncertainty, semantic realism, and retrieval failure rate—on CIFAR‑10, ImageNet‑1K, and an industrial dataset. Results show that weather simulation and SaSPA yield the highest uncertainty and failure rates while maintaining realistic visuals, whereas GAN‑based methods produce low realism due to synthetic artifacts.

By Yehan De Silva, Anirudh Sridhar, Armin Lotfy, Nafiseh Kahani, Yvan Labiche, Ziyu Wang, Frank Ouyang, Clare Carty, Azalia Shamsaei
ragdiffusion
More like this →
arXiv Machine Learning
Aug 28

A Framework for Low-Effort Training Data Generation for Urban Semantic Segmentation

The paper introduces a framework that adapts a diffusion model to a target urban domain using only imperfect pseudo‑labels, enabling the generation of high‑fidelity, target‑aligned images from semantic maps of any synthetic dataset. By filtering poor generations, correcting image‑label misalignments, and standardising semantics, the method transforms low‑effort synthetic data into competitive real‑domain training sets. Experiments on five synthetic and two real datasets show up to +8.0 %pt mIoU improvement over state‑of‑the‑art translation methods, demonstrating that rapidly constructed synthetic datasets can match the performance of high‑effort, manually designed ones.

By Damjan Kal\v{s}an, Denis Zavadski, Tim K\"uchler, Haebom Lee, Stefan Roth, Carsten Rother
diffusioncomputer-visionbenchmarks
More like this →
arXiv AI
Aug 3

Leveraging Image Generators to Address Data Scarcity: The Gen4Regen Dataset for Forest Regeneration Mapping

arXiv:2605. 05627v2 Announce Type: replace-cross Abstract: Sustainable forest management relies on precise species composition mapping, yet traditional ground surveys are labour-intensive and geographically constrained.

By Gabriel Jeanson, David-Alexandre Duclos, William Larriv\'ee-Hardy, No\'e Cochet, Mat\v{e}j Boxan, Anthony Desch\^enes, Fran\c{c}ois Pomerleau, Philippe Gigu\`ere
computer-vision
More like this →
arXiv Computer Vision
Oct 12

Low, High, and Semantic-Level Vision-Language Learning for AI-Generated Image Detection

The paper introduces LHSDet, a detector for AI‑generated images that treats detection as a visual question answering task. It employs a triple‑branch architecture: a low‑level visual branch for local texture cues, a high‑level visual branch using SigLIP2 for global perception, and a semantic‑level textual branch that generates captions with BLIP‑2. Experiments show that LHSDet achieves strong accuracy and robustness across various generative models.

By Qian Yao, Luming Yang, Jun-Jie Huang, Yongjun Wang, Xinwang Liu, Meng Wang
llmsdiffusionnlpfine-tuningmultimodal
More like this →
Hugging Face Trending Papers
Jun 23

Benchmarking the Alignment of Data-Quality Metrics, Human Judgment and Land-Cover Segmentation Performance for Earth Observation

Volume and quality of datasets are crucial for deep learning model training, yet they are often constrained by availability and data acquisition costs. Synthetic data augmentation can extend existing datasets with realistic images, and the quality of these images is generally assessed through fidelity metrics such as FID, KID, IS, LPIPS and SSIM that measure structural or distributional similarity.

computer-visionbenchmarkssafety
More like this →