Material Classification in the Wild: Do Synthesized Training Data Generalise Better than Real-World Training Data?
We question the dominant role of real-world training images in the field of material classification by investigating whether synthesized data can generalise more effectively than real-world data. Experimental results on three challenging real-world material databases show that the best performing pre-trained convolutional neural network (CNN) architectures can achieve up to 91.03% mean average precision when classifying materials in cross-dataset scenarios. We demonstrate that synthesized data achieve an improvement on mean average precision when used as training data and in conjunction with pre-trained CNN architectures, which spans from ~ 5% to ~ 19% across three widely used material databases of real-world images.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationMaterial ClassificationSimilar Papers 제목 키워드 기반
WildSci: Advancing Scientific Reasoning from In-the-Wild Literature
Recent progress in large language model (LLM) reasoning has focused on domains like mathematics and coding, where abundant high-quality data and objective evaluation metrics are readily available. In contrast, progress i…
Reinforcement LearningMaterial Recognition in the Wild with the Materials in Context Database
Recognizing materials in real-world images is a challenging task. Real-world materials have rich surface texture, geometry, lighting conditions, and clutter, which combine to make the problem particularly difficult. In t…
Material RecognitionSegmentationFLAME Diffuser: Wildfire Image Synthesis using Mask Guided Diffusion
Wildfires are a significant threat to ecosystems and human infrastructure, leading to widespread destruction and environmental degradation. Recent advancements in deep learning and generative models have enabled new meth…
Fire DetectionImage Generationobject-detectionObject Detection+1Training Object Detectors on Synthetic Images Containing Reflecting Materials
One of the grand challenges of deep learning is the requirement to obtain large labeled training data sets. While synthesized data sets can be used to overcome this challenge, it is important that these data sets close t…
Image GenerationObjectThermodynamic assessment of machine learning models for solid-state synthesis prediction
Machine learning models have recently emerged to predict whether hypothetical solid-state materials can be synthesized. These models aim to circumvent direct first-principles modeling of solid-state phase transformations…