نظرة عامة
رصد مجتمع Hacker News هذا الخبر الذي حصد 3 نقطة و0 تعليق خلال ساعات قليلة، مما يجعله من أبرز أخبار الذكاء الاصطناعي اليوم. المصدر الأصلي: usefeyn.com.
في هذا المقال نستعرض أبرز ما جاء في هذا الخبر، تحليله من منظور عربي، وما يعنيه للمستخدمين العرب المهتمين بأدوات الذكاء الاصطناعي.
التفاصيل
Hey HN, I’m Shreyash from Feyn. We help companies build custom models from their data.<p>Today, we’re releasing FeyNoBg, an automatic background removal model. Alongside it, we're open-sourcing NoBg, the Python library we built to train and run it.<p>Try the model here: <a href="https://huggingface.co/spaces/feyninc/feynobg" rel="nofollow">https://huggingface.co/spaces/feyninc/feynobg</a>. Check out the library here: <a href="https://github.com/feyninc/nobg" rel="nofollow">https://github.com/feyninc/nobg</a><p>Some sample outputs:<p>(1) Soccer Freekick: <a href="https://drive.google.com/file/d/1MZkAGLwbhNVOZ0Oi7XvpCfSEu9QPCbwj/view?usp=sharing" rel="nofollow">https://drive.google.com/file/d/1MZkAGLwbhNVOZ0Oi7XvpCfSEu9Q...</a><p>(2) Hair in wind: <a href="https://drive.google.com/file/d/1Odc2m0XMVH9uZtvI_KjaRbXzhLLdGK8Z/view?usp=sharing" rel="nofollow">https://drive.google.com/file/d/1Odc2m0XMVH9uZtvI_KjaRbXzhLL...</a><p>(3) Bicycle with visible spokes: <a href="https://drive.google.com/file/d/1h99ahjfrtS1MFQJJgiKE2fuM3HZyQ-QJ/view?usp=sharing" rel="nofollow">https://drive.google.com/file/d/1h99ahjfrtS1MFQJJgiKE2fuM3HZ...</a><p>(4) Live Demo video: <a href="https://youtu.be/b1heHPvY8BM" rel="nofollow">https://youtu.be/b1heHPvY8BM</a><p>Background removal separates an image's subject from its surrounding. We've all tried it at some point. Often it is to reuse the subject in a different artifact. Nowadays, it is common to make chat stickers out of it. It is one of the most common but under-appreciated uses of AI. It is also surprisingly complex. Models can be easily confused by camouflage, motion blur, or fine structures like hair.<p>The task requires two skills. First, a model has to identify the foreground. Second, it has to trace the foreground’s boundary and estimate an opacity value for each pixel. Generally, these skills are taught with different datasets. That creates a failure point. A poor training mix can improve one skill at the expense of the other. We saw this in our controlled evaluation. A training run with just the MaskFactory dataset improved on the CAMO benchmark but regressed on DIS5K.<p>For FeyNoBg, we took an interpretability-first approach to training
المصدر الأصلي
هذا الخبر مأخوذ من منصة Hacker News — المجتمع التقني الأكثر متابعة في العالم.