研究人员开发了 Slimmable ConvNeXt，这是一种创建自适应视觉模型的新方法。该方法训练一组单一的权重，可以动态调整其容量，以便在各种设备和不断变化的计算资源上高效部署。Slimmable ConvNeXt-T 模型在 ImageNet-1k 上实现了 80.8% 的准确率，计算量为 4.5 GMACs，优于 HydraViT 和 MatFormer-S 等现有的可扩展方法。 AI
影响 能够更高效地将视觉模型部署到各种硬件上，减少了对多个模型版本et的需求。
排序理由 该集群包含一篇 arXiv 论文，详细介绍了新的模型架构及其在基准测试上的性能。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.22677v1 Announce Type: new Abstract: Deploying vision models across devices with varying resource constraints, or even on a single device where available compute fluctuates due to battery state, thermal throttling, or latency deadlines, typically requires training and …
Deploying vision models across devices with varying resource constraints, or even on a single device where available compute fluctuates due to battery state, thermal throttling, or latency deadlines, typically requires training and maintaining separate models. Width-adaptive infe…