Brac大学（Bracu）参与了大学罗佛挑战（URC），这是由Mars社会组织的大学级学生的机器人竞赛，以设计和建造一个将用于火星早期探险家的流动站。Bracu已经设计和开发了一个全功能的下一代火星罗孚，蒙古托伊，可以在星球火星的极端敌对状态下运行。不仅拥有自主和手动控制功能的蒙古Tori，它还能够进行科学任务，以确定火星环境中的土壤和风化的特点。
translated by 谷歌翻译
Object detection requires substantial labeling effort for learning robust models. Active learning can reduce this effort by intelligently selecting relevant examples to be annotated. However, selecting these examples properly without introducing a sampling bias with a negative impact on the generalization performance is not straightforward and most active learning techniques can not hold their promises on real-world benchmarks. In our evaluation paper, we focus on active learning techniques without a computational overhead besides inference, something we refer to as zero-cost active learning. In particular, we show that a key ingredient is not only the score on a bounding box level but also the technique used for aggregating the scores for ranking images. We outline our experimental setup and also discuss practical considerations when using active learning for object detection.
translated by 谷歌翻译
本地监督的学习旨在根据网络每个解耦模块的全局损耗函数的局部估计来训练神经网络。通常将辅助网络附加到模块上，以根据贪婪的本地损失近似梯度更新。尽管在平行性和减少记忆消耗方面是有利的，但这种训练的范式严重降低了神经网络的概括性能。在本文中，我们建议定期指导本地学习（PGL），该学习将全球客观重复地重复地重复纳入基于局部损坏的神经网络的培训，主要是增强模型的概括能力。我们表明，一个简单的周期性指导方案在记忆范围低的同时会带来显着的性能增长。我们在各种数据集和网络上进行了广泛的实验，以证明PGL的有效性，尤其是在具有许多解耦模块的配置中。
translated by 谷歌翻译