arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.10089eess.IV
收藏

多任务协作智能的潜在空间可扩展性

Latent-space scalability for multi-task collaborative intelligence

Hyomin Choi, Ivan V. Bajic

摘要:

我们研究多任务协作智能的潜在空间可扩展性,其中一个任务是对象检测,另一个是输入重建。在我们提出的方法中,部分潜在空间可以选择性地解码,以支持对象检测,而其余的可以解码时,输入重建是必要的。当仅需要对象检测时,这种方法允许减少计算资源,并且这可以在不重构输入像素的情况下实现。通过改变训练损失函数中的各个项的缩放因子,可以训练系统以实现对象检测精度和输入重建质量之间的各种权衡。实验证明,与相关基准相比,这两个任务的可调系统性能。

英文摘要:

We investigate latent-space scalability for multi-task collaborative intelligence, where one of the tasks is object detection and the other is input reconstruction. In our proposed approach, part of the latent space can be selectively decoded to support object detection while the remainder can be decoded when input reconstruction is needed. Such an approach allows reduced computational resources when only object detection is required, and this can be achieved without reconstructing input pixels. By varying the scaling factors of various terms in the training loss function, the system can be trained to achieve various trade-offs between object detection accuracy and input reconstruction quality. Experiments are conducted to demonstrate the adjustable system performance on the two tasks compared to the relevant benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑