Multi-task self-supervised visual learning

We investigate methods for combining multiple self-supervised tasks-i.e., supervised tasks where data can be collected without manual labeling-in order to train a single visual representation. First, we provide an apples-to-apples comparison of four different self-supervised tasks using the very dee...

সম্পূর্ণ বিবরণ

গ্রন্থ-পঞ্জীর বিবরন
প্রধান লেখক: Doersch, C, Zisserman, A
বিন্যাস: Conference item
প্রকাশিত: IEEE Explore 2017

অনুরূপ উপাদানগুলি