Search Results for author:
Found 4 papers, 1 papers with code
LORD: Leveraging Open-Set Recognition with Unknown Data
To mitigate dependency on extensive and costly background datasets, we explore mixup as an off-the-shelf data generation technique.
Exploring the Open World Using Incremental Extreme Value Machines
One particular machine learning problem in dynamic environments is open world recognition.
Scaling Laws for Gaussian Random Many-Access Channels
When the user activity is random, i. e., when $\ell_n$ and $k_n$ are different, it is demonstrated that if $k_n\log \ell_n$ is sublinear in $n$, then each user can achieve the single-user capacity per unit-energy $(\log e)/N_0$.
Information Theory Information Theory
Evaluation of CNN-based Single-Image Depth Estimation Methods
While an increasing interest in deep models for single-image depth estimation methods can be observed, established schemes for their evaluation are still limited.
