Scene text recognition (STR) task has a common practice: All state-of-the-art STR models
are trained on large synthetic data. In contrast to this practice, training STR models only on …

This work focuses on learning deep visual representation models for retrieval by exploring
the interplay between a new loss function, the batch size, and a new regularization …

We propose-RANSAC, a generalized differentiable RANSAC that allows learning the entire
randomized robust estimation pipeline. The proposed approach enables the use of …

Designing proper loss functions is essential in training deep networks. Especially in the field
of semantic segmentation, various evaluation metrics have been proposed for diverse …

Gradient-based optimization is now ubiquitous across graphics, but unfortunately can not be
applied to problems with undefined or zero gradients. To circumvent this issue, the loss …

We study the problem of directly optimizing arbitrary non-differentiable task evaluation
metrics such as misclassification rate and recall. Our method, named MetricOpt, operates in …

Gradient-based optimization is now ubiquitous across graphics, but unfortunately can not be
applied to problems with undefined or zero gradients. To circumvent this issue, the loss …

In design, fabrication, and control problems, we are often faced with the task of synthesis, in
which we must generate an object or configuration that satisfies a set of constraints while …

This paper addresses acoustic vehicle counting using one-channel audio. We predict the
pass-by instants of vehicles from local minima of clipped vehicle-to-microphone distance …

Loss functions play an important role in training deep-network-based object detectors. The
most widely used evaluation metric for object detection is Average Precision (AP), which …