568 citations · 2.2k across the 54 of their papers we have counts for
5 papers · 1 filter
Improved Robustness to Open Set Inputs via Tempered Mixup
Ryne Roady, Tyler L. Hayes, Christopher Kanan
Supervised classification methods often assume that evaluation data is drawn from the same distribution as training data and that all classes are present for training. However, rea…
RODEO: Replay for Online Object Detection
Manoj Acharya, Tyler L. Hayes, Christopher Kanan
Humans can incrementally learn to do new visual detection tasks, which is a huge challenge for today's computer vision systems. Incrementally trained deep learning models lack back…
On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law
Damien Teney, Kushal Kafle, Robik Shrestha +3
Out-of-distribution (OOD) testing is increasingly popular for evaluating a machine learning system's ability to generalize beyond the biases of a training set. OOD benchmarks are d…
Do We Need Fully Connected Output Layers in Convolutional Networks?
Zhongchao Qian, Tyler L. Hayes, Kushal Kafle +1
Traditionally, deep convolutional neural networks consist of a series of convolutional and pooling layers followed by one or more fully connected (FC) layers to perform the final c…
Visual Grounding Methods for VQA are Working for the Wrong Reasons!
Robik Shrestha, Kushal Kafle, Christopher Kanan
Existing Visual Question Answering (VQA) methods tend to exploit dataset biases and spurious statistical correlations, instead of producing right answers for the right reasons. To…