activity
20172022
most citedMeasuring Catastrophic Forgetting in Neural Networks

191 citations · 426 across the 21 of their papers we have counts for

collaborators
Showing cs.CVShow all

21 papers · 1 filter

cs.CV20223 cited

Semantic Segmentation with Active Semi-Supervised Representation Learning

Aneesh Rangnekar, Christopher Kanan, Matthew Hoffman

Obtaining human per-pixel labels for semantic segmentation is incredibly laborious, often making labeled dataset construction prohibitively expensive. Here, we endeavor to overcome…

cs.CV202212 cited

EllSeg-Gen, towards Domain Generalization for head-mounted eyetracking

Rakshit S. Kothari, Reynold J. Bailey, Christopher Kanan +2

The study of human gaze behavior in natural contexts requires algorithms for gaze estimation that are robust to a wide range of imaging conditions. However, algorithms often fail t…

cs.CV20223 cited

Detecting out-of-context objects using contextual cues

Manoj Acharya, Anirban Roy, Kaushik Koneripalli +3

This paper presents an approach to detect out-of-context (OOC) objects in an image. Given an image with a set of objects, our goal is to determine if an object is inconsistent with…

cs.CV20212 cited

2nd Place Solution for SODA10M Challenge 2021 -- Continual Detection Track

Manoj Acharya, Christopher Kanan

In this technical report, we present our approaches for the continual object detection track of the SODA10M challenge. We adapt ResNet50-FPN as the baseline and try several improve…

cs.CV2021

How Does Heterogeneous Label Noise Impact Generalization in Neural Nets?

Bidur Khanal, Christopher Kanan

Incorrectly labeled examples, or label noise, is common in real-world computer vision datasets. While the impact of label noise on learning in deep neural networks has been studied…

cs.CV2021

Self-Supervised Training Enhances Online Continual Learning

Jhair Gallardo, Tyler L. Hayes, Christopher Kanan

In continual learning, a system must incrementally learn from a non-stationary data stream without catastrophic forgetting. Recently, multiple methods have been devised for increme…