activity
20142017
most citedDeep Domain Confusion: Maximizing for Domain Invariance

2.4k citations · 2.5k across the 8 of their papers we have counts for

collaborators

8 papers

cs.LG20172 cited

Stable Distribution Alignment Using the Dual of the Adversarial Distance

Ben Usman, Kate Saenko, Brian Kulis

Methods that align distributions by minimizing an adversarial distance between them have recently achieved impressive results. However, these approaches are difficult to optimize w…

cs.RO2017100 cited

Learning a visuomotor controller for real world robotic grasping using simulated depth images

Ulrich Viereck, Andreas ten Pas, Kate Saenko +1

We want to build robots that are useful in unstructured real world applications, such as doing work in the household. Grasping in particular is an important skill in this domain, y…

cs.CV201714 cited

Synthetic to Real Adaptation with Generative Correlation Alignment Networks

Xingchao Peng, Kate Saenko

Synthetic images rendered from 3D CAD models are useful for augmenting training data for object recognition algorithms. However, the generated images are non-photorealistic and do…

cs.CV201613 cited

Correlation Alignment for Unsupervised Domain Adaptation

Baochen Sun, Jiashi Feng, Kate Saenko

In this chapter, we present CORrelation ALignment (CORAL), a simple yet effective method for unsupervised domain adaptation. CORAL minimizes domain shift by aligning the second-ord…

cs.CV201621 cited

Modeling Relationships in Referential Expressions with Compositional Modular Networks

Ronghang Hu, Marcus Rohrbach, Jacob Andreas +2

People often refer to entities in an image in terms of their relationships with other entities. For example, "the black cat sitting under the table" refers to both a "black cat" en…

cs.CV2016

Combining Texture and Shape Cues for Object Recognition With Minimal Supervision

Xingchao Peng, Kate Saenko

We present a novel approach to object classification and detection which requires minimal supervision and which combines visual texture cues and shape information learned from free…