Picture for Aditya Khosla

Aditya Khosla

Network Dissection: Quantifying Interpretability of Deep Visual Representations

Apr 19, 2017
David Bau, Bolei Zhou, Aditya Khosla, Aude Oliva, Antonio Torralba

Figure 1 for Network Dissection: Quantifying Interpretability of Deep Visual Representations

Figure 2 for Network Dissection: Quantifying Interpretability of Deep Visual Representations

Figure 3 for Network Dissection: Quantifying Interpretability of Deep Visual Representations

Figure 4 for Network Dissection: Quantifying Interpretability of Deep Visual Representations

* First two authors contributed equally. Oral presentation at CVPR 2017

Access Paper or Ask Questions

Following Gaze Across Views

Dec 09, 2016
Adrià Recasens, Carl Vondrick, Aditya Khosla, Antonio Torralba

Figure 1 for Following Gaze Across Views

Figure 2 for Following Gaze Across Views

Figure 3 for Following Gaze Across Views

Figure 4 for Following Gaze Across Views

* 9 pages, 8 figures

Access Paper or Ask Questions

Eye Tracking for Everyone

Jun 18, 2016
Kyle Krafka, Aditya Khosla, Petr Kellnhofer, Harini Kannan, Suchendra Bhandarkar, Wojciech Matusik, Antonio Torralba

Figure 1 for Eye Tracking for Everyone

Figure 2 for Eye Tracking for Everyone

Figure 3 for Eye Tracking for Everyone

Figure 4 for Eye Tracking for Everyone

* The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016

Access Paper or Ask Questions

Object Detectors Emerge in Deep Scene CNNs

Apr 15, 2015
Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba

Figure 1 for Object Detectors Emerge in Deep Scene CNNs

Figure 2 for Object Detectors Emerge in Deep Scene CNNs

Figure 3 for Object Detectors Emerge in Deep Scene CNNs

Figure 4 for Object Detectors Emerge in Deep Scene CNNs

* 12 pages, ICLR 2015 conference paper

Access Paper or Ask Questions

3D ShapeNets: A Deep Representation for Volumetric Shapes

Apr 15, 2015
Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, Jianxiong Xiao

Figure 1 for 3D ShapeNets: A Deep Representation for Volumetric Shapes

Figure 2 for 3D ShapeNets: A Deep Representation for Volumetric Shapes

Figure 3 for 3D ShapeNets: A Deep Representation for Volumetric Shapes

Figure 4 for 3D ShapeNets: A Deep Representation for Volumetric Shapes

* to be appeared in CVPR 2015

Access Paper or Ask Questions

Visualizing Object Detection Features

Feb 19, 2015
Carl Vondrick, Aditya Khosla, Hamed Pirsiavash, Tomasz Malisiewicz, Antonio Torralba

Figure 1 for Visualizing Object Detection Features

Figure 2 for Visualizing Object Detection Features

Figure 3 for Visualizing Object Detection Features

Figure 4 for Visualizing Object Detection Features

* In submission to IJCV

Access Paper or Ask Questions