Timezone: »
Although the human visual system can recognize many concepts under challengingconditions, it still has some biases. In this paper, we investigate whether wecan extract these biases and transfer them into a machine recognition system.We introduce a novel method that, inspired by well-known tools in humanpsychophysics, estimates the biases that the human visual system might use forrecognition, but in computer vision feature spaces. Our experiments aresurprising, and suggest that classifiers from the human visual system can betransferred into a machine with some success. Since these classifiers seem tocapture favorable biases in the human visual system, we further present an SVMformulation that constrains the orientation of the SVM hyperplane to agree withthe bias from human visual system. Our results suggest that transferring thishuman bias into machines may help object recognition systems generalize acrossdatasets and perform better when very little training data is available.
Author Information
Carl Vondrick (MIT)
Hamed Pirsiavash (UMBC)
Aude Oliva (MIT)
Antonio Torralba (MIT)
More from the Same Authors
-
2020 Poster: Debiased Contrastive Learning »
Ching-Yao Chuang · Joshua Robinson · Yen-Chen Lin · Antonio Torralba · Stefanie Jegelka -
2020 Spotlight: Debiased Contrastive Learning »
Ching-Yao Chuang · Joshua Robinson · Yen-Chen Lin · Antonio Torralba · Stefanie Jegelka -
2018 Poster: Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding »
Kexin Yi · Jiajun Wu · Chuang Gan · Antonio Torralba · Pushmeet Kohli · Josh Tenenbaum -
2018 Poster: 3D-Aware Scene Manipulation via Inverse Graphics »
Shunyu Yao · Tzu Ming Hsu · Jun-Yan Zhu · Jiajun Wu · Antonio Torralba · Bill Freeman · Josh Tenenbaum -
2018 Spotlight: Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding »
Kexin Yi · Jiajun Wu · Chuang Gan · Antonio Torralba · Pushmeet Kohli · Josh Tenenbaum -
2016 Poster: Generating Videos with Scene Dynamics »
Carl Vondrick · Hamed Pirsiavash · Antonio Torralba -
2016 Poster: SoundNet: Learning Sound Representations from Unlabeled Video »
Yusuf Aytar · Carl Vondrick · Antonio Torralba -
2015 Poster: Skip-Thought Vectors »
Jamie Kiros · Yukun Zhu · Russ Salakhutdinov · Richard Zemel · Raquel Urtasun · Antonio Torralba · Sanja Fidler -
2015 Poster: Where are they looking? »
Adria Recasens · Aditya Khosla · Carl Vondrick · Antonio Torralba -
2015 Spotlight: Where are they looking? »
Adria Recasens · Aditya Khosla · Carl Vondrick · Antonio Torralba -
2014 Poster: Learning Deep Features for Scene Recognition using Places Database »
Bolei Zhou · Agata Lapedriza · Jianxiong Xiao · Antonio Torralba · Aude Oliva -
2014 Spotlight: Learning Deep Features for Scene Recognition using Places Database »
Bolei Zhou · Agata Lapedriza · Jianxiong Xiao · Antonio Torralba · Aude Oliva -
2011 Poster: Understanding the Intrinsic Memorability of Images »
Phillip Isola · Devi Parikh · Antonio Torralba · Aude Oliva -
2011 Poster: Video Annotation and Tracking with Active Learning »
Carl Vondrick · Deva Ramanan