Implementation-Independent Representation for Deep Convolutional Neural Networks and Humans in Processing Faces.
TL;DR: In this paper, a reverse-correlation method was applied to make explicit representations of DCNNs and humans when performing face gender classification, which showed that humans and a typical DCNN, VGG-Face, used similar critical information for this task, which mainly resided at low spatial frequencies.
read more
Abstract: Deep convolutional neural networks (DCNN) nowadays can match human performance in challenging complex tasks, but it remains unknown whether DCNNs achieve human-like performance through human-like processes. Here we applied a reverse-correlation method to make explicit representations of DCNNs and humans when performing face gender classification. We found that humans and a typical DCNN, VGG-Face, used similar critical information for this task, which mainly resided at low spatial frequencies. Importantly, the prior task experience, which the VGG-Face was pre-trained to process faces at the subordinate level (i.e., identification) as humans do, seemed necessary for such representational similarity, because AlexNet, a DCNN pre-trained to process objects at the basic level (i.e., categorization), succeeded in gender classification but relied on a completely different representation. In sum, although DCNNs and humans rely on different sets of hardware to process faces, they can use a similar and implementation-independent representation to achieve the same computation goal.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
The Face Module Emerged in a Deep Convolutional Neural Network Selectively Deprived of Face Experience
TL;DR: Zhang et al. as mentioned in this paper built a model of selective deprivation of the experience on faces with a representative deep convolutional neural network, AlexNet, by removing all images containing faces from its training stimuli.
The Face Inversion Effect in Deep Convolutional Neural Networks
Fang Tian,Hailun Xie,Yiying Song,Siyuan Hu,Jian Liu +4 more
TL;DR: Zhang et al. as mentioned in this paper examined the face inversion effect in an artificial face system, visual geometry group network-face (VGG-Face), a deep convolutional neural network (DCNN) specialized for identifying faces.
13
Implementation-Independent Representation for Deep Convolutional Neural Networks and Humans in Processing Faces.
TL;DR: In this paper, a reverse-correlation method was applied to make explicit representations of DCNNs and humans when performing face gender classification, which showed that humans and a typical DCNN, VGG-Face, used similar critical information for this task, which mainly resided at low spatial frequencies.
Semantic Relatedness Emerges in Deep Convolutional Neural Networks Designed for Object Recognition
TL;DR: Zhang et al. as discussed by the authors explored representational similarity among objects in a typical DCNN (e.g., AlexNet), and found that representations of object categories were organized in a hierarchical fashion, suggesting that the relatedness among objects emerged automatically when learning to recognize them.
Using deep neural networks to disentangle visual and semantic information in human perception and memory.
Adva Shoham,Idan Grosbard,Or Patashnik,Daniel Cohen-Or,Galit Yovel +4 more
TL;DR: Deep neural networks are used to uncover the content of human mental representations of familiar faces and objects when they are viewed or recalled from memory and reveal a previously unknown unique contribution of an integrated visual-semantic representation in both perception and memory.
10
References
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
FaceNet: A Unified Embedding for Face Recognition and Clustering
TL;DR: FaceNet as discussed by the authors uses a deep convolutional network trained to directly optimize the embedding itself, rather than an intermediate bottleneck layer as in previous deep learning approaches, and achieves state-of-the-art face recognition performance using only 128 bytes per face.
14.2K
FaceNet: A unified embedding for face recognition and clustering
Florian Schroff,Dmitry Kalenichenko,James Philbin +2 more
- 07 Jun 2015
TL;DR: A system that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity, and achieves state-of-the-art face recognition performance using only 128-bytes perface.
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
Yaniv Taigman,Ming Yang,Marc'Aurelio Ranzato,Lior Wolf +3 more
- 23 Jun 2014
TL;DR: This work revisits both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network.