Can a biologically-plausible hierarchy e ectively replace face detection, alignment, and recognition pipelines?
Name
CBMM-Memo-003.pdf
Size
963.66 KB
Format
Adobe PDF
Checksum (MD5)
22f13e96a01d305c0a4130515f86c8be
Author(s)
Liao, Qianli
Leibo, Joel Z
Mroueh, Youssef
Poggio, Tomaso
Date Issued
March 27, 2014
Publisher
Center for Brains, Minds and Machines (CBMM), arXiv
Citation
arXiv:1311.4082v3
Series/Report no.
CBMM Memo Series;003
Abstract
The standard approach to unconstrained face recognition in natural photographs is via a detection, alignment, recognition pipeline. While that approach has achieved impressive results, there are several reasons to be dissatisfied with it, among them is its lack of biological plausibility. A recent theory of invariant recognition by feedforward hierarchical networks, like HMAX, other convolutional networks, or possibly the ventral stream, implies an alternative approach to unconstrained face recognition. This approach accomplishes detection and alignment implicitly by storing transformations of training images (called templates) rather than explicitly detecting and aligning faces at test time. Here we propose a particular locality-sensitive hashing based voting scheme which we call “consensus of collisions” and show that it can be used to approximate the full 3-layer hierarchy implied by the theory. The resulting end-to-end system for unconstrained face recognition operates on photographs of faces taken under natural conditions, e.g., Labeled Faces in the Wild (LFW), without aligning or cropping them, as is normally done. It achieves a drastic improvement in the state of the art on this end-to-end task, reaching the same level of performance as the best systems operating on aligned, closely cropped images (no outside training data). It also performs well on two newer datasets, similar to LFW, but more difficult: LFW-jittered (new here) and SUFR-W.
Subjects
Computer vision
Face recognition
Hierarchy
Invariance
Terms of Use
Attribution-NonCommercial 3.0 United States
Persistent DSpace Link
