%0 Conference Paper %B NIPS 2015 %D 2015 %T Learning with Group Invariant Features: A Kernel Perspective %A Youssef Mroueh %A Stephen Voinea %A Tomaso Poggio %X
We analyze in this paper a random feature map based on a theory of invariance (I-theory) introduced in Anselmi et.al. 2013. More specifically, a group invariant signal signature is obtained through cumulative distributions of group-transformed random projections. Our analysis bridges invariant feature learning with kernel methods, as we show that this feature map defines an expected Haar-integration kernel that is invariant to the specified group action. We show how this non-linear random feature map approximates this group invariant kernel uniformly on a set of N points. Moreover, we show that it defines a function space that is dense in the equivalent Invariant Reproducing Kernel Hilbert Space. Finally, we quantify error rates of the convergence of the empirical risk minimization, as well as the reduction in the sample complexity of a learning algorithm using such an invariant representation for signal classification, in a classical supervised learning setting
%B NIPS 2015 %G eng %U https://papers.nips.cc/paper/5798-learning-with-group-invariant-features-a-kernel-perspective %0 Generic %D 2014 %T Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines? %A Qianli Liao %A JZ. Leibo %A Youssef Mroueh %A Tomaso Poggio %K Computer vision %K Face recognition %K Hierarchy %K Invariance %X

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.

%8 03/2014 %1

arXiv:1311.4082v3

%2

http://hdl.handle.net/1721.1/100164