Collaborating Authors

How Coders Are Fighting Bias in Facial Recognition Software


Software engineer Henry Gan got a surprise last summer when he tested his team's new facial recognition system on coworkers at startup Gfycat. The machine-learning software successfully identified most of his colleagues, but the system stumbled with one group. "It got some of our Asian employees mixed up," says Gan, who is Asian. "Which was strange because it got everyone else correctly." Gan could take solace from the fact that similar problems have tripped up much larger companies.

Identifying Bias in AI using Simulation Machine Learning

Machine learned models exhibit bias, often because the datasets used to train them are biased. This presents a serious problem for the deployment of such technology, as the resulting models might perform poorly on populations that are minorities within the training set and ultimately present higher risks to them. We propose to use high-fidelity computer simulations to interrogate and diagnose biases within ML classifiers. We present a framework that leverages Bayesian parameter search to efficiently characterize the high dimensional feature space and more quickly identify weakness in performance. We apply our approach to an example domain, face detection, and show that it can be used to help identify demographic biases in commercial face application programming interfaces (APIs).

Learning to Align from Scratch

Neural Information Processing Systems

Unsupervised joint alignment of images has been demonstrated to improve performance on recognition tasks such as face verification. Such alignment reduces undesired variability due to factors such as pose, while only requiring weak supervision in the form of poorly aligned examples. However, prior work on unsupervised alignment of complex, real world images has required the careful selection of feature representation based on hand-crafted image descriptors, in order to achieve an appropriate, smooth optimization landscape. In this paper, we instead propose a novel combination of unsupervised joint alignment with unsupervised feature learning. Specifically, we incorporate deep learning into the {\em congealing} alignment framework. Through deep learning, we obtain features that can represent the image at differing resolutions based on network depth, and that are tuned to the statistics of the specific data being aligned. In addition, we modify the learning algorithm for the restricted Boltzmann machine by incorporating a group sparsity penalty, leading to a topographic organization on the learned filters and improving subsequent alignment results. We apply our method to the Labeled Faces in the Wild database (LFW). Using the aligned images produced by our proposed unsupervised algorithm, we achieve a significantly higher accuracy in face verification than obtained using the original face images, prior work in unsupervised alignment, and prior work in supervised alignment. We also match the accuracy for the best available, but unpublished method.

Do-It-Yourself Cat Door Recognizes Your Feline

AITopics Original Links

Forster's cat, Timothy, is pretty cute, but Forster is tired of him bringing in dead or dying birds and mice and dropping them on the carpet. Eight years ago, an image-recognition software company solved the same problem with its company cat, Flo. Quantum Picture developed a cat door that let Flo in, but locked her out if it saw she was carrying something in her mouth. At the time, the door connected to a desktop computer that ran the program that snapped pictures of Flo and analyzed them as she approached the door. Now, Forster is determined to build Flo's door for Timothy on weekends, in between his usual consulting work in Simi Valley, Calif.

A Comprehensive Performance Evaluation of Deformable Face Tracking "In-the-Wild" Artificial Intelligence

Recently, technologies such as face detection, facial landmark localisation and face recognition and verification have matured enough to provide effective and efficient solutions for imagery captured under arbitrary conditions (referred to as "in-the-wild"). This is partially attributed to the fact that comprehensive "in-the-wild" benchmarks have been developed for face detection, landmark localisation and recognition/verification. A very important technology that has not been thoroughly evaluated yet is deformable face tracking "in-the-wild". Until now, the performance has mainly been assessed qualitatively by visually assessing the result of a deformable face tracking technology on short videos. In this paper, we perform the first, to the best of our knowledge, thorough evaluation of state-of-the-art deformable face tracking pipelines using the recently introduced 300VW benchmark. We evaluate many different architectures focusing mainly on the task of on-line deformable face tracking. In particular, we compare the following general strategies: (a) generic face detection plus generic facial landmark localisation, (b) generic model free tracking plus generic facial landmark localisation, as well as (c) hybrid approaches using state-of-the-art face detection, model free tracking and facial landmark localisation technologies. Our evaluation reveals future avenues for further research on the topic.