Visualizing Deep Similarity Networks

Stylianou, Abby; Souvenir, Richard; Pless, Robert

doi:10.1109/wacv.2019.00220

Cited by 49 publications

(28 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, we first needed to ascertain whether the difference images contained any useful information at all. Therefore, we used a similarity visualization technique [26] to visualize whether the difference image retained any useful information. Figure 7 depicts the visualization in terms of heatmaps (saliency maps) which shows that the difference images contain discriminative information which can be harnessed for decoding the second subject.…”

Section: Results From Experimentsmentioning

confidence: 99%

Conditional Identity Disentanglement for Differential Face Morph Detection

Banerjee¹,

Ross²

2021

Preprint

View full text Add to dashboard Cite

We present the task of differential face morph attack detection using a conditional generative network (cGAN). To determine whether a face image in an identification document, such as a passport, is morphed or not, we propose an algorithm that learns to implicitly disentangle identities from the morphed image conditioned on the trusted reference image using the cGAN. Furthermore, the proposed method can also recover some underlying information about the second subject used in generating the morph. We performed experiments on AMSL face morph, MorGAN, and EMorGAN datasets to demonstrate the effectiveness of the proposed method. We also conducted cross-dataset and cross-attack detection experiments. We obtained promising results of 3% BPCER @ 10% APCER on intra-dataset evaluation, which is comparable to existing methods; and 4.6% BPCER @ 10% APCER on cross-dataset evaluation, which outperforms state-of-the-art methods by at least 13.9%.

show abstract

Section: Results From Experimentsmentioning

confidence: 99%

Conditional Identity Disentanglement for Differential Face Morph Detection

Banerjee¹,

Ross²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…GradCAM [43] and CNN Fixation [28] are two popular methods to visualize CNNs, however, they are not designed for such pairwise networks as our ComplexIris-Net. The works in [45], [57] have proposed to decompose the last convolution activation to highlight the image regions that contribute the most to the overall matching score. We employ these frameworks to visualize and compare the last convolution activation of both complex-valued and realvalued iris networks.…”

Section: Visualizationmentioning

confidence: 99%

Complex-Valued Iris Recognition Network

Nguyen

Fookes

Sridharan

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

In this work, we design a fully complex-valued neural network for the task of iris recognition. Unlike the problem of general object recognition, where real-valued neural networks can be used to extract pertinent features, iris recognition depends on the extraction of both phase and amplitude information from the input iris texture in order to better represent its stochastic content. This necessitates the extraction and processing of phase information that cannot be effectively handled by a real-valued neural network. In this regard, we design a fully complex-valued neural network that can better capture the multi-scale, multi-resolution, and multi-orientation phase and amplitude features of the iris texture. We show a strong correspondence of the proposed complex-valued iris recognition network with Gabor wavelets that are used to generate the classical IrisCode; however, the proposed method enables a new capability of automatic complex-valued feature learning that is tailored for iris recognition. We conduct experiments on three benchmark datasets -ND-CrossSensor-2013, CASIA-Iris-Thousand and UBIRIS.v2 -and show the benefit of the proposed network for the task of iris recognition. We exploit visualization schemes to convey how the complex-valued network, when in comparison to standard real-valued networks, extract fundamentally different features from the iris texture.

show abstract

“…Each diagram shows a different XAI use case (clockwise, starting from the lower left): XAI as preprocessing (eg, explaining the data), XAI as part of the system (eg, inherently interpretable models), XAI as post-hoc explanation (eg, visual saliency maps), and XAI as a combination of all the previous methods been an increasing push to create explanations for other image understanding tasks, including object detection 17 and image similarity. [18][19][20][21][22] A notional architecture diagram for an analytics Domain Implementation is shown in Figure 6, here supporting saliency maps as an example. On the client side (right), the framework provides hooks for configuration, supplying lists of images, receiving lists of saliency maps, etc.…”

Section: Analytics Domain Implementationmentioning

confidence: 99%

XAITK: The explainable AI toolkit

Tunison

Vasu

et al. 2021

Applied AI Letters

View full text Add to dashboard Cite

Recent advances in artificial intelligence (AI), driven mainly by deep neural networks, have yielded remarkable progress in fields, such as computer vision, natural language processing, and reinforcement learning. Despite these successes, the inability to predict how AI systems will behave "in the wild" impacts almost all stages of planning and deployment, including research and development, verification and validation, and user trust and acceptance. The field of explainable artificial intelligence (XAI) seeks to develop techniques enabling AI algorithms to generate explanations of their results; generally these are human-interpretable representations or visualizations that are meant to "explain" how the system produced its outputs. We introduce the Explainable AI Toolkit (XAITK), a DARPA-sponsored effort that builds on results from the 4-year DARPA XAI program. The XAITK has two goals: (a) to consolidate research results from DARPA XAI into a single publicly accessible repository; and (b) to identify operationally relevant capabilities developed on DARPA XAI and assist in their transition to interested partners. We first describe the XAITK website and associated capabilities. These place the research results from DARPA XAI in the wider context of general research in the field of XAI, and include performer contributions of code, data, publications, and reports. We then describe the XAITK analytics and autonomy software frameworks. These are Python-based frameworks focused on particular XAI domains, and designed to provide a single integration endpoint for multiple algorithm implementations from across DARPA XAI. Each framework generalizes APIs for system-level data and control while providing a plugin interface for existing and future algorithm implementations. The XAITK project can be followed at: https://xaitk.org.

show abstract

Visualizing Deep Similarity Networks

Cited by 49 publications

References 21 publications

Conditional Identity Disentanglement for Differential Face Morph Detection

Conditional Identity Disentanglement for Differential Face Morph Detection

Complex-Valued Iris Recognition Network

XAITK: The explainable AI toolkit

Contact Info

Product

Resources

About