Christopher Sweet
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Christopher Sweet has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Adam Czajka
University of Notre Dame
2 shared publications - Jacob Piland
Department of Computer Science and Engineering University of Notre Dame Notre Dame 46556 IN
2 shared publications - Aidan Boyd
University of Notre Dame, Notre Dame, IN, USA
1 shared publication - Colton R. Crum
Department of Computer Science and Engineering University of Notre Dame IN USA
1 shared publication - James Sweet
Department of Computer Science and Engineering
1 shared publication - Jesús A. Izaguirre
Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN 46556, USA
1 shared publication
Latest Publications
- Open Access
Explain To Me: Salience-Based Explainability for Synthetic Face Detection Models
The performance of convolutional neural networks has continued to improve over the last decade. At the same time, as model complexity grows, it becomes increasingly more difficult to explain model decisions. Such explanations may be of critical importance for reliable operation of human-machine pairing setups, or for model selection when the "best" model among many equally-accurate models must be established. Saliency maps represent one popular way of explaining model decisions by highlighting image regions models deem important when making a prediction. However, examining salience maps at scale is not practical. In this paper, we propose five novel methods of leveraging model salience to explain a model behavior at scale. These methods ask: (a) what is the average entropy for a model's salience maps, (b) how does model salience change when fed out-of-set samples, (c) how closely does model salience follow geometrical transformations, (d) what is the stability of model salience across independent training runs, and (e) how does model salience react to salience-guided image degradations. To assess the proposed measures on a concrete and topical problem, we conducted a series of experiments for the task of synthetic face detection with two types of models: those trained traditionally with cross-entropy loss, and those guided by human salience when training to increase model generalizability. These two types of models are characterized by different, interpretable properties of their salience maps, which allows for the evaluation of the correctness of the proposed measures. We offer source codes for each measure along with this paper.
Open AccessExplain To Me: Salience-Based Explainability for Synthetic Face Detection Models
The performance of convolutional neural networks has continued to improve over the last decade. At the same time, as model complexity grows, it becomes increasingly more difficult to explain model decisions. Such explanations may be of critical importance for reliable operation of human-machine pairing setups, or for model selection when the "best" model among many equally-accurate models must be established. Saliency maps represent one popular way of explaining model decisions by highlighting image regions models deem important when making a prediction. However, examining salience maps at scale is not practical. In this paper, we propose five novel methods of leveraging model salience to explain a model behavior at scale. These methods ask: (a) what is the average entropy for a model's salience maps, (b) how does model salience change when fed out-of-set samples, (c) how closely does model salience follow geometrical transformations, (d) what is the stability of model salience across independent training runs, and (e) how does model salience react to salience-guided image degradations. To assess the proposed measures on a concrete and topical problem, we conducted a series of experiments for the task of synthetic face detection with two types of models: those trained traditionally with cross-entropy loss, and those guided by human salience when training to increase model generalizability. These two types of models are characterized by different, interpretable properties of their salience maps, which allows for the evaluation of the correctness of the proposed measures. We offer source codes for each measure along with this paper.
- Open Access
Improving Model's Focus Improves Performance of Deep Learning-Based Synthetic Face Detectors
Deep learning-based models generalize better to unknown data samples after being guided "where to look" by incorporating human perception into training strategies. We made an observation that the entropy of the model's salience trained in that way is lower when compared to salience entropy computed for models training without human perceptual intelligence. Thus the question: does further increase of model's focus, by lowering the entropy of model's class activation map, help in further increasing the performance? In this paper we propose and evaluate several entropy-based new loss function components controlling the model's focus, covering the full range of the level of such control, from none to its "aggressive" minimization. We show, using a problem of synthetic face detection, that improving the model's focus, through lowering entropy, leads to models that perform better in an open-set scenario, in which the test samples are synthesized by unknown generative models. We also show that optimal performance is obtained when the model's loss function blends three aspects: regular classification, low-entropy of the model's focus, and human-guided saliency.
Open AccessImproving Model's Focus Improves Performance of Deep Learning-Based Synthetic Face Detectors
Deep learning-based models generalize better to unknown data samples after being guided "where to look" by incorporating human perception into training strategies. We made an observation that the entropy of the model's salience trained in that way is lower when compared to salience entropy computed for models training without human perceptual intelligence. Thus the question: does further increase of model's focus, by lowering the entropy of model's class activation map, help in further increasing the performance? In this paper we propose and evaluate several entropy-based new loss function components controlling the model's focus, covering the full range of the level of such control, from none to its "aggressive" minimization. We show, using a problem of synthetic face detection, that improving the model's focus, through lowering entropy, leads to models that perform better in an open-set scenario, in which the test samples are synthesized by unknown generative models. We also show that optimal performance is obtained when the model's loss function blends three aspects: regular classification, low-entropy of the model's focus, and human-guided saliency.
- Open Access
Visual Recognition of Paper Analytical Device Images for Detection of Falsified Pharmaceuticals
Falsification of medicines is a big problem in many developing countries, where technological infrastructure is inadequate to detect these harmful products. We have developed a set of inexpensive paper cards, called Paper Analytical Devices (PADs), which can efficiently classify drugs based on their chemical composition, as a potential solution to the problem. These cards have different reagents embedded in them which produce a set of distinctive color descriptors upon reacting with the chemical compounds that constitute pharmaceutical dosage forms. If a falsified version of the medicine lacks the active ingredient or includes substitute fillers, the difference in color is perceivable by humans. However, reading the cards with accuracy takes training and practice, which may hamper their scaling and implementation in low resource settings. To deal with this, we have developed an automatic visual recognition system to read the results from the PAD images. At first, the optimal set of reagents was found by running singular value decomposition on the intensity values of the color tones in the card images. A dataset of cards embedded with these reagents is produced to generate the most distinctive results for a set of 26 different active pharmaceutical ingredients (APIs) and excipients. Then, we train two popular convolutional neural network (CNN) models, with the card images. We also extract some "hand-crafted" features from the images and train a nearest neighbor classifier and a non-linear support vector machine with them. On testing, higher-level features performed much better in accurately classifying the PAD images, with the CNN models reaching the highest average accuracy of over 94\%.
Open AccessVisual Recognition of Paper Analytical Device Images for Detection of Falsified Pharmaceuticals
Falsification of medicines is a big problem in many developing countries, where technological infrastructure is inadequate to detect these harmful products. We have developed a set of inexpensive paper cards, called Paper Analytical Devices (PADs), which can efficiently classify drugs based on their chemical composition, as a potential solution to the problem. These cards have different reagents embedded in them which produce a set of distinctive color descriptors upon reacting with the chemical compounds that constitute pharmaceutical dosage forms. If a falsified version of the medicine lacks the active ingredient or includes substitute fillers, the difference in color is perceivable by humans. However, reading the cards with accuracy takes training and practice, which may hamper their scaling and implementation in low resource settings. To deal with this, we have developed an automatic visual recognition system to read the results from the PAD images. At first, the optimal set of reagents was found by running singular value decomposition on the intensity values of the color tones in the card images. A dataset of cards embedded with these reagents is produced to generate the most distinctive results for a set of 26 different active pharmaceutical ingredients (APIs) and excipients. Then, we train two popular convolutional neural network (CNN) models, with the card images. We also extract some "hand-crafted" features from the images and train a nearest neighbor classifier and a non-linear support vector machine with them. On testing, higher-level features performed much better in accurately classifying the PAD images, with the CNN models reaching the highest average accuracy of over 94\%.
- Open Access
- 1 October 2009
- Published by World Scientific Pub Co Pte Ltd
- p. 240-251
MULTISCALE DYNAMICS OF MACROMOLECULES USING NORMAL MODE LANGEVIN
Proteins and other macromolecules have coupled dynamics over multiple time scales (from femtosecond to millisecond and beyond) that make resolving molecular dynamics challenging. We present an approach based on periodically decomposing the dynamics of a macromolecule into slow and fast modes based on a scalable coarse-grained normal mode analysis. A Langevin equation is used to propagate the slowest degrees of freedom while minimizing the nearly instantaneous degrees of freedom. We present numerical results showing that time steps of up to 1000 fs can be used, with real speedups of up to 200 times over plain molecular dynamics. We present results of successfully folding the Fip35 mutant of WW domain.
- 1 October 2009
- Published by World Scientific Pub Co Pte Ltd
- p. 240-251
Open AccessMULTISCALE DYNAMICS OF MACROMOLECULES USING NORMAL MODE LANGEVIN
Proteins and other macromolecules have coupled dynamics over multiple time scales (from femtosecond to millisecond and beyond) that make resolving molecular dynamics challenging. We present an approach based on periodically decomposing the dynamics of a macromolecule into slow and fast modes based on a scalable coarse-grained normal mode analysis. A Langevin equation is used to propagate the slowest degrees of freedom while minimizing the nearly instantaneous degrees of freedom. We present numerical results showing that time steps of up to 1000 fs can be used, with real speedups of up to 200 times over plain molecular dynamics. We present results of successfully folding the Fip35 mutant of WW domain.