arXiv subjects

Ian Stavness

Publications and source records attributed to Ian Stavness.

24 records · Page 2Linked to original sources

arXiv2018

Improving Object Counting with Heatmap Regulation

In this paper, we propose a simple and effective way to improve one-look regression models for object counting from images. We use class activation map visualizations to illustrate the drawbacks of learning a pure one-look regression model for a counting task. Based on these insights, we enhance one-look regression counting models by regulating activation maps from the final convolution layer of the network with coarse ground-truth activation maps generated from simple dot annotations. We call this strategy heatmap regulation (HR). We show that this simple enhancement effectively suppresses false detections generated by the corresponding one-look baseline model and also improves the performance in terms of false negatives. Evaluations are performed on four different counting datasets --- two for car counting (CARPK, PUCPR+), one for crowd counting (WorldExpo) and another for biological cell counting (VGG-Cells). Adding HR to a simple VGG front-end improves performance on all these benchmarks compared to a simple one-look baseline model and results in state-of-the-art performance for car counting.

cs.CV↗

arXiv2018

Bridgeout: stochastic bridge regularization for deep neural networks

A major challenge in training deep neural networks is overfitting, i.e. inferior performance on unseen test examples compared to performance on training examples. To reduce overfitting, stochastic regularization methods have shown superior performance compared to deterministic weight penalties on a number of image recognition tasks. Stochastic methods such as Dropout and Shakeout, in expectation, are equivalent to imposing a ridge and elastic-net penalty on the model parameters, respectively. However, the choice of the norm of weight penalty is problem dependent and is not restricted to $\{L_1,L_2\}$. Therefore, in this paper we propose the Bridgeout stochastic regularization technique and prove that it is equivalent to an $L_q$ penalty on the weights, where the norm $q$ can be learned as a hyperparameter from data. Experimental results show that Bridgeout results in sparse model weights, improved gradients and superior classification performance compared to Dropout and Shakeout on synthetic and real datasets.

cs.NE↗

arXiv2018

DeepWheat: Estimating Phenotypic Traits from Crop Images with Deep Learning

In this paper, we investigate estimating emergence and biomass traits from color images and elevation maps of wheat field plots. We employ a state-of-the-art deconvolutional network for segmentation and convolutional architectures, with residual and Inception-like layers, to estimate traits via high dimensional nonlinear regression. Evaluation was performed on two different species of wheat, grown in field plots for an experimental plant breeding study. Our framework achieves satisfactory performance with mean and standard deviation of absolute difference of 1.05 and 1.40 counts for emergence and 1.45 and 2.05 for biomass estimation. Our results for counting wheat plants from field images are better than the accuracy reported for the similar, but arguably less difficult, task of counting leaves from indoor images of rosette plants. Our results for biomass estimation, even with a very small dataset, improve upon all previously proposed approaches in the literature.

cs.CV↗

arXiv2017

Leaf Counting with Deep Convolutional and Deconvolutional Networks

In this paper, we investigate the problem of counting rosette leaves from an RGB image, an important task in plant phenotyping. We propose a data-driven approach for this task generalized over different plant species and imaging setups. To accomplish this task, we use state-of-the-art deep learning architectures: a deconvolutional network for initial segmentation and a convolutional network for leaf counting. Evaluation is performed on the leaf counting challenge dataset at CVPPP-2017. Despite the small number of training samples in this dataset, as compared to typical deep learning image sets, we obtain satisfactory performance on segmenting leaves from the background as a whole and counting the number of leaves using simple data augmentation strategies. Comparative analysis is provided against methods evaluated on the previous competition datasets. Our framework achieves mean and standard deviation of absolute count difference of 1.62 and 2.30 averaged over all five test datasets.

cs.CV↗

arXiv2017

Prediction of Muscle Activations for Reaching Movements using Deep Neural Networks

The motor control problem involves determining the time-varying muscle activation trajectories required to accomplish a given movement. Muscle redundancy makes motor control a challenging task: there are many possible activation trajectories that accomplish the same movement. Despite this redundancy, most movements are accomplished in highly stereotypical ways. For example, point-to-point reaching movements are almost universally performed with very similar smooth trajectories. Optimization methods are commonly used to predict muscle forces for measured movements. However, these approaches require computationally expensive simulations and are sensitive to the chosen optimality criteria and regularization. In this work, we investigate deep autoencoders for the prediction of muscle activation trajectories for point-to-point reaching movements. We evaluate our DNN predictions with simulated reaches and two methods to generate the muscle activations: inverse dynamics (ID) and optimal control (OC) criteria. We also investigate optimal network parameters and training criteria to improve the accuracy of the predictions.

cs.NE↗

arXiv2013

A biomechanical modeling study of the effects of the orbicularis oris muscle and jaw posture on lip shape

Purpose: The authors' general aim is to use biomechanical models of speech articulators to explore how possible variations in anatomical structure contribute to differences in articulatory strategies and phone systems across human populations. Specifically, they investigated 2 issues: (a) the link between lip muscle anatomy and variability in lip gestures and (b) the constraints of coupled lip/jaw biomechanics on jaw posture in labial sounds. Method: The authors used a model coupling the jaw, tongue, and face. First, the influence of the orbicularis oris (OO) anatomical implementation was analyzed by assessing how changes in depth (from epidermis to the skull) and peripheralness (proximity to the lip horn center) affected lip shaping. Second, the capability of the lip/jaw system to generate protrusion and rounding, or labial closure, was evaluated for different jaw heights. Results: Results showed that a peripheral and moderately deep OO implementation is most appropriate for protrusion and rounding; a superficial implementation facilitates closure; protrusion and rounding require a high jaw position; and closure is achievable for various jaw heights. Conclusions: Models provide objective information regarding possible links between anatomical and speech production variability across humans. Comparisons with experimental data will illustrate how motor control and cultural factors cope with these constraints.

physics.med-ph↗