• Publications
  • Influence
Pruning Convolutional Neural Networks for Resource Efficient Inference
TLDR
It is shown that pruning can lead to more than 10x theoretical (5x practical) reduction in adapted 3D-convolutional filters with a small drop in accuracy in a recurrent gesture classifier.
Online Detection and Classification of Dynamic Hand Gestures with Recurrent 3D Convolutional Neural Networks
TLDR
A recurrent three-dimensional convolutional neural network that performs simultaneous detection and classification of dynamic hand gestures from multi-modal data and achieves state-of-the-art performance on SKIG and ChaLearn2014 benchmarks.
Pruning Convolutional Neural Networks for Resource Efficient Transfer Learning
TLDR
A new criterion based on an efficient first-order Taylor expansion to approximate the absolute change in training cost induced by pruning a network component is proposed, demonstrating superior performance compared to other criteria, such as the norm of kernel weights or average feature map activation.
Dreaming to Distill: Data-Free Knowledge Transfer via DeepInversion
TLDR
DeepInversion is introduced, a new method for synthesizing images from the image distribution used to train a deep neural network, which optimizes the input while regularizing the distribution of intermediate feature maps using information stored in the batch normalization layers of the teacher.
Importance Estimation for Neural Network Pruning
TLDR
A novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively removes those with smaller scores and two variations of this method using the first and second-order Taylor expansions to approximate a filter's contribution are described.
Hand Pose Estimation via Latent 2.5D Heatmap Regression
TLDR
This paper proposes a new method for 3D hand pose estimation from a monocular image through a novel 2.5D pose representation that implicitly learns depth maps and heatmap distributions with a novel CNN architecture.
Hand gesture recognition with 3D convolutional neural networks
TLDR
An algorithm for drivers' hand gesture recognition from challenging depth and intensity data using 3D convolutional neural networks using spatio-temporal data augmentation for more effective training and to reduce potential overfitting.
SCOPS: Self-Supervised Co-Part Segmentation
TLDR
This work proposes a self-supervised deep learning approach for part segmentation, where several loss functions are devised that aids in predicting part segments that are geometrically concentrated, robust to object variations and are also semantically consistent across different object instances.
Improving Landmark Localization with Semi-Supervised Learning
TLDR
Two techniques to improve landmark localization in images from partially annotated datasets are presented and it is shown that these techniques, improve landmark prediction considerably and can learn effective detectors even when only a small fraction of the dataset has landmark labels.
Few-Shot Adaptive Gaze Estimation
TLDR
Faze learns a rotation-aware latent representation of gaze via a disentangling encoder-decoder architecture along with a highly adaptable gaze estimator trained using meta-learning, capable of adapting to any new person to yield significant performance gains with as few as 3 samples.
...
1
2
3
4
5
...