Search Results for author:
Found 8 papers, 1 papers with code
Compressing Deep CNNs using Basis Representation and Spectral Fine-tuning
We propose an efficient and straightforward method for compressing deep convolutional neural networks (CNNs) that uses basis filters to represent the convolutional layers, and optimizes the performance of the compressed network directly in the basis space.
BasisConv: A method for compressed representation and learning in CNNs
Specifically, any convolution layer of the CNN is easily replaced by two successive convolution layers: the first is a set of fixed filters (that represent the knowledge space of the entire layer and do not change), which is followed by a layer of one-dimensional filters (that represent the learned knowledge in this space).
Attention Guided Anomaly Localization in Images
Without the need of anomalous training images, we propose Convolutional Adversarial Variational autoencoder with Guided Attention (CAVGA), which localizes the anomaly with a convolutional latent variable to preserve the spatial information.
Ranked #74 on
Anomaly Detection
on MVTec AD
(Segmentation AUROC metric)
Multiple View Generation and Classification of Mid-wave Infrared Images using Deep Learning
We further explore the non-linear feature subspace and conclude that our network does not operate in the Euclidean subspace but rather in the Riemannian subspace.
Enhancing Visual Representations for Efficient Object Recognition during Online Distillation
Exploiting this fact, we aim to reduce the computations of our framework by employing a binary student network (BSN) to learn the frequently occurring classes using the pseudo-labels generated by the teacher network (TN) on an unlabeled image stream.
Background Invariant Classification on Infrared Imagery by Data Efficient Training and Reducing Bias in CNNs
Even though convolutional neural networks can classify objects in images very accurately, it is well known that the attention of the network may not always be on the semantically important regions of the scene.
Two-Stream Boosted TCRNet for Range-Tolerant Infra-Red Target Detection
The detection of vehicular targets in infra-red imagery is a challenging task, both due to the relatively few pixels on target and the false alarms produced by the surrounding terrain clutter.
Improving Replay Sample Selection and Storage for Less Forgetting in Continual Learning
Continual learning seeks to enable deep learners to train on a series of tasks of unknown length without suffering from the catastrophic forgetting of previous tasks.
