Search Results for author: Abhijit Mahalanobis

Found 7 papers, 1 papers with code

Background Invariant Classification on Infrared Imagery by Data Efficient Training and Reducing Bias in CNNs

no code implementations22 Jan 2022 Maliha Arif, Calvin Yong, Abhijit Mahalanobis

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

no code implementations IEEE International Conference on Image Processing 2021 Md Jibanul Haque Jiban, Shah Hassan, Abhijit Mahalanobis

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.

Compressing Deep CNNs using Basis Representation and Spectral Fine-tuning

1 code implementation21 May 2021 Muhammad Tayyab, Fahad Ahmad Khan, Abhijit Mahalanobis

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.

Image Classification Object Detection

Enhancing Visual Representations for Efficient Object Recognition during Online Distillation

no code implementations1 Jan 2021 Shashanka Venkataramanan, Bruce W McIntosh, Abhijit Mahalanobis

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.

Object Recognition Outlier Detection

Multiple View Generation and Classification of Mid-wave Infrared Images using Deep Learning

no code implementations18 Aug 2020 Maliha Arif, Abhijit Mahalanobis

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.

General Classification

Attention Guided Anomaly Localization in Images

no code implementations ECCV 2020 Shashanka Venkataramanan, Kuan-Chuan Peng, Rajat Vikram Singh, Abhijit Mahalanobis

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 #23 on Anomaly Detection on MVTec AD (Segmentation AUROC metric, using extra training data)

Anomaly Detection

BasisConv: A method for compressed representation and learning in CNNs

no code implementations11 Jun 2019 Muhammad Tayyab, Abhijit Mahalanobis

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).


Cannot find the paper you are looking for? You can Submit a new open access paper.