Author name cluster

Bharat Singh

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

TCS Journal 2023 Journal Article

Deep learning and natural language processing in computation for offensive language detection in online social networks by feature selection and ensemble classification techniques

M. Anand
Kishan Bhushan Sahay
Mohammed Altaf Ahmed
Daniyar Sultan
Radha Raman Chandan
Bharat Singh

Offensive communications have made their way into social media posts. Using computational algorithms to distinguish objectionable content is one of the most effective ways to deal with this problem. One of the most effective approaches to deal with this issue is to use computational methods to distinguish undesirable content. This research aims to tackle MOLD_DL (Multilingual Offensive Language Detection using deep learning) techniques and natural language processing used in feature selection and classification. Here the dataset has been collected from YouTube, Twitter and Facebook, which has been pre-processed for noise removal, filtering and removing the stop words and segmented. The feature selection has been carried out for segmented data using Fuzzy based convolutional neural network (FCNN). Then the extraction of selected features and classification has been carried out using ensemble architecture of Bi-LSTM model with Naïve Bayes architecture hybrid with Support Vector Machines (SVM). Evaluation of offensive language detection is classified automatically based on the emotions of the text. Here the experimental analysis has been carried out for YouTube, Twitter and Facebook datasets in terms of accuracy of 98%, precision of 95%, recall of 90%, F-1 score of 92. 5% and RMSE of 45% with the confusion matrix in detecting offensive text of various languages.

Details DOI

AAAI Conference 2020 Conference Paper

Recognizing Instagram Filtered Images with Feature De-Stylization

Zhe Wu
Zuxuan Wu
Bharat Singh
Larry Davis

Deep neural networks have been shown to suffer from poor generalization when small perturbations are added (like Gaussian noise), yet little work has been done to evaluate their robustness to more natural image transformations like photo ﬁlters. This paper presents a study on how popular pretrained models are affected by commonly used Instagram ﬁlters. To this end, we introduce ImageNet-Instagram, a ﬁltered version of ImageNet, where 20 popular Instagram ﬁlters are applied to each image in ImageNet. Our analysis suggests that simple structure preserving ﬁlters which only alter the global appearance of an image can lead to large differences in the convolutional feature space. To improve generalization, we introduce a lightweight de-stylization module that predicts parameters used for scaling and shifting feature maps to “undo” the changes incurred by ﬁlters, inverting the process of style transfer tasks. We further demonstrate the module can be readily plugged into modern CNN architectures together with skip connections. We conduct extensive studies on ImageNet-Instagram, and show quantitatively and qualitatively, that the proposed module, among other things, can effectively improve generalization by simply learning normalization parameters without retraining the entire network, thus recovering the alterations in the feature space caused by the ﬁlters.

PDF Details

AAAI Conference 2018 Conference Paper

Deception Detection in Videos

Zhe Wu
Bharat Singh
Larry Davis
V. Subrahmanian

We present a system for covert automated deception detection using information available in a video. We study the importance of different modalities like vision, audio and text for this task. On the vision side, our system uses classiﬁers trained on low level video features which predict human microexpressions. We show that predictions of high-level microexpressions can be used as features for deception prediction. Surprisingly, IDT (Improved Dense Trajectory) features which have been widely used for action recognition, are also very good at predicting deception in videos. We fuse the score of classiﬁers trained on IDT features and high-level microexpressions to improve performance. MFCC (Mel-frequency Cepstral Coefﬁcients) features from the audio domain also provide a signiﬁcant boost in performance, while information from transcripts is not very beneﬁcial for our system. Using various classiﬁers, our automated system obtains an AUC of 0. 877 (10-fold cross-validation) when evaluated on subjects which were not part of the training set. Even though state-ofthe-art methods use human annotations of micro-expressions for deception detection, our fully automated approach outperforms them by 5%. When combined with human annotations of micro-expressions, our AUC improves to 0. 922. We also present results of a user-study to analyze how well do average humans perform on this task, what modalities they use for deception detection and how they perform if only one modality is accessible.

PDF Details

NeurIPS Conference 2018 Conference Paper

SNIPER: Efficient Multi-Scale Training

Bharat Singh
Mahyar Najibi
Larry Davis

We present SNIPER, an algorithm for performing efficient multi-scale training in instance level visual recognition tasks. Instead of processing every pixel in an image pyramid, SNIPER processes context regions around ground-truth instances (referred to as chips) at the appropriate scale. For background sampling, these context-regions are generated using proposals extracted from a region proposal network trained with a short learning schedule. Hence, the number of chips generated per image during training adaptively changes based on the scene complexity. SNIPER only processes 30% more pixels compared to the commonly used single scale training at 800x1333 pixels on the COCO dataset. But, it also observes samples from extreme resolutions of the image pyramid, like 1400x2000 pixels. As SNIPER operates on resampled low resolution chips (512x512 pixels), it can have a batch size as large as 20 on a single GPU even with a ResNet-101 backbone. Therefore it can benefit from batch-normalization during training without the need for synchronizing batch-normalization statistics across GPUs. SNIPER brings training of instance level recognition tasks like object detection closer to the protocol for image classification and suggests that the commonly accepted guideline that it is important to train on high resolution images for instance level visual recognition tasks might not be correct. Our implementation based on Faster-RCNN with a ResNet-101 backbone obtains an mAP of 47. 6% on the COCO dataset for bounding box detection and can process 5 images per second during inference with a single GPU. Code is available at https: //github. com/MahyarNajibi/SNIPER/.

PDF Details

ICML Conference 2016 Conference Paper

Training Neural Networks Without Gradients: A Scalable ADMM Approach

Gavin Taylor
Ryan Burmeister
Zheng Xu 0002
Bharat Singh
Ankit B. Patel
Tom Goldstein

With the growing importance of large network models and enormous training datasets, GPUs have become increasingly necessary to train neural networks. This is largely because conventional optimization algorithms rely on stochastic gradient methods that don’t scale well to large numbers of cores in a cluster setting. Furthermore, the convergence of all gradient methods, including batch methods, suffers from common problems like saturation effects, poor conditioning, and saddle points. This paper explores an unconventional training method that uses alternating direction methods and Bregman iteration to train networks without gradient descent steps. The proposed method reduces the network training problem to a sequence of minimization sub-steps that can each be solved globally in closed form. The proposed method is advantageous because it avoids many of the caveats that make gradient methods slow on highly non-convex problems. In addition, the method exhibits strong scaling in the distributed setting, yielding linear speedups even when split over thousands of cores.

Details