Search Results for author: Saket Anand

Found 24 papers, 11 papers with code

Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders

5 code implementations ECCV 2018 Ananya Harsh Jha, Saket Anand, Maneesh Singh, V. S. R. Veeravasarapu

Our non-adversarial approach is in contrast with the recent works that combine adversarial training with auto-encoders to disentangle representations.

Data Augmentation

Contextual Diversity for Active Learning

1 code implementation ECCV 2020 Sharat Agarwal, Himanshu Arora, Saket Anand, Chetan Arora

Contextual Diversity (CD) hinges on a crucial observation that the probability vector predicted by a CNN for a region of interest typically contains information from a larger receptive field.

Active Learning Image Classification +3

Learning Hierarchy Aware Features for Reducing Mistake Severity

1 code implementation26 Jul 2022 Ashima Garg, Depanshu Sani, Saket Anand

In this paper, we propose a novel approach for learning Hierarchy Aware Features (HAF) that leverages classifiers at each level of the hierarchy that are constrained to generate predictions consistent with the label hierarchy.

REGroup: Rank-aggregating Ensemble of Generative Classifiers for Robust Predictions

1 code implementation18 Jun 2020 Lokender Tiwari, Anish Madan, Saket Anand, Subhashis Banerjee

Specifically, we devise an ensemble of these generative classifiers that rank-aggregates their predictions via a Borda count-based consensus.

Adversarial Attack

Does Data Repair Lead to Fair Models? Curating Contextually Fair Data To Reduce Model Bias

1 code implementation20 Oct 2021 Sharat Agarwal, Sumanyu Muku, Saket Anand, Chetan Arora

Through a series of experiments, we validate that curating contextually fair data helps make model predictions fair by balancing the true positive rate for the protected class across groups without compromising on the model's overall performance.

Active Learning Attribute +3

HIERMATCH: Leveraging Label Hierarchies for Improving Semi-Supervised Learning

1 code implementation30 Oct 2021 Ashima Garg, Shaurya Bagga, Yashvardhan Singh, Saket Anand

Additionally, HIERMATCH is a generic-approach to improve any semisupervised learning framework, we demonstrate this using our results on recent state-of-the-art techniques MixMatch and FixMatch.

Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain Shift

1 code implementation13 Oct 2022 Sharat Agarwal, Saket Anand, Chetan Arora

In this work, we propose an ADA strategy, which given a frame, identifies a set of classes that are hardest for the model to predict accurately, thereby recommending semantically meaningful regions to be annotated in a selected frame.

Active Learning Domain Adaptation +1

SICKLE: A Multi-Sensor Satellite Imagery Dataset Annotated with Multiple Key Cropping Parameters

1 code implementation29 Nov 2023 Depanshu Sani, Sandeep Mahato, Sourabh Saini, Harsh Kumar Agarwal, Charu Chandra Devshali, Saket Anand, Gaurav Arora, Thiagarajan Jayaraman

Out of the 2, 370 samples, 351 paddy samples from 145 plots are annotated with multiple crop parameters; such as the variety of paddy, its growing season and productivity in terms of per-acre yields.

Crop Type Mapping Crop Yield Prediction +3

Semi-Supervised Clustering with Neural Networks

no code implementations5 Jun 2018 Ankita Shukla, Gullal Singh Cheema, Saket Anand

Clustering using neural networks has recently demonstrated promising performance in machine learning and computer vision applications.

Clustering Deep Clustering +2

Unique Identification of Macaques for Population Monitoring and Control

no code implementations2 Nov 2018 Ankita Shukla, Gullal Singh Cheema, Saket Anand, Qamar Qureshi, Yadvendradev Jhala

Despite loss of natural habitat due to development and urbanization, certain species like the Rhesus macaque have adapted well to the urban environment.

Face Identification

Geometry of Deep Generative Models for Disentangled Representations

no code implementations19 Feb 2019 Ankita Shukla, Shagun Uppal, Sarthak Bhagat, Saket Anand, Pavan Turaga

We use several metrics to compare the properties of latent spaces of disentangled representation models in terms of class separability and curvature of the latent-space.

Representation Learning

Primate Face Identification in the Wild

no code implementations3 Jul 2019 Ankita Shukla, Gullal Singh Cheema, Saket Anand, Qamar Qureshi, Yadvendradev Jhala

This loss of habitat has skewed the population of several non-human primate species like chimpanzees and macaques and has constrained them to co-exist in close proximity of human settlements, often leading to human-wildlife conflicts while competing for resources.

Face Identification Management +1

Product of Orthogonal Spheres Parameterization for Disentangled Representation Learning

no code implementations22 Jul 2019 Ankita Shukla, Sarthak Bhagat, Shagun Uppal, Saket Anand, Pavan Turaga

Learning representations that can disentangle explanatory attributes underlying the data improves interpretabilty as well as provides control on data generation.

Disentanglement

Intelligent Querying for Target Tracking in Camera Networks using Deep Q-Learning with n-Step Bootstrapping

no code implementations20 Apr 2020 Anil Sharma, Saket Anand, Sanjit K. Kaul

Surveillance camera networks are a useful infrastructure for various visual analytics applications, where high-level inferences and predictions could be made based on target tracking across the network.

Q-Learning Scheduling

Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction

1 code implementation ECCV 2020 Lokender Tiwari, Pan Ji, Quoc-Huy Tran, Bingbing Zhuang, Saket Anand, Manmohan Chandraker

Classical monocular Simultaneous Localization And Mapping (SLAM) and the recently emerging convolutional neural networks (CNNs) for monocular depth prediction represent two largely disjoint approaches towards building a 3D map of the surrounding environment.

Depth Estimation Depth Prediction +1

GraCIAS: Grassmannian of Corrupted Images for Adversarial Security

no code implementations6 May 2020 Ankita Shukla, Pavan Turaga, Saket Anand

In this work, we propose a defense strategy that applies random image corruptions to the input image alone, constructs a self-correlation based subspace followed by a projection operation to suppress the adversarial perturbation.

Automatic Detection and Recognition of Individuals in Patterned Species

no code implementations6 May 2020 Gullal Singh Cheema, Saket Anand

In this work, we develop a framework for automatic detection and recognition of individuals in different patterned species like tigers, zebras and jaguars.

object-detection Object Detection

DGSAC: Density Guided Sampling and Consensus

no code implementations3 Jun 2020 Lokender Tiwari, Saket Anand

Unlike mode seeking approaches, our model selection algorithms seek to find one representative hypothesis for each genuine structure present in the data.

Clustering Model Selection +1

A Deep Learning Approach To Estimation Using Measurements Received Over a Network

no code implementations20 Jan 2022 Shivangi Agarwal, Sanjit K. Kaul, Saket Anand, P. B. Sujit

The measurements are communicated over a network as packets, at a rate unknown to the estimator.

High-Resolution Satellite Imagery for Modeling the Impact of Aridification on Crop Production

no code implementations25 Sep 2022 Depanshu Sani, Sandeep Mahato, Parichya Sirohi, Saket Anand, Gaurav Arora, Charu Chandra Devshali, Thiagarajan Jayaraman, Harsh Kumar Agarwal

We also propose a yield prediction strategy that uses time-series data generated based on the observed growing season and the standard seasonal information obtained from Tamil Nadu Agricultural University for the region.

Time Series Time Series Analysis

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