Search Results for author: Deepak K. Gupta

Found 23 papers, 9 papers with code

Latent Graph Attention for Enhanced Spatial Context

no code implementations9 Jul 2023 Ayush Singh, Yash Bhambhu, Himanshu Buckchash, Deepak K. Gupta, Dilip K. Prasad

In this paper, we present Latent Graph Attention (LGA) a computationally inexpensive (linear to the number of nodes) and stable, modular framework for incorporating the global context in the existing architectures, especially empowering small-scale architectures to give performance closer to large size architectures, thus making the light-weight architectures more useful for edge devices with lower compute power and lower energy needs.

Graph Attention Image Restoration +3

Data-Efficient Training of CNNs and Transformers with Coresets: A Stability Perspective

1 code implementation3 Mar 2023 Animesh Gupta, Irtiza Hasan, Dilip K. Prasad, Deepak K. Gupta

We further show that when no pretraining is done or when the pretrained transformer models are used with non-natural images (e. g. medical data), CNNs tend to generalize better than transformers at even very small coreset sizes.

Benchmarking Image Classification +1

Patch Gradient Descent: Training Neural Networks on Very Large Images

no code implementations31 Jan 2023 Deepak K. Gupta, Gowreesh Mago, Arnav Chavan, Dilip K. Prasad

Traditional CNN models are trained and tested on relatively low resolution images (<300 px), and cannot be directly operated on large-scale images due to compute and memory constraints.

On Using Deep Learning Proxies as Forward Models in Deep Learning Problems

1 code implementation16 Jan 2023 Fatima Albreiki, Nidhal Belayouni, Deepak K. Gupta

The correctness of the approximate model depends on the extent of sampling conducted in the parameter space, and through numerical experiments, we demonstrate that caution needs to be taken when constructing this landscape with neural networks.

On Designing Light-Weight Object Trackers through Network Pruning: Use CNNs or Transformers?

1 code implementation24 Nov 2022 Saksham Aggarwal, Taneesh Gupta, Pawan Kumar Sahu, Arnav Chavan, Rishabh Tiwari, Dilip K. Prasad, Deepak K. Gupta

A comparison between SOTA trackers using CNNs, transformers as well as the combination of the two is presented to study their stability at various compression ratios.

Network Pruning Object +1

Partial Binarization of Neural Networks for Budget-Aware Efficient Learning

no code implementations12 Nov 2022 Udbhav Bamba, Neeraj Anand, Saksham Aggarwal, Dilip K. Prasad, Deepak K. Gupta

To address this issue, partial binarization techniques have been developed, but a systematic approach to mixing binary and full-precision parameters in a single network is still lacking.

Binarization Neural Network Compression +1

UltraMNIST Classification: A Benchmark to Train CNNs for Very Large Images

no code implementations25 Jun 2022 Deepak K. Gupta, Udbhav Bamba, Abhishek Thakur, Akash Gupta, Suraj Sharan, Ertugrul Demir, Dilip K. Prasad

Based on the outlined issues, we introduce a novel research problem of training CNN models for very large images, and present 'UltraMNIST dataset', a simple yet representative benchmark dataset for this task.

Semantic correspondence

Dynamic Kernel Selection for Improved Generalization and Memory Efficiency in Meta-learning

1 code implementation CVPR 2022 Arnav Chavan, Rishabh Tiwari, Udbhav Bamba, Deepak K. Gupta

MetaDOCK compresses the meta-model as well as the task-specific inner models, thus providing significant reduction in model size for each task, and through constraining the number of active kernels for every task, it implicitly mitigates the issue of meta-overfitting.

Meta-Learning

Implicit Equivariance in Convolutional Networks

1 code implementation28 Nov 2021 Naman Khetan, Tushar Arora, Samee Ur Rehman, Deepak K. Gupta

Several approaches exist that make CNNs equivariant under other transformation groups by design.

Visual Object Tracking

Livestock Monitoring with Transformer

no code implementations1 Nov 2021 Bhavesh Tangirala, Ishan Bhandari, Daniel Laszlo, Deepak K. Gupta, Rajat M. Thomas, Devanshu Arya

Given these challenges, we develop an end-to-end behaviour monitoring system for group-housed pigs to perform simultaneous instance level segmentation, tracking, action recognition and re-identification (STAR) tasks.

Action Recognition Benchmarking

Adaptive Neural Message Passing for Inductive Learning on Hypergraphs

no code implementations22 Sep 2021 Devanshu Arya, Deepak K. Gupta, Stevan Rudinac, Marcel Worring

Most hypergraph learning approaches convert the hypergraph structure to that of a graph and then deploy existing geometric deep learning methods.

ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations

1 code implementation ICLR 2021 Rishabh Tiwari, Udbhav Bamba, Arnav Chavan, Deepak K. Gupta

Structured pruning methods are among the effective strategies for extracting small resource-efficient convolutional neural networks from their dense counterparts with minimal loss in accuracy.

Rotation Equivariant Siamese Networks for Tracking

2 code implementations CVPR 2021 Deepak K. Gupta, Devanshu Arya, Efstratios Gavves

We further show that this change in orientation can be used to impose an additional motion constraint in Siamese tracking through imposing restriction on the change in orientation between two consecutive frames.

2D Pose Estimation Benchmarking +2

Hard Occlusions in Visual Object Tracking

no code implementations10 Sep 2020 Thijs P. Kuipers, Devanshu Arya, Deepak K. Gupta

A tracker is assessed to be good or not based on its performance on the recent tracking datasets, e. g., VOT2019, and LaSOT.

Object Visual Object Tracking

Calibrated Adversarial Refinement for Stochastic Semantic Segmentation

3 code implementations ICCV 2021 Elias Kassapis, Georgi Dikov, Deepak K. Gupta, Cedric Nugteren

To this end, we propose a novel two-stage, cascaded approach for calibrated adversarial refinement: (i) a standard segmentation network is trained with categorical cross entropy to predict a pixelwise probability distribution over semantic classes and (ii) an adversarially trained stochastic network is used to model the inter-pixel correlations to refine the output of the first network into coherent samples.

Semantic Segmentation valid

Generating Annotated High-Fidelity Images Containing Multiple Coherent Objects

1 code implementation22 Jun 2020 Bryan G. Cardenas, Devanshu Arya, Deepak K. Gupta

In particular, layout-to-image generation models have gained significant attention due to their capability to generate realistic complex images containing distinct objects.

Layout-to-Image Generation Vocal Bursts Intensity Prediction

Fusing Structural and Functional MRIs using Graph Convolutional Networks for Autism Classification

no code implementations MIDL 2019 Devanshu Arya, Richard Olij, Deepak K. Gupta, Ahmed El Gazzar, Guido van Wingen, Marcel Worring, Rajat Mani Thomas

We alleviate the use of such non-imaging metadata and propose a fully imaging-based approach where information from structural and functional Magnetic Resonance Imaging (MRI) data are fused to construct the edges and nodes of the graph.

Disease Prediction

Siamese Tracking of Cell Behaviour Patterns

no code implementations MIDL 2019 Andreas Panteli, Deepak K. Gupta, Nathan de Bruin, Efstratios Gavves

Tracking and segmentation of biological cells in video sequences is a challenging problem, especially due to the similarity of the cells and high levels of inherent noise.

Cell Tracking Segmentation

Tracking-Assisted Segmentation of Biological Cells

no code implementations19 Oct 2019 Deepak K. Gupta, Nathan de Bruijn, Andreas Panteli, Efstratios Gavves

U-Net and its variants have been demonstrated to work sufficiently well in biological cell tracking and segmentation.

Cell Tracking Segmentation

Model Decay in Long-Term Tracking

no code implementations5 Aug 2019 Efstratios Gavves, Ran Tao, Deepak K. Gupta, Arnold W. M. Smeulders

Updating the tracker model with adverse bounding box predictions adds an unavoidable bias term to the learning.

Unsupervised Automated Event Detection using an Iterative Clustering based Segmentation Approach

no code implementations22 Jan 2019 Deepak K. Gupta, Rohit K. Shrivastava, Suhas Phadke, Jeroen Goudswaard

The ICS approach consists of a few hyper-parameters that have been chosen based on statistical study performed over a set of test images.

Clustering Event Detection +2

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