31 citations · 85 across the 18 of their papers we have counts for
24 papers
Latent Graph Attention for Enhanced Spatial Context
Ayush Singh, Yash Bhambhu, Himanshu Buckchash +2
Global contexts in images are quite valuable in image-to-image translation problems. Conventional attention-based and graph-based models capture the global context to a large exten…
One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning
Arnav Chavan, Zhuang Liu, Deepak Gupta +2
We present Generalized LoRA (GLoRA), an advanced approach for universal parameter-efficient fine-tuning tasks. Enhancing Low-Rank Adaptation (LoRA), GLoRA employs a generalized pro…
Data-Efficient Training of CNNs and Transformers with Coresets: A Stability Perspective
Animesh Gupta, Irtiza Hasan, Dilip K. Prasad +1
Coreset selection is among the most effective ways to reduce the training time of CNNs, however, only limited is known on how the resultant models will behave under variations of t…
Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropouts
Rohit Agarwal, Deepak Gupta, Alexander Horsch +1
Many real-world applications based on online learning produce streaming data that is haphazard in nature, i.e., contains missing features, features becoming obsolete in time, the a…
Patch Gradient Descent: Training Neural Networks on Very Large Images
Deepak K. Gupta, Gowreesh Mago, Arnav Chavan +1
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 constra…
On Using Deep Learning Proxies as Forward Models in Deep Learning Problems
Fatima Albreiki, Nidhal Belayouni, Deepak K. Gupta
Physics-based optimization problems are generally very time-consuming, especially due to the computational complexity associated with the forward model. Recent works have demonstra…
On Designing Light-Weight Object Trackers through Network Pruning: Use CNNs or Transformers?
Saksham Aggarwal, Taneesh Gupta, Pawan Kumar Sahu +4
Object trackers deployed on low-power devices need to be light-weight, however, most of the current state-of-the-art (SOTA) methods rely on using compute-heavy backbones built usin…
UltraMNIST Classification: A Benchmark to Train CNNs for Very Large Images
Deepak K. Gupta, Udbhav Bamba, Abhishek Thakur +4
Convolutional neural network (CNN) approaches available in the current literature are designed to work primarily with low-resolution images. When applied on very large images, chal…
Dynamic Kernel Selection for Improved Generalization and Memory Efficiency in Meta-learning
Arnav Chavan, Rishabh Tiwari, Udbhav Bamba +1
Gradient based meta-learning methods are prone to overfit on the meta-training set, and this behaviour is more prominent with large and complex networks. Moreover, large networks r…
Implicit Equivariance in Convolutional Networks
Naman Khetan, Tushar Arora, Samee Ur Rehman +1
Convolutional Neural Networks(CNN) are inherently equivariant under translations, however, they do not have an equivalent embedded mechanism to handle other transformations such as…
Livestock Monitoring with Transformer
Bhavesh Tangirala, Ishan Bhandari, Daniel Laszlo +3
Tracking the behaviour of livestock enables early detection and thus prevention of contagious diseases in modern animal farms. Apart from economic gains, this would reduce the amou…
Adaptive Neural Message Passing for Inductive Learning on Hypergraphs
Devanshu Arya, Deepak K. Gupta, Stevan Rudinac +1
Graphs are the most ubiquitous data structures for representing relational datasets and performing inferences in them. They model, however, only pairwise relations between nodes an…
Improving Solar Cell Metallization Designs using Convolutional Neural Networks
Sumit Bhattacharya, Devanshu Arya, Debjani Bhowmick +2
Optimizing the design of solar cell metallizations is one of the ways to improve the performance of solar cells. Recently, it has been shown that Topology Optimization (TO) can be…
ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations
Rishabh Tiwari, Udbhav Bamba, Arnav Chavan +1
Structured pruning methods are among the effective strategies for extracting small resource-efficient convolutional neural networks from their dense counterparts with minimal loss…
Rescaling CNN through Learnable Repetition of Network Parameters
Arnav Chavan, Udbhav Bamba, Rishabh Tiwari +1
Deeper and wider CNNs are known to provide improved performance for deep learning tasks. However, most such networks have poor performance gain per parameter increase. In this pape…
Rotation Equivariant Siamese Networks for Tracking
Deepak K. Gupta, Devanshu Arya, Efstratios Gavves
Rotation is among the long prevailing, yet still unresolved, hard challenges encountered in visual object tracking. The existing deep learning-based tracking algorithms use regular…
Siamese Tracking with Lingual Object Constraints
Maximilian Filtenborg, Efstratios Gavves, Deepak Gupta
Classically, visual object tracking involves following a target object throughout a given video, and it provides us the motion trajectory of the object. However, for many practical…
HyperSAGE: Generalizing Inductive Representation Learning on Hypergraphs
Devanshu Arya, Deepak K. Gupta, Stevan Rudinac +1
Graphs are the most ubiquitous form of structured data representation used in machine learning. They model, however, only pairwise relations between nodes and are not designed for…
Hard Occlusions in Visual Object Tracking
Thijs P. Kuipers, Devanshu Arya, Deepak K. Gupta
Visual object tracking is among the hardest problems in computer vision, as trackers have to deal with many challenging circumstances such as illumination changes, fast motion, occ…
Tackling Occlusion in Siamese Tracking with Structured Dropouts
Deepak K. Gupta, Efstratios Gavves, Arnold W. M. Smeulders
Occlusion is one of the most difficult challenges in object tracking to model. This is because unlike other challenges, where data augmentation can be of help, occlusion is hard to…
Calibrated Adversarial Refinement for Stochastic Semantic Segmentation
Elias Kassapis, Georgi Dikov, Deepak K. Gupta +1
In semantic segmentation tasks, input images can often have more than one plausible interpretation, thus allowing for multiple valid labels. To capture such ambiguities, recent wor…
Generating Annotated High-Fidelity Images Containing Multiple Coherent Objects
Bryan G. Cardenas, Devanshu Arya, Deepak K. Gupta
Recent developments related to generative models have made it possible to generate diverse high-fidelity images. In particular, layout-to-image generation models have gained signif…
Tracking-Assisted Segmentation of Biological Cells
Deepak K. Gupta, Nathan de Bruijn, Andreas Panteli +1
U-Net and its variants have been demonstrated to work sufficiently well in biological cell tracking and segmentation. However, these methods still suffer in the presence of complex…
Model Decay in Long-Term Tracking
Efstratios Gavves, Ran Tao, Deepak K. Gupta +1
Updating the tracker model with adverse bounding box predictions adds an unavoidable bias term to the learning. This bias term, which we refer to as model decay, offsets the learni…