62 citations · 153 across the 45 of their papers we have counts for
24 papers · 1 filter
Foveation-Guided Dynamic Token Selection for Robust and Efficient Vision Transformers
Ibrahim Batuhan Akkaya, Kishaan Jeeveswaran, Bahram Zonooz +1
The human visual system (HVS) employs foveated sampling and eye movements to achieve efficient perception, conserving both metabolic energy and computational resources. Drawing ins…
PhysVid: Physics Aware Local Conditioning for Generative Video Models
Saurabh Pathak, Elahe Arani, Mykola Pechenizkiy +1
Generative video models achieve high visual fidelity but often violate basic physical principles, limiting reliability in real-world settings. Prior attempts to inject physics rely…
Depth3DLane: Fusing Monocular 3D Lane Detection with Self-Supervised Monocular Depth Estimation
Max van den Hoven, Kishaan Jeeveswaran, Pieter Piscaer +3
Monocular 3D lane detection is essential for autonomous driving, but challenging due to the inherent lack of explicit spatial information. Multi-modal approaches rely on expensive…
Can We Break Free from Strong Data Augmentations in Self-Supervised Learning?
Shruthi Gowda, Elahe Arani, Bahram Zonooz
Self-supervised learning (SSL) has emerged as a promising solution for addressing the challenge of limited labeled data in deep neural networks (DNNs), offering scalability potenti…
Transformers in Unsupervised Structure-from-Motion
Hemang Chawla, Arnav Varma, Elahe Arani +1
Transformers have revolutionized deep learning based computer vision with improved performance as well as robustness to natural corruptions and adversarial attacks. Transformers ar…
Continual Learning of Unsupervised Monocular Depth from Videos
Hemang Chawla, Arnav Varma, Elahe Arani +1
Spatial scene understanding, including monocular depth estimation, is an important problem in various applications, such as robotics and autonomous driving. While improvements in u…
Dual Cognitive Architecture: Incorporating Biases and Multi-Memory Systems for Lifelong Learning
Shruthi Gowda, Bahram Zonooz, Elahe Arani
Artificial neural networks (ANNs) exhibit a narrow scope of expertise on stationary independent data. However, the data in the real world is continuous and dynamic, and ANNs must a…
Enhancing Performance of Vision Transformers on Small Datasets through Local Inductive Bias Incorporation
Ibrahim Batuhan Akkaya, Senthilkumar S. Kathiresan, Elahe Arani +1
Vision transformers (ViTs) achieve remarkable performance on large datasets, but tend to perform worse than convolutional neural networks (CNNs) when trained from scratch on smalle…
BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning
Kishaan Jeeveswaran, Prashant Bhat, Bahram Zonooz +1
The ability of deep neural networks to continually learn and adapt to a sequence of tasks has remained challenging due to catastrophic forgetting of previously learned tasks. Human…
LSFSL: Leveraging Shape Information in Few-shot Learning
Deepan Chakravarthi Padmanabhan, Shruthi Gowda, Elahe Arani +1
Few-shot learning (FSL) techniques seek to learn the underlying patterns in data using fewer samples, analogous to how humans learn from limited experience. In this limited-data sc…
Dynamically Modular and Sparse General Continual Learning
Arnav Varma, Elahe Arani, Bahram Zonooz
Real-world applications often require learning continuously from a stream of data under ever-changing conditions. When trying to learn from such non-stationary data, deep neural ne…
AI-Driven Road Maintenance Inspection v2: Reducing Data Dependency & Quantifying Road Damage
Haris Iqbal, Hemang Chawla, Arnav Varma +4
Road infrastructure maintenance inspection is typically a labor-intensive and critical task to ensure the safety of all road users. Existing state-of-the-art techniques in Artifici…
Image Masking for Robust Self-Supervised Monocular Depth Estimation
Hemang Chawla, Kishaan Jeeveswaran, Elahe Arani +1
Self-supervised monocular depth estimation is a salient task for 3D scene understanding. Learned jointly with monocular ego-motion estimation, several methods have been proposed to…
Curbing Task Interference using Representation Similarity-Guided Multi-Task Feature Sharing
Naresh Kumar Gurulingan, Elahe Arani, Bahram Zonooz
Multi-task learning of dense prediction tasks, by sharing both the encoder and decoder, as opposed to sharing only the encoder, provides an attractive front to increase both accura…
Differencing based Self-supervised pretraining for Scene Change Detection
Vijaya Raghavan T. Ramkumar, Elahe Arani, Bahram Zonooz
Scene change detection (SCD), a crucial perception task, identifies changes by comparing scenes captured at different times. SCD is challenging due to noisy changes in illumination…
A Comprehensive Study of Real-Time Object Detection Networks Across Multiple Domains: A Survey
Elahe Arani, Shruthi Gowda, Ratnajit Mukherjee +3
Deep neural network based object detectors are continuously evolving and are used in a multitude of applications, each having its own set of requirements. While safety-critical app…
Adversarial Attacks on Monocular Pose Estimation
Hemang Chawla, Arnav Varma, Elahe Arani +1
Advances in deep learning have resulted in steady progress in computer vision with improved accuracy on tasks such as object detection and semantic segmentation. Nevertheless, deep…
InBiaseD: Inductive Bias Distillation to Improve Generalization and Robustness through Shape-awareness
Shruthi Gowda, Bahram Zonooz, Elahe Arani
Humans rely less on spurious correlations and trivial cues, such as texture, compared to deep neural networks which lead to better generalization and robustness. It can be attribut…
Transformers in Self-Supervised Monocular Depth Estimation with Unknown Camera Intrinsics
Arnav Varma, Hemang Chawla, Bahram Zonooz +1
The advent of autonomous driving and advanced driver assistance systems necessitates continuous developments in computer vision for 3D scene understanding. Self-supervised monocula…
A Comprehensive Study of Vision Transformers on Dense Prediction Tasks
Kishaan Jeeveswaran, Senthilkumar Kathiresan, Arnav Varma +3
Convolutional Neural Networks (CNNs), architectures consisting of convolutional layers, have been the standard choice in vision tasks. Recent studies have shown that Vision Transfo…
Does Thermal data make the detection systems more reliable?
Shruthi Gowda, Bahram Zonooz, Elahe Arani
Deep learning-based detection networks have made remarkable progress in autonomous driving systems (ADS). ADS should have reliable performance across a variety of ambient lighting…
UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial Attacks
Naresh Kumar Gurulingan, Elahe Arani, Bahram Zonooz
Scene understanding is crucial for autonomous systems which intend to operate in the real world. Single task vision networks extract information only based on some aspects of the s…
Highlighting the Importance of Reducing Research Bias and Carbon Emissions in CNNs
Ahmed Badar, Arnav Varma, Adrian Staniec +5
Convolutional neural networks (CNNs) have become commonplace in addressing major challenges in computer vision. Researchers are not only coming up with new CNN architectures but ar…
AI Driven Road Maintenance Inspection
Ratnajit Mukherjee, Haris Iqbal, Shabbir Marzban +5
Road infrastructure maintenance inspection is typically a labour-intensive and critical task to ensure the safety of all the road users. In this work, we propose a detailed methodo…