640 citations · 1.3k across the 22 of their papers we have counts for
28 papers
Stable Diffusion Models are Secretly Good at Visual In-Context Learning
Trevine Oorloff, Vishwanath Sindagi, Wele Gedara Chaminda Bandara +4
Large language models (LLM) in natural language processing (NLP) have demonstrated great potential for in-context learning (ICL) -- the ability to leverage a few sets of example pr…
Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGAN
Rajeev Yasarla, Vishwanath A. Sindagi, Vishal M. Patel
Existing approaches for restoring weather-degraded images follow a fully-supervised paradigm and they require paired data for training. However, collecting paired data for weather…
Uncertainty-aware Mean Teacher for Source-free Unsupervised Domain Adaptive 3D Object Detection
Deepti Hegde, Vishwanath Sindagi, Velat Kilic +3
Pseudo-label based self training approaches are a popular method for source-free unsupervised domain adaptation. However, their efficacy depends on the quality of the labels genera…
Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection
Velat Kilic, Deepti Hegde, Vishwanath Sindagi +3
Lidar-based object detectors are critical parts of the 3D perception pipeline in autonomous navigation systems such as self-driving cars. However, they are known to be sensitive to…
Unsupervised Domain Adaptation of Object Detectors: A Survey
Poojan Oza, Vishwanath A. Sindagi, Vibashan VS +1
Recent advances in deep learning have led to the development of accurate and efficient models for various computer vision applications such as classification, segmentation, and det…
MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection
Vibashan VS, Vikram Gupta, Poojan Oza +2
Existing approaches for unsupervised domain adaptive object detection perform feature alignment via adversarial training. While these methods achieve reasonable improvements in per…
KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation
Jeya Maria Jose Valanarasu, Vishwanath A. Sindagi, Ilker Hacihaliloglu +1
Most methods for medical image segmentation use U-Net or its variants as they have been successful in most of the applications. After a detailed analysis of these "traditional" enc…
Semi-Supervised Image Deraining using Gaussian Processes
Rajeev Yasarla, V. A. Sindagi, V. M. Patel
Recent CNN-based methods for image deraining have achieved excellent performance in terms of reconstruction error as well as visual quality. However, these methods are limited in t…
Completely Self-Supervised Crowd Counting via Distribution Matching
Deepak Babu Sam, Abhinav Agarwalla, Jimmy Joseph +3
Dense crowd counting is a challenging task that demands millions of head annotations for training models. Though existing self-supervised approaches could learn good representation…
Learning to Count in the Crowd from Limited Labeled Data
Vishwanath A. Sindagi, Rajeev Yasarla, Deepak Sam Babu +2
Recent crowd counting approaches have achieved excellent performance. However, they are essentially based on fully supervised paradigm and require large number of annotated samples…
KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations
Jeya Maria Jose, Vishwanath Sindagi, Ilker Hacihaliloglu +1
Due to its excellent performance, U-Net is the most widely used backbone architecture for biomedical image segmentation in the recent years. However, in our studies, we observe tha…
Syn2Real Transfer Learning for Image Deraining using Gaussian Processes
Rajeev Yasarla, Vishwanath A. Sindagi, Vishal M. Patel
Recent CNN-based methods for image deraining have achieved excellent performance in terms of reconstruction error as well as visual quality. However, these methods are limited in t…
JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method
Vishwanath A. Sindagi, Rajeev Yasarla, Vishal M. Patel
Due to its variety of applications in the real-world, the task of single image-based crowd counting has received a lot of interest in the recent years. Recently, several approaches…
Prior-based Domain Adaptive Object Detection for Hazy and Rainy Conditions
Vishwanath A. Sindagi, Poojan Oza, Rajeev Yasarla +1
Adverse weather conditions such as haze and rain corrupt the quality of captured images, which cause detection networks trained on clean images to perform poorly on these images. T…
Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method
Vishwanath A. Sindagi, Rajeev Yasarla, Vishal M. Patel
In this work, we propose a novel crowd counting network that progressively generates crowd density maps via residual error estimation. The proposed method uses VGG16 as the backbon…
Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting
Vishwanath A Sindagi, Vishal M. Patel
Crowd counting presents enormous challenges in the form of large variation in scales within images and across the dataset. These issues are further exacerbated in highly congested…
HA-CCN: Hierarchical Attention-based Crowd Counting Network
Vishwanath A. Sindagi, Vishal M. Patel
Single image-based crowd counting has recently witnessed increased focus, but many leading methods are far from optimal, especially in highly congested scenes. In this paper, we pr…
Inverse Attention Guided Deep Crowd Counting Network
Vishwanath A. Sindagi, Vishal M. Patel
In this paper, we address the challenging problem of crowd counting in congested scenes. Specifically, we present Inverse Attention Guided Deep Crowd Counting Network (IA-DCCN) tha…
MVX-Net: Multimodal VoxelNet for 3D Object Detection
Vishwanath A. Sindagi, Yin Zhou, Oncel Tuzel
Many recent works on 3D object detection have focused on designing neural network architectures that can consume point cloud data. While these approaches demonstrate encouraging pe…
DAFE-FD: Density Aware Feature Enrichment for Face Detection
Vishwanath A. Sindagi, Vishal M. Patel
Recent research on face detection, which is focused primarily on improving accuracy of detecting smaller faces, attempt to develop new anchor design strategies to facilitate increa…
Pushing the Limits of Unconstrained Face Detection: a Challenge Dataset and Baseline Results
Hajime Nada, Vishwanath A. Sindagi, He Zhang +1
Face detection has witnessed immense progress in the last few years, with new milestones being surpassed every year. While many challenges such as large variations in scale, pose,…
High-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networks
Lidan Wang, Vishwanath A. Sindagi, Vishal M. Patel
Synthesizing face sketches from real photos and its inverse have many applications. However, photo/sketch synthesis remains a challenging problem due to the fact that photo and ske…
GP-GAN: Gender Preserving GAN for Synthesizing Faces from Landmarks
Xing Di, Vishwanath A. Sindagi, Vishal M. Patel
Facial landmarks constitute the most compressed representation of faces and are known to preserve information such as pose, gender and facial structure present in the faces. Severa…
CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting
Vishwanath A. Sindagi, Vishal M. Patel
Estimating crowd count in densely crowded scenes is an extremely challenging task due to non-uniform scale variations. In this paper, we propose a novel end-to-end cascaded network…