|
I am a 3rd year PhD candidate in the Visual Geometry Group (VGG) co-advised by Andrea Vedaldi, Andrew Zisserman, João Henriques and Iro Laina, funded by the EPSRC+AWS fellowship with AIMS CDT. Previously, I was a Senior Researcher at Qualcomm AI Research, specializing in Computer Vision and Efficient Deep Learning. I've worked on 3D hand-pose estimation [DIR-Net], low-bit quantization [LSQ+, QKD], structured [StructConv] and unstructured pruning [LTP] of deep networks. I received my Masters in Computer Science from University of Michigan, and my Bachelors in Electrical Engineering (CS minor) from IIT Bombay. Open to collaborations, feel free to setup a call for discussions about my research or new ideas! |
|
|
|
|
|
 
|
Yash Bhalgat, Iro Laina, João Henriques, Andrew Zisserman, Andrea Vedaldi NeurIPS, 2023 (Spotlight presentation) We present a novel "slow-fast" contrastive fusion method to lift 2D predictions to 3D for scalable instance segmentation, achieving significant improvements without requiring an upper bound on the number of objects in the scene. |
 
|
Yash Bhalgat, João Henriques, Andrew Zisserman CVPR, 2023 An "Epipolar-guided training" method to incorporate multi-view geometric priors into Transformer models, which can be implemented in 150 lines of code. During test-time, the Transformer implicitly estimates the epipolar geometry given 2 images and uses it for downstream predictions, e.g. for pose-invariant retrieval. |
 
|
John Yang, Yash Bhalgat, Simyung Chang, Fatih Porikli, Nojun Kwak WACV, 2022 We propose a tiny deep network of which partial layers are recursively exploited for refining its previous estimations. During its iterative refinements, we employ learned gating criteria to decide whether to exit from the weight-sharing loop, allowing per-sample adaptation in our model. We also predict and exploit uncertainty estimations in the gating mechanism. |
 
|
Yash Bhalgat, Yizhe Zhang, Jamie Lin, Fatih Porikli NeurIPS, 2020 We introduce a neat trick to enable the execution of convolution operations in the form of efficient, scaled, sum-pooling components. We present a Structural Regularization loss that enables this decomposition with negligible performance loss. Our method is competitive with other tensor decomposition and structured pruning methods. |
 
|
Debasmit Das, Yash Bhalgat, Fatih Porikli Practical Machine Learning for Developing Countries Workshop, ICLR, 2021 We propose a data-driven scheme to initialize the parameters of a neural network. The initialization is cast as an optimization problem, which is restructured into the well-known Sylvester equation that has fast and efficient gradient-free solutions. We show that our proposed method is especially effective in few-shot and fine-tuning settings. |
 
|
Yash Bhalgat, Jinwon Lee, Markus Nagel, Tijmen Blankevoort, Nojun Kwak Efficient Deep Learning in Computer Vision Workshop, CVPR, 2020 We introduce a general asymmetric quantization scheme with trainable scale and offset parameters. LSQ+ shows SOTA results for EfficientNet and MixNet outperforming LSQ for low-bit quantization. |
 
|
Kambiz Azarian, Yash Bhalgat, Jinwon Lee, Tijmen Blankevoort arxiv, 2020 We propose an end-to-end differentiable method for learning layerwise pruning thresholds which results in SOTA model compression ratios with AlexNet, ResNet and EfficientNet. Our method also generates a trail of checkpoints with different accuracy-efficiency operating points. |
 
|
Yash Bhalgat*, Jangho Kim*, Jinwon Lee, Chirag Patel, Nojun Kwak arxiv, 2020 Low-bit quantization and KD often don't go well together, but both are important approaches to reduces a model's memory footprint. We propose an effective method to combine these two methods and show results that outperform all existing quantization/KD approaches. |
|
Yash Bhalgat, Zhe Liu, Pritam Gundecha, Jalal Mahmud, Amita Misra KONVENS, 2019 Teacher-student tri-training is a method for semi-supervised learning using 3 classifiers working using adaptive teacher and student thresholds. |
|
Yash Bhalgat*, Meet Shah* Suyash Awate Medical Imaging meets NeurIPS workshop, 2019 For Medical Image segmentation, we present a budget-based cost-minimization framework in a mixed-supervision setting via dense segmentations, bounding boxes, and landmarks. |
 
|
Yash Bhalgat, Jean Charlety, Laurent Duval ICASSP, 2018 We use Scattering Wavelets transforms to extract sparse feature sets from seismic data. We show that using this method combined with simple PCA-based feature selection leads to promising classification performance in affordable computation time. |
|
|
|
To get away from my exciting yet stressful life as a computer scientist, I indulge myself into the realms of music. I spent my entire childhood learning Tabla, an Indian percussion instrument. I briefly also tried to learn the Piano, Drums and Harmonia but had to leave that for my higher studies. One day, I naturally started beatboxing (check this out) and I continue that passion to this day. Please checkout my music channels that I try to maintain regularly. :) |
|
|
Website template borrowed from here. |