47 citations · 176 across the 19 of their papers we have counts for
19 papers
3D-Aware Instance Segmentation and Tracking in Egocentric Videos
Yash Bhalgat, Vadim Tschernezki, Iro Laina +3
Egocentric videos present unique challenges for 3D scene understanding due to rapid camera motion, frequent object occlusions, and limited object visibility. This paper introduces…
Reproducibility Study of CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification
Manan Shah, Yash Bhalgat
This report is a reproducibility study of the paper "CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification" (Abdelfattah et al, ICCV 2023). Our report makes…
When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models
Xianzheng Ma, Brandon Smart, Yash Bhalgat +14
As large language models (LLMs) evolve, their integration with 3D spatial data (3D-LLMs) has seen rapid progress, offering unprecedented capabilities for understanding and interact…
SiLVR: Scalable Lidar-Visual Reconstruction with Neural Radiance Fields for Robotic Inspection
Yifu Tao, Yash Bhalgat, Lanke Frank Tarimo Fu +3
We present a neural-field-based large-scale reconstruction system that fuses lidar and vision data to generate high-quality reconstructions that are geometrically accurate and capt…
N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields
Yash Bhalgat, Iro Laina, João F. Henriques +2
Understanding complex scenes at multiple levels of abstraction remains a formidable challenge in computer vision. To address this, we introduce Nested Neural Feature Fields (N2F2),…
Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion
Yash Bhalgat, Iro Laina, João F. Henriques +2
Instance segmentation in 3D is a challenging task due to the lack of large-scale annotated datasets. In this paper, we show that this task can be addressed effectively by leveragin…
Neural Refinement for Absolute Pose Regression with Feature Synthesis
Shuai Chen, Yash Bhalgat, Xinghui Li +4
Absolute Pose Regression (APR) methods use deep neural networks to directly regress camera poses from RGB images. However, the predominant APR architectures only rely on 2D operati…
A Light Touch Approach to Teaching Transformers Multi-view Geometry
Yash Bhalgat, Joao F. Henriques, Andrew Zisserman
Transformers are powerful visual learners, in large part due to their conspicuous lack of manually-specified priors. This flexibility can be problematic in tasks that involve multi…
A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning
Hugo Berg, Siobhan Mackenzie Hall, Yash Bhalgat +4
Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness…
Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation
John Yang, Yash Bhalgat, Simyung Chang +2
While hand pose estimation is a critical component of most interactive extended reality and gesture recognition systems, contemporary approaches are not optimized for computational…
Data-driven Weight Initialization with Sylvester Solvers
Debasmit Das, Yash Bhalgat, Fatih Porikli
In this work, we propose a data-driven scheme to initialize the parameters of a deep neural network. This is in contrast to traditional approaches which randomly initialize paramet…
Structured Convolutions for Efficient Neural Network Design
Yash Bhalgat, Yizhe Zhang, Jamie Lin +1
In this work, we tackle model efficiency by exploiting redundancy in the \textit{implicit structure} of the building blocks of convolutional neural networks. We start our analysis…
LSQ+: Improving low-bit quantization through learnable offsets and better initialization
Yash Bhalgat, Jinwon Lee, Markus Nagel +2
Unlike ReLU, newer activation functions (like Swish, H-swish, Mish) that are frequently employed in popular efficient architectures can also result in negative activation values, w…
Learned Threshold Pruning
Kambiz Azarian, Yash Bhalgat, Jinwon Lee +1
This paper presents a novel differentiable method for unstructured weight pruning of deep neural networks. Our learned-threshold pruning (LTP) method learns per-layer thresholds vi…
QKD: Quantization-aware Knowledge Distillation
Jangho Kim, Yash Bhalgat, Jinwon Lee +2
Quantization and Knowledge distillation (KD) methods are widely used to reduce memory and power consumption of deep neural networks (DNNs), especially for resource-constrained edge…
Teacher-Student Learning Paradigm for Tri-training: An Efficient Method for Unlabeled Data Exploitation
Yash Bhalgat, Zhe Liu, Pritam Gundecha +2
Given that labeled data is expensive to obtain in real-world scenarios, many semi-supervised algorithms have explored the task of exploitation of unlabeled data. Traditional tri-tr…
Annotation-cost Minimization for Medical Image Segmentation using Suggestive Mixed Supervision Fully Convolutional Networks
Yash Bhalgat, Meet Shah, Suyash Awate
For medical image segmentation, most fully convolutional networks (FCNs) need strong supervision through a large sample of high-quality dense segmentations, which is taxing in term…
FusedLSTM: Fusing frame-level and video-level features for Content-based Video Relevance Prediction
Yash Bhalgat
This paper describes two of my best performing approaches on the Content-based Video Relevance Prediction challenge. In the FusedLSTM based approach, the inception-pool3 and the C3…
Stamp processing with examplar features
Yash Bhalgat, Mandar Kulkarni, Shirish Karande +1
Document digitization is becoming increasingly crucial. In this work, we propose a shape based approach for automatic stamp verification/detection in document images using an unsup…