Search Results for author:
Found 16 papers, 6 papers with code
Transfer Learning with Point Transformers
In this project we explore two things: classification performance of these attention based networks on ModelNet10 dataset and then, we use the trained model to classify 3D MNIST dataset after finetuning.
The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?
This study uses linear probing to shed light on the hidden knowledge at the output layer of LVLMs.
Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection
Feature shaping refers to a family of methods that exhibit state-of-the-art performance for out-of-distribution (OOD) detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Reducing the Side-Effects of Oscillations in Training of Quantized YOLO Networks
While quantization-aware training QAT is the well-studied approach to quantize the networks at low precision, most research focuses on over-parameterized networks for classification with limited studies on popular and edge device friendly single-shot object detection and semantic segmentation methods like YOLO.
Understanding and Improving the Role of Projection Head in Self-Supervised Learning
Most current contrastive learning approaches append a parametrized projection head to the end of some backbone network to optimize the InfoNCE objective and then discard the learned projection head after training.
DrawMon: A Distributed System for Detection of Atypical Sketch Content in Concurrent Pictionary Games
Pictionary, the popular sketch-based guessing game, provides an opportunity to analyze shared goal cooperative game play in restricted communication settings.
Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devices
We perform extensive experiments on standard FL benchmarks to evaluate our proposed FedAvg variants for quantization robustness and provide a convergence analysis for our Quantization-Aware variants in FL.
Calibration of Neural Networks using Splines
From this, by approximating the empirical cumulative distribution using a differentiable function via splines, we obtain a recalibration function, which maps the network outputs to actual (calibrated) class assignment probabilities.
Post-hoc Calibration of Neural Networks by g-Layers
Calibration of neural networks is a critical aspect to consider when incorporating machine learning models in real-world decision-making systems where the confidence of decisions are equally important as the decisions themselves.
Learning Minimax Estimators via Online Learning
We view the problem of designing minimax estimators as finding a mixed strategy Nash equilibrium of a zero-sum game.
Improved Gradient based Adversarial Attacks for Quantized Networks
In this work, we systematically study the robustness of quantized networks against gradient based adversarial attacks and demonstrate that these quantized models suffer from gradient vanishing issues and show a fake sense of robustness.
Mirror Descent View for Neural Network Quantization
Quantizing large Neural Networks (NN) while maintaining the performance is highly desirable for resource-limited devices due to reduced memory and time complexity.
CullNet: Calibrated and Pose Aware Confidence Scores for Object Pose Estimation
We present a new approach for a single view, image-based object pose estimation.
Ranked #13 on
6D Pose Estimation using RGB
on Occlusion LineMOD
Classifying Object Manipulation Actions based on Grasp-types and Motion-Constraints
Due to the variations in geometrical and motion constraints, there are different manipulations actions possible to perform different sets of actions with an object.
Nearly Optimal Robust Matrix Completion
Finally, an application of our result to the robust PCA problem (low-rank+sparse matrix separation) leads to nearly linear time (in matrix dimensions) algorithm for the same; existing state-of-the-art methods require quadratic time.
Nearly-optimal Robust Matrix Completion
Finally, an application of our result to the robust PCA problem (low-rank+sparse matrix separation) leads to nearly linear time (in matrix dimensions) algorithm for the same; existing state-of-the-art methods require quadratic time.
