Search Results for author:
Found 22 papers, 8 papers with code
FaBULOUS: Fact-checking Based on Understanding of Language Over Unstructured and Structured information
As part of the FEVEROUS shared task, we developed a robust and finely tuned architecture to handle the joint retrieval and entailment on text data as well as structured data like tables.
DimCL: Dimensional Contrastive Learning For Improving Self-Supervised Learning
Self-supervised learning (SSL) has gained remarkable success, for which contrastive learning (CL) plays a key role.
Regret-Based Defense in Adversarial Reinforcement Learning
We demonstrate that our approaches provide a significant improvement in performance across a wide variety of benchmarks against leading approaches for robust Deep RL.
LAD: A Hybrid Deep Learning System for Benign Paroxysmal Positional Vertigo Disorders Diagnostic
Herein, we introduce "Look and Diagnose" (LAD), a hybrid deep learning-based system that aims to support doctors in the medical field in diagnosing effectively the Benign Paroxysmal Positional Vertigo (BPPV) disorder.
Scalable SoftGroup for 3D Instance Segmentation on Point Clouds
Furthermore, SoftGroup can be extended to perform object detection and panoptic segmentation with nontrivial improvements over existing methods.
Few-shot Object Counting and Detection
We tackle a new task of few-shot object counting and detection.
Ranked #10 on
Object Counting
on FSC147
Beyond NaN: Resiliency of Optimization Layers in The Face of Infeasibility
We show that an adversary can cause such failures by forcing rank deficiency on the matrix fed to the optimization layer which results in the optimization failing to produce a solution.
Whose Hands Are These? Hand Detection and Hand-Body Association in the Wild
We also introduce a new challenging dataset called BodyHands containing unconstrained images with hand and their corresponding body locations annotations.
GDCA: GAN-based single image super resolution with Dual discriminators and Channel Attention
Single Image Super-Resolution (SISR) is a very active research field.
Ensemble Learning based on Classifier Prediction Confidence and Comprehensive Learning Particle Swarm Optimisation for polyp localisation
Based on an observation that different segmentation algorithms will perform well on different subsets of examples because of the nature and size of training sets they have been exposed to and because of method-intrinsic factors, we propose to measure the confidence in the prediction of each algorithm and then use an associate threshold to determine whether the confidence is acceptable or not.
Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model
Developing an agent in reinforcement learning (RL) that is capable of performing complex control tasks directly from high-dimensional observation such as raw pixels is yet a challenge as efforts are made towards improving sample efficiency and generalization.
Robust MAML: Prioritization task buffer with adaptive learning process for model-agnostic meta-learning
Model agnostic meta-learning (MAML) is a popular state-of-the-art meta-learning algorithm that provides good weight initialization of a model given a variety of learning tasks.
NeRD: Neural Representation of Distribution for Medical Image Segmentation
We introduce Neural Representation of Distribution (NeRD) technique, a module for convolutional neural networks (CNNs) that can estimate the feature distribution by optimizing an underlying function mapping image coordinates to the feature distribution.
Topological Signatures in Nodal Semimetals through Neutron Scattering
Topological nodal semimetals are known to host a variety of fascinating electronic properties due to the topological protection of the band-touching nodes.
Materials Science
Learning to Attack with Fewer Pixels: A Probabilistic Post-hoc Framework for Refining Arbitrary Dense Adversarial Attacks
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier.
Probabilistic Dipole Inversion for Adaptive Quantitative Susceptibility Mapping
A learning-based posterior distribution estimation method, Probabilistic Dipole Inversion (PDI), is proposed to solve the quantitative susceptibility mapping (QSM) inverse problem in MRI with uncertainty estimation.
Bayesian Optimization with Unknown Search Space
Applying Bayesian optimization in problems wherein the search space is unknown is challenging.
BUZz: BUffer Zones for defending adversarial examples in image classification
We argue that our defense based on buffer zones offers significant improvements over state-of-the-art defenses.
Virtual organelle self-coding for fluorescence imaging via adversarial learning
A detailed comparative analysis is also conducted on the performance of the cGAN network between predicting fluorescence channels based on phase contrast or based on another fluorescence channel using human breast cancer MDA-MB-231 cell line as a test case.
Multi-Agent Deep Reinforcement Learning with Human Strategies
In this paper, we introduce an approach that integrates human strategies to increase the exploration capacity of multiple deep reinforcement learning agents.
Deep learning approach to Fourier ptychographic microscopy
Specifically, we show that it is possible to reconstruct high-SBP dynamic cell videos by a CNN trained only on the first FPM dataset captured at the beginning of a time-series experiment.
A Human Mixed Strategy Approach to Deep Reinforcement Learning
In 2015, Google's DeepMind announced an advancement in creating an autonomous agent based on deep reinforcement learning (DRL) that could beat a professional player in a series of 49 Atari games.
