Search Results for author:
Found 46 papers, 16 papers with code
Investigating the Robustness of Vision Transformers against Label Noise in Medical Image Classification
Label noise in medical image classification datasets significantly hampers the training of supervised deep learning methods, undermining their generalizability.
Investigation of Federated Learning Algorithms for Retinal Optical Coherence Tomography Image Classification with Statistical Heterogeneity
Purpose: We apply federated learning to train an OCT image classifier simulating a realistic scenario with multiple clients and statistical heterogeneous data distribution where data in the clients lack samples of some categories entirely.
How does self-supervised pretraining improve robustness against noisy labels across various medical image classification datasets?
In this study, we address three key questions: i) How does label noise impact various medical image classification datasets?
Medical Vision Language Pretraining: A survey
Medical Vision Language Pretraining (VLP) has recently emerged as a promising solution to the scarcity of labeled data in the medical domain.
TextAug: Test time Text Augmentation for Multimodal Person Re-identification
In this study, we investigate the effectiveness of two computer vision data augmentation techniques: cutout and cutmix, for text augmentation in multi-modal person re-identification.
Federated Active Learning for Target Domain Generalisation
In this paper, we introduce Active Learning framework in Federated Learning for Target Domain Generalisation, harnessing the strength from both learning paradigms.
Dimension Mixer: A Generalized Method for Structured Sparsity in Deep Neural Networks
The recent success of multiple neural architectures like CNNs, Transformers, and MLP-Mixers motivated us to look for similarities and differences between them.
Importance Estimation with Random Gradient for Neural Network Pruning
Global Neuron Importance Estimation is used to prune neural networks for efficiency reasons.
Multimodal Federated Learning in Healthcare: a Review
Recent advancements in multimodal machine learning have empowered the development of accurate and robust AI systems in the medical domain, especially within centralized database systems.
Data Augmentation through Pseudolabels in Automatic Region Based Coronary Artery Segmentation for Disease Diagnosis
Coronary Artery Diseases(CADs) though preventable are one of the leading causes of death and disability.
ConvNeXtv2 Fusion with Mask R-CNN for Automatic Region Based Coronary Artery Stenosis Detection for Disease Diagnosis
Coronary Artery Diseases although preventable are one of the leading cause of mortality worldwide.
Task-guided Domain Gap Reduction for Monocular Depth Prediction in Endoscopy
Colorectal cancer remains one of the deadliest cancers in the world.
Improving Medical Image Classification in Noisy Labels Using Only Self-supervised Pretraining
In this work, we explore contrastive and pretext task-based self-supervised pretraining to initialize the weights of a deep learning classification model for two medical datasets with self-induced noisy labels -- NCT-CRC-HE-100K tissue histological images and COVID-QU-Ex chest X-ray images.
Neural Network Pruning for Real-time Polyp Segmentation
In this study, we show an application of neural network pruning in polyp segmentation.
M-VAAL: Multimodal Variational Adversarial Active Learning for Downstream Medical Image Analysis Tasks
Acquiring properly annotated data is expensive in the medical field as it requires experts, time-consuming protocols, and rigorous validation.
A Client-server Deep Federated Learning for Cross-domain Surgical Image Segmentation
This paper presents a solution to the cross-domain adaptation problem for 2D surgical image segmentation, explicitly considering the privacy protection of distributed datasets belonging to different centers.
T2FNorm: Extremely Simple Scaled Train-time Feature Normalization for OOD Detection
Indeed, the naive incorporation of feature normalization within neural networks does not guarantee substantial improvement in OOD detection performance.
iEdit: Localised Text-guided Image Editing with Weak Supervision
We propose a novel learning method for text-guided image editing, namely \texttt{iEdit}, that generates images conditioned on a source image and a textual edit prompt.
Translating Simulation Images to X-ray Images via Multi-Scale Semantic Matching
In this paper, we propose a new method to translate simulation images from an endovascular simulator to X-ray images.
Why is the winner the best?
The "typical" lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning.
CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection
This paper presents the CholecTriplet2022 challenge, which extends surgical action triplet modeling from recognition to detection.
Ranked #1 on
Action Triplet Detection
on CholecT50 (Challenge)
MoBYv2AL: Self-supervised Active Learning for Image Classification
We present MoBYv2AL, a novel self-supervised active learning framework for image classification.
Generalized Product-of-Experts for Learning Multimodal Representations in Noisy Environments
In order to process the multimodal information automatically and use it for an end application, Multimodal Representation Learning (MRL) has emerged as an active area of research in recent times.
Noisy Heuristics NAS: A Network Morphism based Neural Architecture Search using Heuristics
Network Morphism based Neural Architecture Search (NAS) is one of the most efficient methods, however, knowing where and when to add new neurons or remove dis-functional ones is generally left to black-box Reinforcement Learning models.
Placental Vessel Segmentation and Registration in Fetoscopy: Literature Review and MICCAI FetReg2021 Challenge Findings
For this challenge, we released a dataset of 2060 images, pixel-annotated for vessels, tool, fetus and background classes, from 18 in-vivo TTTS fetoscopy procedures and 18 short video clips.
Bimodal Camera Pose Prediction for Endoscopy
Deducing the 3D structure of endoscopic scenes from images is exceedingly challenging.
Task-Aware Active Learning for Endoscopic Image Analysis
Semantic segmentation of polyps and depth estimation are two important research problems in endoscopic image analysis.
Histogram of Oriented Gradients Meet Deep Learning: A Novel Multi-task Deep Network for Medical Image Semantic Segmentation
We employed our method on two powerful and widely used semantic segmentation networks: UNet and U2Net to train in a multi-task setup.
A Unified Architecture of Semantic Segmentation and Hierarchical Generative Adversarial Networks for Expression Manipulation
Recently, hierarchical networks that consist of both a global network dealing with the whole image and multiple local networks focusing on local parts are showing success.
SeCGAN: Parallel Conditional Generative Adversarial Networks for Face Editing via Semantic Consistency
Whilst both branches are required during training, the RGB branch is our primary network and the semantic branch is not needed for inference.
Brand Label Albedo Extraction of eCommerce Products using Generative Adversarial Network
In this paper we present our solution to extract albedo of branded labels for e-commerce products.
Input Invex Neural Network
In the experiments section, we use our methods for classification tasks using an ensemble of 1-vs-all models as well as using a single multiclass model on larger-scale datasets.
Visual Transformer for Task-aware Active Learning
In this paper, we present a novel pipeline for pool-based Active Learning.
Label Geometry Aware Discriminator for Conditional Generative Networks
Multi-domain image-to-image translation with conditional Generative Adversarial Networks (GANs) can generate highly photo realistic images with desired target classes, yet these synthetic images have not always been helpful to improve downstream supervised tasks such as image classification.
Active Learning for Bayesian 3D Hand Pose Estimation
We propose a Bayesian approximation to a deep learning architecture for 3D hand pose estimation.
3D Dense Geometry-Guided Facial Expression Synthesis by Adversarial Learning
We utilise this dataset to minimise the novel depth consistency loss via adversarial learning (note we do not have ground truth depth maps for generated face images) and the depth categorical loss of synthetic data on the discriminator.
Sequential Graph Convolutional Network for Active Learning
We flip the label of newly queried nodes from unlabelled to labelled, re-train the learner to optimise the downstream task and the graph to minimise its modified objective.
Ranked #4 on
Active Learning
on CIFAR10 (10,000)
MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative Adversarial Network
We perform augmentation by randomly sampling sensible labels from the label space of the few labelled examples available and assigning them as target labels to the abundant unlabelled examples from the same distribution as that of the labelled ones.
Additive Angular Margin for Few Shot Learning to Classify Clinical Endoscopy Images
In this work, we propose to use a few-shot learning approach that requires less training data and can be used to predict label classes of test samples from an unseen dataset.
Inducing Optimal Attribute Representations for Conditional GANs
Existing conditional GANs commonly encode target domain label information as hard-coded categorical vectors in the form of 0s and 1s.
Sampling Strategies for GAN Synthetic Data
Unlike previous studies of randomly augmenting the synthetic data with real data, we present our simple, effective and easy to implement synthetic data sampling methods to train deep CNNs more efficiently and accurately.
AugLabel: Exploiting Word Representations to Augment Labels for Face Attribute Classification
Augmenting data in image space (eg.
Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model
We propose a novel end-to-end semi-supervised adversarial framework to generate photorealistic face images of new identities with wide ranges of expressions, poses, and illuminations conditioned by a 3D morphable model.
Ranked #16 on
Face Verification
on IJB-A
Deep fusion of visual signatures for client-server facial analysis
The challenge addressed in this paper is to design a common universal representation such that a single merged signature is transmitted to the server, whatever be the type and number of features computed by the client, ensuring nonetheless an optimal performance.
CP-mtML: Coupled Projection multi-task Metric Learning for Large Scale Face Retrieval
The experiments clearly demonstrate the scalability and improved performance of the proposed method on the tasks of identity and age based face image retrieval compared to competitive existing methods, on the standard datasets and with the presence of a million distractor face images.
