103 citations · 349 across the 55 of their papers we have counts for
13 papers · 1 filter
Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding
Mengya Xu, Mobarakol Islam, Ben Glocker +1
Curriculum learning and self-paced learning are the training strategies that gradually feed the samples from easy to more complex. They have captivated increasing attention due to…
Task-Aware Asynchronous Multi-Task Model with Class Incremental Contrastive Learning for Surgical Scene Understanding
Lalithkumar Seenivasan, Mobarakol Islam, Mengya Xu +2
Purpose: Surgery scene understanding with tool-tissue interaction recognition and automatic report generation can play an important role in intra-operative guidance, decision-makin…
Bi-Link: Bridging Inductive Link Predictions from Text via Contrastive Learning of Transformers and Prompts
Bohua Peng, Shihao Liang, Mobarakol Islam
Inductive knowledge graph completion requires models to comprehend the underlying semantics and logic patterns of relations. With the advance of pretrained language models, recent…
Frequency Dropout: Feature-Level Regularization via Randomized Filtering
Mobarakol Islam, Ben Glocker
Deep convolutional neural networks have shown remarkable performance on various computer vision tasks, and yet, they are susceptible to picking up spurious correlations from the tr…
Estimating Model Performance under Domain Shifts with Class-Specific Confidence Scores
Zeju Li, Konstantinos Kamnitsas, Mobarakol Islam +2
Machine learning models are typically deployed in a test setting that differs from the training setting, potentially leading to decreased model performance because of domain shift.…
Angular Gap: Reducing the Uncertainty of Image Difficulty through Model Calibration
Bohua Peng, Mobarakol Islam, Mei Tu
Curriculum learning needs example difficulty to proceed from easy to hard. However, the credibility of image difficulty is rarely investigated, which can seriously affect the effec…
Rethinking Surgical Instrument Segmentation: A Background Image Can Be All You Need
An Wang, Mobarakol Islam, Mengya Xu +1
Data diversity and volume are crucial to the success of training deep learning models, while in the medical imaging field, the difficulty and cost of data collection and annotation…
Rethinking Surgical Captioning: End-to-End Window-Based MLP Transformer Using Patches
Mengya Xu, Mobarakol Islam, Hongliang Ren
Surgical captioning plays an important role in surgical instruction prediction and report generation. However, the majority of captioning models still rely on the heavy computation…
Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer
Lalithkumar Seenivasan, Mobarakol Islam, Adithya K Krishna +1
Visual question answering (VQA) in surgery is largely unexplored. Expert surgeons are scarce and are often overloaded with clinical and academic workloads. This overload often limi…
Class Balanced PixelNet for Neurological Image Segmentation
Mobarakol Islam, Hongliang Ren
In this paper, we propose an automatic brain tumor segmentation approach (e.g., PixelNet) using a pixel-level convolutional neural network (CNN). The model extracts feature from mu…
Ischemic Stroke Lesion Segmentation Using Adversarial Learning
Mobarakol Islam, N Rajiv Vaidyanathan, V Jeya Maria Jose +1
Ischemic stroke occurs through a blockage of clogged blood vessels supplying blood to the brain. Segmentation of the stroke lesion is vital to improve diagnosis, outcome assessment…
CholecTriplet2021: A benchmark challenge for surgical action triplet recognition
Chinedu Innocent Nwoye, Deepak Alapatt, Tong Yu +59
Context-aware decision support in the operating room can foster surgical safety and efficiency by leveraging real-time feedback from surgical workflow analysis. Most existing works…
Global-Reasoned Multi-Task Learning Model for Surgical Scene Understanding
Lalithkumar Seenivasan, Sai Mitheran, Mobarakol Islam +1
Global and local relational reasoning enable scene understanding models to perform human-like scene analysis and understanding. Scene understanding enables better semantic segmenta…