Search Results for author:
Found 45 papers, 18 papers with code
PCBEAR: Pose Concept Bottleneck for Explainable Action Recognition
Unlike methods based on pixel-level features or static textual descriptions, PCBEAR leverages human skeleton poses, which focus solely on body movements, providing robust and interpretable explanations of motion dynamics.
Adversarial Wear and Tear: Exploiting Natural Damage for Generating Physical-World Adversarial Examples
The translation network encodes the characteristics of damaged signs into a latent `damage style code'.
HiCM$^2$: Hierarchical Compact Memory Modeling for Dense Video Captioning
With the growing demand for solutions to real-world video challenges, interest in dense video captioning (DVC) has been on the rise.
Ranked #1 on
Dense Video Captioning
on YouCook2
(using extra training data)
Resource-Efficient Medical Report Generation using Large Language Models
Medical report generation is the task of automatically writing radiology reports for chest X-ray images.
LLaVA Needs More Knowledge: Retrieval Augmented Natural Language Generation with Knowledge Graph for Explaining Thoracic Pathologies
To address these issues, we propose a novel Vision-Language framework augmented with a Knowledge Graph (KG)-based datastore, which enhances the model's understanding by incorporating additional domain-specific medical knowledge essential for generating accurate and informative NLEs.
PCEvE: Part Contribution Evaluation Based Model Explanation for Human Figure Drawing Assessment and Beyond
Unlike existing attribution-based XAI approaches, the PCEvE provides a straightforward explanation of a model decision, i. e., a part contribution histogram.
Retrieval-Augmented Natural Language Reasoning for Explainable Visual Question Answering
In this work, we introduce a new VQA-NLE model, ReRe (Retrieval-augmented natural language Reasoning), using leverage retrieval information from the memory to aid in generating accurate answers and persuasive explanations without relying on complex networks and extra datasets.
MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection
It contains two components: (1) the weather codebook to memorize the knowledge of the clear weather and generate a weather-reference feature for any input, and (2) the weather-adaptive diffusion model to enhance the feature representation of the input feature by incorporating a weather-reference feature.
SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge
Surgical data science has seen rapid advancement due to the excellent performance of end-to-end deep neural networks (DNNs) for surgical video analysis.
Mask-Free Neuron Concept Annotation for Interpreting Neural Networks in Medical Domain
Recent advancements in deep neural networks have shown promise in aiding disease diagnosis and medical decision-making.
Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval
There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video.
Ranked #4 on
Dense Video Captioning
on YouCook2
WWW: A Unified Framework for Explaining What, Where and Why of Neural Networks by Interpretation of Neuron Concepts
Recent advancements in neural networks have showcased their remarkable capabilities across various domains.
OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
Federated learning (FL) has emerged as a promising approach to collaboratively train machine learning models across multiple edge devices while preserving privacy.
Ranked #7 on
Image Classification
on EMNIST-Balanced
WWW: A Unified Framework for Explaining What Where and Why of Neural Networks by Interpretation of Neuron Concepts
Recent advancements in neural networks have showcased their remarkable capabilities across various domains.
One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era
Overall, this work is the first to survey ChatGPT with a comprehensive review of its underlying technology, applications, and challenges.
Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability
Data augmentation strategies are actively used when training deep neural networks (DNNs).
LINe: Out-of-Distribution Detection by Leveraging Important Neurons
In this study, from the perspective of neurons in the deep layer of the model representing high-level features, we introduce a new aspect for analyzing the difference in model outputs between in-distribution data and OOD data.
Ranked #2 on
Out-of-Distribution Detection
on ImageNet-1k vs SUN
Improved Abdominal Multi-Organ Segmentation via 3D Boundary-Constrained Deep Neural Networks
To address the problem of abdominal multi-organ segmentation, we train the 3D encoder-decoder network to simultaneously segment the abdominal organs and their corresponding boundaries in CT scans via multi-task learning.
Exploiting Diversity of Unlabeled Data for Label-Efficient Semi-Supervised Active Learning
By considering the consistency information with the diversity in the consistency-based embedding scheme, the proposed method could select more informative samples for labeling in the semi-supervised learning setting.
Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models
One challenging property lurking in medical datasets is the imbalanced data distribution, where the frequency of the samples between the different classes is not balanced.
Longitudinal Self-Supervision for COVID-19 Pathology Quantification
For this purpose, longitudinal self-supervision schemes are explored on clinical longitudinal COVID-19 CT scans.
Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information
We propose a method to identify features with predictive information in the input domain.
Interactive Segmentation for COVID-19 Infection Quantification on Longitudinal CT scans
Existing automatic and interactive segmentation models for medical images only use data from a single time point (static).
Towards Semantic Interpretation of Thoracic Disease and COVID-19 Diagnosis Models
We present our findings using publicly available chest pathologies (CheXpert, NIH ChestX-ray8) and COVID-19 datasets (BrixIA, and COVID-19 chest X-ray segmentation dataset).
Explaining COVID-19 and Thoracic Pathology Model Predictions by Identifying Informative Input Features
Neural networks have demonstrated remarkable performance in classification and regression tasks on chest X-rays.
Neural Response Interpretation through the Lens of Critical Pathways
Is critical input information encoded in specific sparse pathways within the neural network?
GLOWin: A Flow-based Invertible Generative Framework for Learning Disentangled Feature Representations in Medical Images
Disentangled representations can be useful in many downstream tasks, help to make deep learning models more interpretable, and allow for control over features of synthetically generated images that can be useful in training other models that require a large number of labelled or unlabelled data.
Longitudinal Quantitative Assessment of COVID-19 Infection Progression from Chest CTs
Chest computed tomography (CT) has played an essential diagnostic role in assessing patients with COVID-19 by showing disease-specific image features such as ground-glass opacity and consolidation.
OperA: Attention-Regularized Transformers for Surgical Phase Recognition
In this paper we introduce OperA, a transformer-based model that accurately predicts surgical phases from long video sequences.
On Sparse Critical Paths of Neural Response
Is critical input information encoded in specific sparse paths within the network?
Self-Supervised Out-of-Distribution Detection in Brain CT Scans
To address these issues, recently, unsupervised deep anomaly detection methods that train the model on large-sized normal scans and detect abnormal scans by calculating reconstruction error have been reported.
Robust Ensemble Model Training via Random Layer Sampling Against Adversarial Attack
After the ensemble models are trained, it can hide the gradient efficiently and avoid the gradient-based attack by the random layer sampling method.
Efficient Ensemble Model Generation for Uncertainty Estimation with Bayesian Approximation in Segmentation
Experimental results show that the proposed method could provide useful uncertainty information by Bayesian approximation with the efficient ensemble model generation and improve the predictive performance.
Spatio-temporal Learning from Longitudinal Data for Multiple Sclerosis Lesion Segmentation
Our results show that spatio-temporal information in longitudinal data is a beneficial cue for improving segmentation.
Confident Coreset for Active Learning in Medical Image Analysis
Active learning is one of the solutions to this problem where an active learner is designed to indicate which samples need to be annotated to effectively train a target model.
TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networks
Automatic surgical phase recognition is a challenging and crucial task with the potential to improve patient safety and become an integral part of intra-operative decision-support systems.
Ranked #5 on
Surgical phase recognition
on Cholec80
Force-Ultrasound Fusion: Bringing Spine Robotic-US to the Next "Level"
Processed force and ultrasound data are fused using a 1D Convolutional Network to compute the location of the vertebral levels.
Improving Feature Attribution through Input-specific Network Pruning
Attributing the output of a neural network to the contribution of given input elements is a way of shedding light on the black-box nature of neural networks.
Generation of Multimodal Justification Using Visual Word Constraint Model for Explainable Computer-Aided Diagnosis
The ambiguity of the decision-making process has been pointed out as the main obstacle to applying the deep learning-based method in a practical way in spite of its outstanding performance.
Feature2Mass: Visual Feature Processing in Latent Space for Realistic Labeled Mass Generation
In order to learn deep network model to be well-behaved in bio-image computing fields, a lot of labeled data is required.
ICADx: Interpretable computer aided diagnosis of breast masses
In this paper, we investigate interpretability in CADx with the proposed interpretable CADx (ICADx) framework.
Facial Dynamics Interpreter Network: What are the Important Relations between Local Dynamics for Facial Trait Estimation?
In this paper, a novel deep learning approach, named facial dynamics interpreter network, has been proposed to interpret the important relations between local dynamics for estimating facial traits from expression sequence.
Differential Generative Adversarial Networks: Synthesizing Non-linear Facial Variations with Limited Number of Training Data
through a generative model is helpful in addressing the lack of training data.
Convolution with Logarithmic Filter Groups for Efficient Shallow CNN
Our classification results on Multi-PIE dataset for facial expression recognition and CIFAR-10 dataset for object classification reveal that the compact CNN with the proposed logarithmic filter grouping scheme outperforms the same network with the uniform filter grouping in terms of accuracy and parameter efficiency.
EvaluationNet: Can Human Skill be Evaluated by Deep Networks?
In order to improve the effectiveness of the learning with instructional video, observation and evaluation of the activity are required.
