23 citations · 96 across the 26 of their papers we have counts for
26 papers
ShapKO: Shapley-Adaptive Modality Knockout for Robust Multimodal Learning
Nusrat Binta Nizam, Fengbei Liu, Sunwoo Kwak +3
Multimodal medical models often degrade when inputs are missing, a common scenario in real-world clinical workflows. Separately, even when all modalities are present, modality domi…
MAdam: Metric-Aware Multi-Objective Adam
Fengbei Liu, Rachit Saluja, Sunwoo Kwak +5
Multi-objective optimization (MOO) underlies many machine learning problems, yet MOO solvers across the loss-balancing, gradient-balancing, and Pareto-based families almost univers…
From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding
Yuyuan Liu, Yiping Ji, Anjie Le +6
Finetuning Large Vision-Language Models with reinforcement learning has emerged as a promising approach to enhance their capability in object-level grounding. However, existing met…
BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation
Rachit Saluja, Asli Cihangir, Ruining Deng +3
Segmenting small lesions in medical images remains notoriously difficult. Most prior work tackles this challenge by either designing better architectures, loss functions, or data a…
Cross- and Intra-image Prototypical Learning for Multi-label Disease Diagnosis and Interpretation
Chong Wang, Fengbei Liu, Yuanhong Chen +2
Recent advances in prototypical learning have shown remarkable potential to provide useful decision interpretations associating activation maps and predictions with class-specific…
Knockout: A simple way to handle missing inputs
Minh Nguyen, Batuhan K. Karaman, Heejong Kim +3
Deep learning models benefit from rich (e.g., multi-modal) input features. However, multimodal models might be challenging to deploy, because some inputs may be missing at inferenc…
Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognition
Chong Wang, Yuanhong Chen, Fengbei Liu +4
Prototypical-part methods, e.g., ProtoPNet, enhance interpretability in image recognition by linking predictions to training prototypes, thereby offering intuitive insights into th…
Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation
Fengbei Liu, Chong Wang, Yuanhong Chen +2
Although noisy-label learning is often approached with discriminative methods for simplicity and speed, generative modeling offers a principled alternative by capturing the joint m…
Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation
Yuanhong Chen, Yuyuan Liu, Hu Wang +4
Audio-visual segmentation (AVS) is a challenging task that involves accurately segmenting sounding objects based on audio-visual cues. The effectiveness of audio-visual learning cr…
Learning Support and Trivial Prototypes for Interpretable Image Classification
Chong Wang, Yuyuan Liu, Yuanhong Chen +5
Prototypical part network (ProtoPNet) methods have been designed to achieve interpretable classification by associating predictions with a set of training prototypes, which we refe…
Asymmetric Co-teaching with Multi-view Consensus for Noisy Label Learning
Fengbei Liu, Yuanhong Chen, Chong Wang +2
Learning with noisy-labels has become an important research topic in computer vision where state-of-the-art (SOTA) methods explore: 1) prediction disagreement with co-teaching stra…
Multi-view Local Co-occurrence and Global Consistency Learning Improve Mammogram Classification Generalisation
Yuanhong Chen, Hu Wang, Chong Wang +6
When analysing screening mammograms, radiologists can naturally process information across two ipsilateral views of each breast, namely the cranio-caudal (CC) and mediolateral-obli…
Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Models
Chong Wang, Yuanhong Chen, Yuyuan Liu +6
State-of-the-art (SOTA) deep learning mammogram classifiers, trained with weakly-labelled images, often rely on global models that produce predictions with limited interpretability…
Translation Consistent Semi-supervised Segmentation for 3D Medical Images
Yuyuan Liu, Yu Tian, Chong Wang +4
3D medical image segmentation methods have been successful, but their dependence on large amounts of voxel-level annotated data is a disadvantage that needs to be addressed given t…
Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detection
Yu Tian, Guansong Pang, Fengbei Liu +5
Current polyp detection methods from colonoscopy videos use exclusively normal (i.e., healthy) training images, which i) ignore the importance of temporal information in consecutiv…
Unsupervised Anomaly Detection in Medical Images with a Memory-augmented Multi-level Cross-attentional Masked Autoencoder
Yu Tian, Guansong Pang, Yuyuan Liu +7
Unsupervised anomaly detection (UAD) aims to find anomalous images by optimising a detector using a training set that contains only normal images. UAD approaches can be based on re…
BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification
Yuanhong Chen, Fengbei Liu, Hu Wang +4
Deep learning methods have shown outstanding classification accuracy in medical imaging problems, which is largely attributed to the availability of large-scale datasets manually a…
ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image Classification
Fengbei Liu, Yu Tian, Yuanhong Chen +3
Effective semi-supervised learning (SSL) in medical image analysis (MIA) must address two challenges: 1) work effectively on both multi-class (e.g., lesion classification) and mult…
Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
Yuyuan Liu, Yu Tian, Yuanhong Chen +3
Consistency learning using input image, feature, or network perturbations has shown remarkable results in semi-supervised semantic segmentation, but this approach can be seriously…
Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes
Yu Tian, Yuyuan Liu, Guansong Pang +3
State-of-the-art (SOTA) anomaly segmentation approaches on complex urban driving scenes explore pixel-wise classification uncertainty learned from outlier exposure, or external rec…
Self-supervised Pseudo Multi-class Pre-training for Unsupervised Anomaly Detection and Segmentation in Medical Images
Yu Tian, Fengbei Liu, Guansong Pang +5
Unsupervised anomaly detection (UAD) methods are trained with normal (or healthy) images only, but during testing, they are able to classify normal and abnormal (or disease) images…
3D Semantic Mapping from Arthroscopy using Out-of-distribution Pose and Depth and In-distribution Segmentation Training
Yaqub Jonmohamadi, Shahnewaz Ali, Fengbei Liu +4
Minimally invasive surgery (MIS) has many documented advantages, but the surgeon's limited visual contact with the scene can be problematic. Hence, systems that can help surgeons n…
NVUM: Non-Volatile Unbiased Memory for Robust Medical Image Classification
Fengbei Liu, Yuanhong Chen, Yu Tian +4
Real-world large-scale medical image analysis (MIA) datasets have three challenges: 1) they contain noisy-labelled samples that affect training convergence and generalisation, 2) t…
Self-supervised Mean Teacher for Semi-supervised Chest X-ray Classification
Fengbei Liu, Yu Tian, Filipe R. Cordeiro +3
The training of deep learning models generally requires a large amount of annotated data for effective convergence and generalisation. However, obtaining high-quality annotations i…