182 citations · 305 across the 18 of their papers we have counts for
24 papers
Uncertainty Aware Neural Network from Similarity and Sensitivity
H M Dipu Kabir, Subrota Kumar Mondal, Sadia Khanam +8
Researchers have proposed several approaches for neural network (NN) based uncertainty quantification (UQ). However, most of the approaches are developed considering strong assumpt…
COLT: Cyclic Overlapping Lottery Tickets for Faster Pruning of Convolutional Neural Networks
Md. Ismail Hossain, Mohammed Rakib, M. M. Lutfe Elahi +2
Pruning refers to the elimination of trivial weights from neural networks. The sub-networks within an overparameterized model produced after pruning are often called Lottery ticket…
Exemplar Guided Deep Neural Network for Spatial Transcriptomics Analysis of Gene Expression Prediction
Yan Yang, Md Zakir Hossain, Eric A Stone +1
Spatial transcriptomics (ST) is essential for understanding diseases and developing novel treatments. It measures gene expression of each fine-grained area (i.e., different windows…
Less is More: Facial Landmarks can Recognize a Spontaneous Smile
Md. Tahrim Faroque, Yan Yang, Md Zakir Hossain +3
Smile veracity classification is a task of interpreting social interactions. Broadly, it distinguishes between spontaneous and posed smiles. Previous approaches used hand-engineere…
Prompt-guided Scene Generation for 3D Zero-Shot Learning
Majid Nasiri, Ali Cheraghian, Townim Faisal Chowdhury +3
Zero-shot learning on 3D point cloud data is a related underexplored problem compared to its 2D image counterpart. 3D data brings new challenges for ZSL due to the unavailability o…
Rethinking Task-Incremental Learning Baselines
Md Sazzad Hossain, Pritom Saha, Townim Faisal Chowdhury +3
It is common to have continuous streams of new data that need to be introduced in the system in real-world applications. The model needs to learn newly added capabilities (future t…
Few-shot Class-incremental Learning for 3D Point Cloud Objects
Townim Chowdhury, Ali Cheraghian, Sameera Ramasinghe +3
Few-shot class-incremental learning (FSCIL) aims to incrementally fine-tune a model (trained on base classes) for a novel set of classes using a few examples without forgetting the…
DPST: De Novo Peptide Sequencing with Amino-Acid-Aware Transformers
Yan Yang, Zakir Hossain, Khandaker Asif +3
De novo peptide sequencing aims to recover amino acid sequences of a peptide from tandem mass spectrometry (MS) data. Existing approaches for de novo analysis enumerate MS evidence…
Learning without Forgetting for 3D Point Cloud Objects
Townim Chowdhury, Mahira Jalisha, Ali Cheraghian +1
When we fine-tune a well-trained deep learning model for a new set of classes, the network learns new concepts but gradually forgets the knowledge of old training. In some real-lif…
Zero-Shot Learning on 3D Point Cloud Objects and Beyond
Ali Cheraghian, Shafinn Rahman, Townim F. Chowdhury +2
Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification. However, des…
Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning
Ali Cheraghian, Shafin Rahman, Pengfei Fang +3
Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts gradually, where only a few examples per concept are available to the learner. Due to the…
S2FGAN: Semantically Aware Interactive Sketch-to-Face Translation
Yan Yang, Md Zakir Hossain, Tom Gedeon +1
Interactive facial image manipulation attempts to edit single and multiple face attributes using a photo-realistic face and/or semantic mask as input. In the absence of the photo-r…
Classifying Eye-Tracking Data Using Saliency Maps
Shafin Rahman, Sejuti Rahman, Omar Shahid +2
A plethora of research in the literature shows how human eye fixation pattern varies depending on different factors, including genetics, age, social functioning, cognitive function…
Synthesizing the Unseen for Zero-shot Object Detection
Nasir Hayat, Munawar Hayat, Shafin Rahman +3
The existing zero-shot detection approaches project visual features to the semantic domain for seen objects, hoping to map unseen objects to their corresponding semantics during in…
RealSmileNet: A Deep End-To-End Network for Spontaneous and Posed Smile Recognition
Yan Yang, Md Zakir Hossain, Tom Gedeon +1
Smiles play a vital role in the understanding of social interactions within different communities, and reveal the physical state of mind of people in both real and deceptive ways.…
Any-Shot Object Detection
Shafin Rahman, Salman Khan, Nick Barnes +1
Previous work on novel object detection considers zero or few-shot settings where none or few examples of each category are available for training. In real world scenarios, it is l…
Transductive Zero-Shot Learning for 3D Point Cloud Classification
Ali Cheraghian, Shafin Rahman, Dylan Campbell +1
Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification. However desp…
Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects
Ali Cheraghian, Shafin Rahman, Dylan Campbell +1
The development of advanced 3D sensors has enabled many objects to be captured in the wild at a large scale, and a 3D object recognition system may therefore encounter many objects…
Zero-shot Learning of 3D Point Cloud Objects
Ali Cheraghian, Shafin Rahman, Lars Petersson
Recent deep learning architectures can recognize instances of 3D point cloud objects of previously seen classes quite well. At the same time, current 3D depth camera technology all…
Task-generalizable Adversarial Attack based on Perceptual Metric
Muzammal Naseer, Salman H. Khan, Shafin Rahman +1
Deep neural networks (DNNs) can be easily fooled by adding human imperceptible perturbations to the images. These perturbed images are known as `adversarial examples' and pose a se…
Polarity Loss for Zero-shot Object Detection
Shafin Rahman, Salman Khan, Nick Barnes
Conventional object detection models require large amounts of training data. In comparison, humans can recognize previously unseen objects by merely knowing their semantic descript…
Deep Multiple Instance Learning for Zero-shot Image Tagging
Shafin Rahman, Salman Khan
In-line with the success of deep learning on traditional recognition problem, several end-to-end deep models for zero-shot recognition have been proposed in the literature. These m…
Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts
Shafin Rahman, Salman Khan, Fatih Porikli
Current Zero-Shot Learning (ZSL) approaches are restricted to recognition of a single dominant unseen object category in a test image. We hypothesize that this setting is ill-suite…
A Unified approach for Conventional Zero-shot, Generalized Zero-shot and Few-shot Learning
Shafin Rahman, Salman H. Khan, Fatih Porikli
Prevalent techniques in zero-shot learning do not generalize well to other related problem scenarios. Here, we present a unified approach for conventional zero-shot, generalized ze…