Ali Cheraghian, Shafin Rahman, Sameera Ramasinghe, Pengfei Fang et al.
Few-shot class incremental learning (FSCIL) aims to incrementally add sets of novel classes to a well-trained base model in multiple training sessions with the restriction that only a few novel instances are available per class. While learning novel classes, FSCIL methods gradually forget base (old)...
Ali Cheraghian, Shafin Rahman, Townim Faisal Chowdhury, Dylan Campbell et al.
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, despite the increasing ubiquity of 3D sensors, the corresponding 3D point cloud classification problem has not been meaning...
Yanshuo Wang, Jie Hong, Ali Cheraghian, Shafin Rahman et al.
The objective of Continual Test-time Domain Adaptation (CTDA) is to gradually adapt a pre-trained model to a sequence of target domains without accessing the source data. This paper proposes a Dynamic Sample Selection (DSS) method for CTDA. DSS consists of dynamic thresholding, positive learning, an...
Townim Faisal Chowdhury, Ali Cheraghian, Sameera Ramasinghe, Sahar Ahmadi et al.
Ali Cheraghian, Shafin Rahman, Pengfei Fang, Soumava Kumar Roy et al.
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 limited number of examples for training, the techniques developed for standard incremental learning cannot be applied ve...
Yanshuo Wang, Ali Cheraghian, Zeeshan Hayder, Jie Hong et al.
Real-world systems often encounter new data over time, which leads to experiencing target domain shifts. Existing Test- Time Adaptation (TTA) methods tend to apply computationally heavy and memory-intensive backpropagation-based approaches to handle this. Here, we propose a novel method that uses a ...
Majid Nasiri, Ali Cheraghian, Townim Faisal Chowdhury, Sahar Ahmadi et al.
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 of robust pre-trained feature extraction models. To address this problem, we propose a prompt-guided 3D scene generation ...
Sahar Ahmadi, Ali Cheraghian, Townim Faisal Chowdhury, Morteza Saberi et al.
Sahar Ahmadi, Ali Cheraghian, Morteza Saberi, Md. Towsif Abir et al.
Ali Cheraghian, Zeeshan Hayder, Sameera Ramasinghe, Shafin Rahman et al.
Fahimul Hoque Shubho, Townim Faisal Chowdhury, Ali Cheraghian, Morteza Saberi et al.
Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen classes to the unseen classes. Existing methods of obtaining class semantics include manual attributes or automatic word vector...
Hamidreza Dastmalchi, Aijun An, Ali Cheraghian, Shafin Rahman et al.
Test-time adaptation (TTA) of 3D point clouds is crucial for mitigating discrepancies between training and testing samples in real-world scenarios, particularly when handling corrupted point clouds. LiDAR data, for instance, can be affected by sensor failures or environmental factors, causing domain...
Townim Faisal Chowdhury, Mahira Jalisha, Ali Cheraghian, Shafin Rahman
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-life applications, we may be interested in learning new classes without forgetting the capability of previous experience. S...