14 citations · 23 across the 13 of their papers we have counts for
5 papers · 1 filter
Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning
Mark D. McDonnell, Dong Gong, Ehsan Abbasnejad +1
Continual learning requires a model to adapt to ongoing changes in the data distribution, and often to the set of tasks to be performed. It is rare, however, that the data and task…
SCONE-GAN: Semantic Contrastive learning-based Generative Adversarial Network for an end-to-end image translation
Iman Abbasnejad, Fabio Zambetta, Flora Salim +4
SCONE-GAN presents an end-to-end image translation, which is shown to be effective for learning to generate realistic and diverse scenery images. Most current image-to-image transl…
Progressive Feature Adjustment for Semi-supervised Learning from Pretrained Models
Hai-Ming Xu, Lingqiao Liu, Hao Chen +2
As an effective way to alleviate the burden of data annotation, semi-supervised learning (SSL) provides an attractive solution due to its ability to leverage both labeled and unlab…
ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning
Islam Nassar, Munawar Hayat, Ehsan Abbasnejad +2
Confidence-based pseudo-labeling is among the dominant approaches in semi-supervised learning (SSL). It relies on including high-confidence predictions made on unlabeled data as ad…
EBMs vs. CL: Exploring Self-Supervised Visual Pretraining for Visual Question Answering
Violetta Shevchenko, Ehsan Abbasnejad, Anthony Dick +2
The availability of clean and diverse labeled data is a major roadblock for training models on complex tasks such as visual question answering (VQA). The extensive work on large vi…