activity
20182022
most citedKnowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains

25 citations · 40 across the 8 of their papers we have counts for

collaborators

12 papers

cs.CV2022★ 1 cited

Knowledge Distillation for Multi-Target Domain Adaptation in Real-Time Person Re-Identification

Félix Remigereau, Djebril Mekhazni, Sajjad Abdoli +3

Despite the recent success of deep learning architectures, person re-identification (ReID) remains a challenging problem in real-word applications. Several unsupervised single-targ…

cs.CV2022★ 1 cited

Dynamic Template Selection Through Change Detection for Adaptive Siamese Tracking

Madhu Kiran, Le Thanh Nguyen-Meidine, Rajat Sahay +3

Deep Siamese trackers have recently gained much attention in recent years since they can track visual objects at high speeds. Additionally, adaptive tracking methods, where target…

cs.CV2022★ 2 cited

Generative Target Update for Adaptive Siamese Tracking

Madhu Kiran, Le Thanh Nguyen-Meidine, Rajat Sahay +3

Siamese trackers perform similarity matching with templates (i.e., target models) to recursively localize objects within a search region. Several strategies have been proposed in t…

cs.CV2021★ 11 cited

Holistic Guidance for Occluded Person Re-Identification

Madhu Kiran, R Gnana Praveen, Le Thanh Nguyen-Meidine +3

In real-world video surveillance applications, person re-identification (ReID) suffers from the effects of occlusions and detection errors. Despite recent advances, occlusions cont…

cs.CV2021

Incremental Multi-Target Domain Adaptation for Object Detection with Efficient Domain Transfer

Le Thanh Nguyen-Meidine, Madhu Kiran, Marco Pedersoli +3

Recent advances in unsupervised domain adaptation have significantly improved the recognition accuracy of CNNs by alleviating the domain shift between (labeled) source and (unlabel…

cs.CV2021★ 25 cited

Knowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains

Le Thanh Nguyen-Meidine, Atif Belal, Madhu Kiran +3

Beyond the complexity of CNNs that require training on large annotated datasets, the domain shift between design and operational data has limited the adoption of CNNs in many real-…