1 citations · 1 across the 8 of their papers we have counts for
9 papers
Deep Attention-guided Adaptive Subsampling
Sharath M Shankaranarayana, Soumava Kumar Roy, Prasad Sudhakar +1
Although deep neural networks have provided impressive gains in performance, these improvements often come at the cost of increased computational complexity and expense. In many ca…
Learning from Noisy Labels with Contrastive Co-Transformer
Yan Han, Soumava Kumar Roy, Mehrtash Harandi +1
Deep learning with noisy labels is an interesting challenge in weakly supervised learning. Despite their significant learning capacity, CNNs have a tendency to overfit in the prese…
Vision-Based Power Line Cables and Pylons Detection for Low Flying Aircraft
Jakub Gwizdała, Doruk Oner, Soumava Kumar Roy +6
Power lines are dangerous for low-flying aircraft, especially in low-visibility conditions. Thus, a vision-based system able to analyze the aircraft's surroundings and to provide t…
Occlusion Resilient 3D Human Pose Estimation
Soumava Kumar Roy, Ilia Badanin, Sina Honari +1
Occlusions remain one of the key challenges in 3D body pose estimation from single-camera video sequences. Temporal consistency has been extensively used to mitigate their impact b…
FORML: A Riemannian Hessian-free Method for Meta-learning on Stiefel Manifolds
Hadi Tabealhojeh, Soumava Kumar Roy, Peyman Adibi +1
Meta-learning problem is usually formulated as a bi-level optimization in which the task-specific and the meta-parameters are updated in the inner and outer loops of optimization,…
Learning Deep Optimal Embeddings with Sinkhorn Divergences
Soumava Kumar Roy, Yan Han, Mehrtash Harandi +1
Deep Metric Learning algorithms aim to learn an efficient embedding space to preserve the similarity relationships among the input data. Whilst these algorithms have achieved signi…
On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation
Soumava Kumar Roy, Leonardo Citraro, Sina Honari +1
Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. However, as the acquisition of ground-truth 3D labels is labo…
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…
Cross-Correlated Attention Networks for Person Re-Identification
Jieming Zhou, Soumava Kumar Roy, Pengfei Fang +2
Deep neural networks need to make robust inference in the presence of occlusion, background clutter, pose and viewpoint variations -- to name a few -- when the task of person re-id…