113 citations · 299 across the 71 of their papers we have counts for
15 papers · 1 filter
Dilated Balanced Cross Entropy Loss for Medical Image Segmentation
Seyed Mohsen Hosseini, Mahdieh Soleymani Baghshah
A novel method for tackling the problem of imbalanced data in medical image segmentation is proposed in this work. In balanced cross entropy (CE) loss, which is a type of weighted…
LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions
Faridoun Mehri, Mahdieh Soleymani Baghshah, Mohammad Taher Pilehvar
Why do gradient-based explanations struggle with Transformers, and how can we improve them? We identify gradient flow imbalances in Transformers that violate FullGrad-completeness,…
CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectives
Armin Saghafian, Amirmohammad Izadi, Negin Hashemi Dijujin +1
Grounding the instruction in the environment is a key step in solving language-guided goal-reaching reinforcement learning problems. In automated reinforcement learning, a key conc…
Improving 3D Few-Shot Segmentation with Inference-Time Pseudo-Labeling
Mohammad Mozafari, Hosein Hasani, Reza Vahidimajd +2
In recent years, few-shot segmentation (FSS) models have emerged as a promising approach in medical imaging analysis, offering remarkable adaptability to segment novel classes with…
Trained Models Tell Us How to Make Them Robust to Spurious Correlation without Group Annotation
Mahdi Ghaznavi, Hesam Asadollahzadeh, Fahimeh Hosseini Noohdani +5
Classifiers trained with Empirical Risk Minimization (ERM) tend to rely on attributes that have high spurious correlation with the target. This can degrade the performance on under…
PreND: Enhancing Intrinsic Motivation in Reinforcement Learning through Pre-trained Network Distillation
Mohammadamin Davoodabadi, Negin Hashemi Dijujin, Mahdieh Soleymani Baghshah
Intrinsic motivation, inspired by the psychology of developmental learning in infants, stimulates exploration in agents without relying solely on sparse external rewards. Existing…