66 citations · 117 across the 8 of their papers we have counts for
9 papers
Token Pooling in Vision Transformers
Dmitrii Marin, Jen-Hao Rick Chang, Anurag Ranjan +3
Despite the recent success in many applications, the high computational requirements of vision transformers limit their use in resource-constrained settings. While many existing me…
Robust Trust Region for Weakly Supervised Segmentation
Dmitrii Marin, Yuri Boykov
Acquisition of training data for the standard semantic segmentation is expensive if requiring that each pixel is labeled. Yet, current methods significantly deteriorate in weakly s…
Confluent Vessel Trees with Accurate Bifurcations
Zhongwen Zhang, Dmitrii Marin, Maria Drangova +1
We are interested in unsupervised reconstruction of complex near-capillary vasculature with thousands of bifurcations where supervision and learning are infeasible. Unsupervised me…
Efficient Segmentation: Learning Downsampling Near Semantic Boundaries
Dmitrii Marin, Zijian He, Peter Vajda +4
Many automated processes such as auto-piloting rely on a good semantic segmentation as a critical component. To speed up performance, it is common to downsample the input frame. Ho…
Divergence Prior and Vessel-tree Reconstruction
Zhongwen Zhang, Egor Chesakov, Dmitrii Marin +1
We propose a new geometric regularization principle for reconstructing vector fields based on prior knowledge about their divergence. As one important example of this general idea,…
Beyond Gradient Descent for Regularized Segmentation Losses
Dmitrii Marin, Meng Tang, Ismail Ben Ayed +1
The simplicity of gradient descent (GD) made it the default method for training ever-deeper and complex neural networks. Both loss functions and architectures are often explicitly…