211 citations · 276 across the 4 of their papers we have counts for
5 papers
Training DNNs in O(1) memory with MEM-DFA using Random Matrices
Tien Chu, Kamil Mykitiuk, Miron Szewczyk +2
This work presents a method for reducing memory consumption to a constant complexity when training deep neural networks. The algorithm is based on the more biologically plausible a…
Holistic Multi-View Building Analysis in the Wild with Projection Pooling
Zbigniew Wojna, Krzysztof Maziarz, Łukasz Jocz +3
We address six different classification tasks related to fine-grained building attributes: construction type, number of floors, pitch and geometry of the roof, facade material, and…
Large-scale mammography CAD with Deformable Conv-Nets
Stephen Morrell, Zbigniew Wojna, Can Son Khoo +2
State-of-the-art deep learning methods for image processing are evolving into increasingly complex meta-architectures with a growing number of modules. Among them, region-based ful…
Augmentation for small object detection
Mate Kisantal, Zbigniew Wojna, Jakub Murawski +2
In recent years, object detection has experienced impressive progress. Despite these improvements, there is still a significant gap in the performance between the detection of smal…
Semantic Instance Segmentation via Deep Metric Learning
Alireza Fathi, Zbigniew Wojna, Vivek Rathod +4
We propose a new method for semantic instance segmentation, by first computing how likely two pixels are to belong to the same object, and then by grouping similar pixels together.…