FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2510182739> ?p ?o ?g. }

• W2510182739 abstract "In this work we introduce a convolutional neural network (CNN) that jointly handles low-, mid-, and high-level vision tasks in a unified architecture that is trained end-to-end. Such a universal network can act like a `swiss knife' for vision tasks; we call this architecture an UberNet to indicate its overarching nature. We address two main technical challenges that emerge when broadening up the range of tasks handled by a single CNN: (i) training a deep architecture while relying on diverse training sets and (ii) training many (potentially unlimited) tasks with a limited memory budget. Properly addressing these two problems allows us to train accurate predictors for a host of tasks, without compromising accuracy. Through these advances we train in an end-to-end manner a CNN that simultaneously addresses (a) boundary detection (b) normal estimation (c) saliency estimation (d) semantic segmentation (e) human part segmentation (f) semantic boundary detection, (g) region proposal generation and object detection. We obtain competitive performance while jointly addressing all of these tasks in 0.7 seconds per frame on a single GPU. A demonstration of this system can be found at this http URL." @default.
• W2510182739 created "2016-09-16" @default.
• W2510182739 creator A5077035803 @default.
• W2510182739 date "2016-09-07" @default.
• W2510182739 modified "2023-10-01" @default.
• W2510182739 title "UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory" @default.
• W2510182739 cites W125693051 @default.
• W2510182739 cites W1529410181 @default.
• W2510182739 cites W1539790486 @default.
• W2510182739 cites W1673923490 @default.
• W2510182739 cites W174734558 @default.
• W2510182739 cites W1817277359 @default.
• W2510182739 cites W1861492603 @default.
• W2510182739 cites W1869500417 @default.
• W2510182739 cites W1885185971 @default.
• W2510182739 cites W1896424170 @default.
• W2510182739 cites W1897243830 @default.
• W2510182739 cites W1899309388 @default.
• W2510182739 cites W1901129140 @default.
• W2510182739 cites W1902568950 @default.
• W2510182739 cites W1903029394 @default.
• W2510182739 cites W1905829557 @default.
• W2510182739 cites W1910619957 @default.
• W2510182739 cites W1929856797 @default.
• W2510182739 cites W1930528368 @default.
• W2510182739 cites W1942214758 @default.
• W2510182739 cites W1947031653 @default.
• W2510182739 cites W1949049686 @default.
• W2510182739 cites W1953465585 @default.
• W2510182739 cites W1976047850 @default.
• W2510182739 cites W1994488211 @default.
• W2510182739 cites W2022508996 @default.
• W2510182739 cites W2037227137 @default.
• W2510182739 cites W2037954058 @default.
• W2510182739 cites W2086791339 @default.
• W2510182739 cites W2097117768 @default.
• W2510182739 cites W2102605133 @default.
• W2510182739 cites W2110158442 @default.
• W2510182739 cites W2112796928 @default.
• W2510182739 cites W2113325037 @default.
• W2510182739 cites W2115240329 @default.
• W2510182739 cites W2117539524 @default.
• W2510182739 cites W2121927366 @default.
• W2510182739 cites W2125215748 @default.
• W2510182739 cites W2127251585 @default.
• W2510182739 cites W2131297486 @default.
• W2510182739 cites W2137223622 @default.
• W2510182739 cites W2144794286 @default.
• W2510182739 cites W2158865742 @default.
• W2510182739 cites W2161236525 @default.
• W2510182739 cites W2165140157 @default.
• W2510182739 cites W2171048379 @default.
• W2510182739 cites W2172014587 @default.
• W2510182739 cites W2194775991 @default.
• W2510182739 cites W2216125271 @default.
• W2510182739 cites W2223120221 @default.
• W2510182739 cites W2226771013 @default.
• W2510182739 cites W2236679687 @default.
• W2510182739 cites W2255781698 @default.
• W2510182739 cites W2288122362 @default.
• W2510182739 cites W2290180618 @default.
• W2510182739 cites W2309415944 @default.
• W2510182739 cites W2325368899 @default.
• W2510182739 cites W2338908902 @default.
• W2510182739 cites W2339391301 @default.
• W2510182739 cites W2341204628 @default.
• W2510182739 cites W2363162442 @default.
• W2510182739 cites W2381998130 @default.
• W2510182739 cites W2407521645 @default.
• W2510182739 cites W2470948946 @default.
• W2510182739 cites W252252322 @default.
• W2510182739 cites W2613718673 @default.
• W2510182739 cites W2949086864 @default.
• W2510182739 cites W2949117887 @default.
• W2510182739 cites W2949213045 @default.
• W2510182739 cites W2949370174 @default.
• W2510182739 cites W2949896259 @default.
• W2510182739 cites W2950064337 @default.
• W2510182739 cites W2950094539 @default.
• W2510182739 cites W2950209802 @default.
• W2510182739 cites W2950612966 @default.
• W2510182739 cites W2950622378 @default.
• W2510182739 cites W2950650321 @default.
• W2510182739 cites W2950762923 @default.
• W2510182739 cites W2950891598 @default.
• W2510182739 cites W2951329458 @default.
• W2510182739 cites W2951478140 @default.
• W2510182739 cites W2951548216 @default.
• W2510182739 cites W2951548327 @default.
• W2510182739 cites W2952637581 @default.
• W2510182739 cites W2952865063 @default.
• W2510182739 cites W2953382498 @default.
• W2510182739 cites W2962803021 @default.
• W2510182739 cites W2962835968 @default.
• W2510182739 cites W2962872526 @default.
• W2510182739 cites W2963542991 @default.
• W2510182739 cites W2964056935 @default.
• W2510182739 cites W2964288706 @default.
• W2510182739 cites W3209862660 @default.
• W2510182739 cites W337610345 @default.

• next