CNN-based salient object detection (SOD) methods achieve impressive performance. However, the way semantic information is encoded in them and whether they are category-agnostic is less explored. On…
Viswanathan, Harish - Uusitalo, Mikko A. - Kokkoniemi-Tarkkanen, Heli - Grudnitsky, Artjom - Moisio, Martti - Harkonen, Teemu - Yli-Paunu, Pekka - Horsmanheimo, Seppo - Samardzija, Dragan