salient object detection
A Simple Pooling-Based Design for Real-Time Salient Object Detection (2019 CVPR)
Global Guidance Module (GGM) : PPM feature 與 FPN 每個(gè)level 融合。增加RF,緩解obj預(yù)測不完整。
Feature Aggregation Module (FAM): 類似PPM,add代替concate。
? ? ? ?1、reducing the aliasing effect of upsampling。
? ? ? ?2、allows each spatial location to view the local?context at different scale spaces, context at different scale spaces
joint training:edge data(BCE)和 salient data (CE)交替訓(xùn)練,細(xì)化edge。
Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection (2019 CVPR)
depth label 與 SOD 結(jié)合。
Contrast-enhanced Net(CEN):增加depth map前景背景的contrast,類內(nèi)緊湊,類間可分。
original depth map?contrast?not obvious enough
????
cross-modal fusion:Enhanced map 作為 attention map??
Fluid Pyramid Integration(FPI):FPI leads all the highlevel features into low-level features for every node.
B+C>B+C+M,?meets feature compatibility problem
LOSS:saliency?cross-entropy loss + 5?contrast loss
總結(jié)
以上是生活随笔為你收集整理的salient object detection的全部內(nèi)容,希望文章能夠幫你解決所遇到的問題。
- 上一篇: 计算机专业教师资格证考什么内容,计算机教
- 下一篇: sadfa