A2dele: Adaptive and Attentive Depth Distiller for Efficient RGB-D Salient Object Detection

CVPR 2020 Yongri Piao Zhengkun Rong Miao Zhang Weisong Ren Huchuan Lu

Existing state-of-the-art RGB-D salient object detection methods explore RGB-D data relying on a two-stream architecture, in which an independent subnetwork is required to process depth data. This inevitably incurs extra computational costs and memory consumption, and using depth data during testing may hinder the practical applications of RGB-D saliency detection... (read more)

PDF Abstract

Results from the Paper


Ranked #10 on RGB-D Salient Object Detection on NJU2K (Average MAE metric, using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
BENCHMARK
RGB-D Salient Object Detection NJU2K A2dele Average MAE 0.051 # 10

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet