Adaptive decoders for FLIM networks applied to salient object detection

This repository contains the source code for the experiments on Feature Learning from Image Markers with Adaptive Decoders (FLIM-AD). The proposed method builds lightweight CNN encoders from small training datasets and combines them with Adaptive Decoders to perform Salient Object Detection (SOD) efficiently. The code enables the full reproduction of results presented in the Master’s thesis: “Adaptive Decoders for FLIM Networks Applied to Salient Object Detection”, and supports the findings reported in the article: “FLIM-Based Salient Object Detection Networks with Adaptive Decoders”.