External Prompt Features Enhanced Parameter-efficient Fine-tuning for Salient Object Detection

arXiv:2404.15008v1 Announce Type: new
Abstract: Salient object detection (SOD) aims at finding the most salient objects in images and outputs pixel-level binary masks. Transformer-based methods achieve promising performance due to their global semantic understanding, crucial for identifying salient objects. However, these models tend to be large and require numerous training parameters. To better harness the potential of transformers for SOD, we propose a novel parameter-efficient fine-tuning method aimed at reducing the number of training parameters while enhancing the salient object …

abstract arxiv binary cs.cv detection features fine-tuning global however images masks object objects performance pixel prompt semantic training transformer type understanding