TY - JOUR AU - Lee, Min Seok AU - Shin, WooSeok AU - Han, Sung Won PY - 2022/06/28 Y2 - 2024/03/29 TI - TRACER: Extreme Attention Guided Salient Object Tracing Network (Student Abstract) JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 36 IS - 11 SE - AAAI Student Abstract and Poster Program DO - 10.1609/aaai.v36i11.21633 UR - https://ojs.aaai.org/index.php/AAAI/article/view/21633 SP - 12993-12994 AB - Existing studies on salient object detection (SOD) focus on extracting distinct objects with edge features and aggregating multi-level features to improve SOD performance. However, both performance gain and computational efficiency cannot be achieved, which has motivated us to study the inefficiencies in existing encoder-decoder structures to avoid this trade-off. We propose TRACER which excludes multi-decoder structures and minimizes the learning parameters usage by employing attention guided tracing modules (ATMs), as shown in Fig. 1. ER -