ML Anthology

TRACER: Extreme Attention Guided Salient Object Tracing Network (Student Abstract)

Min Seok Lee, Wooseok Shin, Sung Won Han
AAAI 2022 pp. 12993-12994
doi:10.1609/AAAI.V36I11.21633 /aaai/2022/lee2022aaai-tracer/

Abstract

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.

PDF AAAI Semantic Scholar

Cite

Text

Lee et al. "TRACER: Extreme Attention Guided Salient Object Tracing Network (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I11.21633

Markdown

[Lee et al. "TRACER: Extreme Attention Guided Salient Object Tracing Network (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/lee2022aaai-tracer/) doi:10.1609/AAAI.V36I11.21633

BibTeX

@inproceedings{lee2022aaai-tracer,
  title     = {{TRACER: Extreme Attention Guided Salient Object Tracing Network (Student Abstract)}},
  author    = {Lee, Min Seok and Shin, Wooseok and Han, Sung Won},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {12993-12994},
  doi       = {10.1609/AAAI.V36I11.21633},
  url       = {https://mlanthology.org/aaai/2022/lee2022aaai-tracer/}
}