Home

Awesome

TRACER: Extreme Attention Guided Salient Object Tracing Network

This paper was accepted at AAAI 2022 SA poster session. [pdf]

PWC
PWC
PWC
PWC
PWC

alt text

Updates

[09/06/2022] Demo has been released on Open In Colab Try it now!

[06/17/2022] Now, fast inference mode offers a salient object result with the mask.
We have improved a result quality of salient object as follows.
You can get the more clear salient object by tuning the threshold. img We will release initializing TRACER with a version of pre-trained TE-x.

[04/20/2022] We update a pipeline for custom dataset inference w/o measuring.

<pre><code> TRACER ├── data │ ├── custom_dataset │ │ ├── sample_image1.png │ │ ├── sample_image2.png . . . # For testing TRACER with pre-trained model (e.g.) python main.py inference --dataset custom_dataset/ --arch 7 --img_size 640 --save_map True </code></pre>

Datasets

All datasets are available in public.

Data structure

<pre><code> TRACER ├── data │ ├── DUTS │ │ ├── Train │ │ │ ├── images │ │ │ ├── masks │ │ │ ├── edges │ │ ├── Test │ │ │ ├── images │ │ │ ├── masks │ ├── DUT-O │ │ ├── Test │ │ │ ├── images │ │ │ ├── masks │ ├── HKU-IS │ │ ├── Test │ │ │ ├── images │ │ │ ├── masks . . . </code></pre>

Requirements

Run

<pre><code> # For training TRACER-TE0 (e.g.) python main.py train --arch 0 --img_size 320 # For testing TRACER with pre-trained model (e.g.) python main.py test --exp_num 0 --arch 0 --img_size 320 </code></pre>

Configurations

--arch: EfficientNet backbone scale: TE0 to TE7.
--frequency_radius: High-pass filter radius in the MEAM.
--gamma: channel confidence ratio \gamma in the UAM.
--denoise: Denoising ratio d in the OAM.
--RFB_aggregated_channel: # of channels in receptive field blocks.
--multi_gpu: Multi-GPU learning options.
--img_size: Input image resolution.
--save_map: Options saving predicted mask.

<table> <thead> <tr> <th>Model</th> <th>Img size</th> </tr> </thead> <tbody> <tr> <td>TRACER-Efficient-0 ~ 1</td> <td>320</td> </tr> <tr> <td>TRACER-Efficient-2</td> <td>352</td> </tr> <tr> <td>TRACER-Efficient-3</td> <td>384</td> </tr> <tr> <td>TRACER-Efficient-4</td> <td>448</td> </tr> <tr> <td>TRACER-Efficient-5</td> <td>512</td> </tr> <tr> <td>TRACER-Efficient-6</td> <td>576</td> </tr> <tr> <td>TRACER-Efficient-7</td> <td>640</td> </tr> </tbody> </table>

Citation

<pre><code> @article{lee2021tracer, title={TRACER: Extreme Attention Guided Salient Object Tracing Network}, author={Lee, Min Seok and Shin, WooSeok and Han, Sung Won}, journal={arXiv preprint arXiv:2112.07380}, year={2021} } </code></pre>