AutoScaler: Scale-Attention Networks for Visual Correspondence
By Shenlong Wang, Linjie Luo, Ning Zhang, Jia Li. 2016
19 citations recorded by the source corpus.
Finding visual correspondence between local features is key to many computer vision problems. While defining features with larger contextual scales usually implies greater discriminativeness, it could also lead to less spatial accuracy of the features. We propose AutoScaler, a scale-attention network to explicitly optimize this trade-off in visual correspondence tasks. Our network consists of a weight-sharing feature network to compute multi-scale feature maps and an attention network to combine them optimally in the scale space. This allows our network to have adaptive receptive field sizes over different scales of the input. The entire network is trained end-to-end in a siamese framework for visual correspondence tasks. Our method achieves favorable results compared to state-of-the-art methods on challenging optical flow and semantic matching benchmarks, including Sintel, KITTI and CUB-2011. We also show that our method can generalize to improve hand-crafted descriptors (e.g Daisy) on general visual correspondence tasks. Finally, our attention network can generate visually interpretable scale attention maps.
Subfields: Computer Vision and Pattern Recognition, Model Architectures
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Simon Stent
- Adrià Recasens
- Wojciech Matusik
- Petr Kellnhofer
- Antonio Torralba
- Kristen Grauman
- Andrew Zisserman
- Luc Van Gool
In Model Architectures
Citations in the corpus
- Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks (2018, background): “[22], who generate the features of the input image at different scales to then select the best features and produce the final output.”