SRF-GAN
None
view repo
Recent convolutional object detectors exploit multi-scale feature representations added with top-down pathway in order to detect objects at different scales and learn stronger semantic feature responses. In general, during the top-down feature propagation, the coarser feature maps are upsampled to be combined with the features forwarded from bottom-up pathway, and the combined stronger semantic features are inputs of detector's headers. However, simple interpolation methods (e.g. nearest neighbor and bilinear) are still used for increasing feature resolutions although they cause noisy and blurred features. In this paper, we propose a novel generator for super-resolving features of the convolutional object detectors. To achieve this, we first design super-resolved feature GAN (SRF-GAN) consisting of a detection-based generator and a feature patch discriminator. In addition, we present SRF-GAN losses for generating the high quality of super-resolved features and improving detection accuracy together. Our SRF generator can substitute for the traditional interpolation methods, and easily fine-tuned combined with other conventional detectors. To prove this, we have implemented our SRF-GAN by using the several recent one-stage and two-stage detectors, and improved detection accuracy over those detectors. Code is available at https://github.com/SHLee-cv/SRF-GAN.
READ FULL TEXT
Recently, a lot of single stage detectors using multi-scale features hav...
read it
Although Faster R-CNN and its variants have shown promising performance ...
read it
Single shot detectors that are potentially faster and simpler than two-s...
read it
This report to our stage 1 submission to the NeurIPS 2019 disentanglemen...
read it
One-stage object detectors such as SSD or YOLO already have shown promis...
read it
Traditional neural objection detection methods use multi-scale features ...
read it
Finding semantic correspondences is a challenging problem. With the
brea...
read it
None
Comments
There are no comments yet.