FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction
This provides a versatile backbone for computer vision tasks like classification, detection, and segmentation, addressing a divergence in network design principles.
The authors tackled the problem of designing a unified backbone for image, region, and pixel-level prediction by creating FishNet, which preserves and refines information across all resolutions and improves gradient propagation, achieving higher accuracy than DenseNet and ResNet on ImageNet-1k with fewer parameters and contributing to a winning entry in the COCO Detection 2018 challenge.
The basic principles in designing convolutional neural network (CNN) structures for predicting objects on different levels, e.g., image-level, region-level, and pixel-level are diverging. Generally, network structures designed specifically for image classification are directly used as default backbone structure for other tasks including detection and segmentation, but there is seldom backbone structure designed under the consideration of unifying the advantages of networks designed for pixel-level or region-level predicting tasks, which may require very deep features with high resolution. Towards this goal, we design a fish-like network, called FishNet. In FishNet, the information of all resolutions is preserved and refined for the final task. Besides, we observe that existing works still cannot \emph{directly} propagate the gradient information from deep layers to shallow layers. Our design can better handle this problem. Extensive experiments have been conducted to demonstrate the remarkable performance of the FishNet. In particular, on ImageNet-1k, the accuracy of FishNet is able to surpass the performance of DenseNet and ResNet with fewer parameters. FishNet was applied as one of the modules in the winning entry of the COCO Detection 2018 challenge. The code is available at https://github.com/kevin-ssy/FishNet.