Per-Pixel Feedback for improving Semantic Segmentation
arXiv:1712.02861
Abstract
Semantic segmentation is the task of assigning a label to each pixel in the image.In recent years, deep convolutional neural networks have been driving advances in multiple tasks related to cognition. Although, DCNNs have resulted in unprecedented visual recognition performances, they offer little transparency. To understand how DCNN based models work at the task of semantic segmentation, we try to analyze the DCNN models in semantic segmentation. We try to find the importance of global image information for labeling pixels. Based on the experiments on discriminative regions, and modeling of fixations, we propose a set of new training loss functions for fine-tuning DCNN based models. The proposed training regime has shown improvement in performance of DeepLab Large FOV(VGG-16) Segmentation model for PASCAL VOC 2012 dataset. However, further test remains to conclusively evaluate the benefits due to the proposed loss functions across models, and data-sets. Submitted in part fulfillment of the requirements for the degree of Integrated Masters of Science in Applied Mathematics. Update: Further Experiment showed minimal benefits. Code Available [here](https://github.com/BardOfCodes/Seg-Unravel).
33 pages,18 figures,3 tables
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- End to End Learning for Self-Driving Cars
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- Visualizing and Understanding Convolutional Networks
- Pyramid Scene Parsing Network
- CrowdNet: A Deep Convolutional Network for Dense Crowd Counting
- On the Origin of Deep Learning
- Mixed context networks for semantic segmentation