%0 Generic %1 mayer2018towards %A Mayer, Christoph %A Timofte, Radu %A Paul, Grégory %D 2018 %K segmentation weakly %T Towards Closing the Gap in Weakly Supervised Semantic Segmentation with DCNNs: Combining Local and Global Models %U http://arxiv.org/abs/1808.01625 %X Generating training sets for deep convolutional neural networks is a bottleneck for modern real-world applications. This is a demanding tasks for applications where annotating training data is costly, such as in semantic segmentation. In the literature, there is still a gap between the performance achieved by a network trained on full and on weak annotations. In this paper, we establish a strategy to measure this gap and to identify the ingredients necessary to close it. On scribbles, we establish state-of-the-art results comparable to the latest published ones (Tang et al., 2018, arXiv:1804.01346): we obtain a gap in mIoU of 2.4% without CRF (2.8% in Tang et al., 2018, arXiv:1804.01346), and 2.9% with CRF post-processing (2.3% in Tang et al., 2018, arXiv:1804.01346). However, we use completely different ideas: combining local and global annotator models and regularising their prediction to train DeepLabV2. Finally, closing the gap was reported only recently for bounding boxes in Khoreva et al. (arXiv:1603.07485v2), by requiring 10x more training images. By simulating varying amounts of pixel-level annotations respecting scribble human annotations statistics, we show that our training strategy reacts to small increases in the amount of annotations and requires only 2-5x more annotated pixels, closing the gap with only 3.1% of all pixels annotated. This work contributes new ideas towards closing the gap in real-world applications.

@misc{mayer2018towards, abstract = {Generating training sets for deep convolutional neural networks is a bottleneck for modern real-world applications. This is a demanding tasks for applications where annotating training data is costly, such as in semantic segmentation. In the literature, there is still a gap between the performance achieved by a network trained on full and on weak annotations. In this paper, we establish a strategy to measure this gap and to identify the ingredients necessary to close it. On scribbles, we establish state-of-the-art results comparable to the latest published ones (Tang et al., 2018, arXiv:1804.01346): we obtain a gap in mIoU of 2.4% without CRF (2.8% in Tang et al., 2018, arXiv:1804.01346), and 2.9% with CRF post-processing (2.3% in Tang et al., 2018, arXiv:1804.01346). However, we use completely different ideas: combining local and global annotator models and regularising their prediction to train DeepLabV2. Finally, closing the gap was reported only recently for bounding boxes in Khoreva et al. (arXiv:1603.07485v2), by requiring 10x more training images. By simulating varying amounts of pixel-level annotations respecting scribble human annotations statistics, we show that our training strategy reacts to small increases in the amount of annotations and requires only 2-5x more annotated pixels, closing the gap with only 3.1% of all pixels annotated. This work contributes new ideas towards closing the gap in real-world applications.}, added-at = {2018-09-13T21:00:19.000+0200}, author = {Mayer, Christoph and Timofte, Radu and Paul, Grégory}, biburl = {https://www.bibsonomy.org/bibtex/2a6be6af49a5e25f54f1bdc2bc91470f9/huntstart}, description = {[1808.01625] Towards Closing the Gap in Weakly Supervised Semantic Segmentation with DCNNs: Combining Local and Global Models}, interhash = {916f57eb1050d899dc7c3c8c13d279fc}, intrahash = {a6be6af49a5e25f54f1bdc2bc91470f9}, keywords = {segmentation weakly}, note = {cite arxiv:1808.01625}, timestamp = {2018-09-13T21:00:19.000+0200}, title = {Towards Closing the Gap in Weakly Supervised Semantic Segmentation with DCNNs: Combining Local and Global Models}, url = {http://arxiv.org/abs/1808.01625}, year = 2018 }