Hi there.
\nI was doing research on weakly-supervised instance segmentation and found this interesting paper. Hopefully, it inspires you as much as it did me!
\n--> Pytorch Implementation By Author on Github
\n\n\nWeakly supervised semantic instance segmentation with only image-level supervision, instead of relying on expensive pixel-wise masks or bounding box annotations, is an important problem to alleviate the data-hungry nature of deep learning. In this paper, we tackle this challenging problem by aggregating the image-level information of all training images into a large knowledge graph and exploiting semantic relationships from this graph. Specifically, our effort starts with some generic segment-based object proposals (SOP) without category priors. We propose a multiple instance learning (MIL) framework, which can be trained in an end-to-end manner using training images with image-level labels. For each proposal, this MIL framework can simultaneously compute probability distributions and category-aware semantic features, with which we can formulate a large undirected graph. The category of background is also included in this graph to remove the massive noisy object proposals. An optimal multi-way cut of this graph can thus assign a reliable category label to each proposal. The denoised SOP with assigned category labels can be viewed as pseudo instance segmentation of training images, which are used to train fully supervised models. The proposed approach achieves state-of-the-art performance for both weakly supervised instance segmentation and semantic segmentation.
\n
Hi there.
\nI was doing research on weakly-supervised instance segmentation and found this interesting paper. Hopefully, it inspires you as much as it did me!
\n--> Pytorch Implementation By Author on Github
\n\n\nWeakly supervised semantic instance segmentation with only image-level supervision, instead of relying on expensive pixel-wise masks or bounding box annotations, is an important problem to alleviate the data-hungry nature of deep learning. In this paper, we tackle this challenging problem by aggregating the image-level information of all training images into a large knowledge graph and exploiting semantic relationships from this graph. Specifically, our effort starts with some generic segment-based object proposals (SOP) without category priors. We propose a multiple instance learning (MIL) framework, which can be trained in an end-to-end manner using training images with image-level labels. For each proposal, this MIL framework can simultaneously compute probability distributions and category-aware semantic features, with which we can formulate a large undirected graph. The category of background is also included in this graph to remove the massive noisy object proposals. An optimal multi-way cut of this graph can thus assign a reliable category label to each proposal. The denoised SOP with assigned category labels can be viewed as pseudo instance segmentation of training images, which are used to train fully supervised models. The proposed approach achieves state-of-the-art performance for both weakly supervised instance segmentation and semantic segmentation.
\n
Another interesting/relevant paper: Coarse-to-fine Semantic Segmentation from Image-level Labels
", "rawMarkdown": "Another interesting/relevant paper: [Coarse-to-fine Semantic Segmentation from Image-level Labels](https://arxiv.org/abs/1812.10885)", "votes": 1 } ], "comments": [ { "id": 1211878, "author_name": "Ayush Thakur", "author_url": "", "post_date": "2021-02-20T16:19:37.453000", "content": "Another interesting/relevant paper: Coarse-to-fine Semantic Segmentation from Image-level Labels
", "votes": 1, "replies": [] } ], "raw_markdown_by_id": { "1193446": "Hi there.\n\nI was doing research on weakly-supervised instance segmentation and found this interesting paper. Hopefully, it inspires you as much as it did me!\n\n---\n\n