Dong Zhang, Hanwang Zhang, Jinhui Tang, Xiansheng Hua, Qianru Sun
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.
We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudomasks by using only image-level labels -the most crucial step in WSSS. We attribute the cause of the ambiguous boundaries of pseudo-masks to the confounding context, e.g., the correct image-level classification of "horse" and "person" may be not only due to the recognition of each instance, but also their co-occurrence context, making the model inspection (e.g., CAM) hard to distinguish between the boundaries. Inspired by this, we propose a structural causal model to analyze the causalities among images, contexts, and class labels. Based on it, we develop a new method: Context Adjustment (CONTA), to remove the confounding bias in image-level classification and thus provide better pseudo-masks as ground-truth for the subsequent segmentation model. On PASCAL VOC 2012 and MS-COCO, we show that CONTA boosts various popular WSSS methods to new state-of-the-arts.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2009.12547")
get_code_for_paper("2009.12547")
have("2009.12547")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2009.12547.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2009.12547)
Connect an agent — have() is free.