Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentation
Dec 6, 2022
Speakers
Jinlong Li
Speaker · 0 followers
Xiaolin Wei
Speaker · 0 followers
About
Generating precise class-aware pseudo ground-truths, a.k.a, class activation maps (CAMs), is essential for weakly-supervised semantic segmentation. The original CAM method usually produces incomplete and inaccurate localization maps. To tackle with this issue, this paper proposes an Expansion and Shrinkage scheme based on the offset learning in the deformable convolution, to sequentially improve the recall and precision of the located object in the two respective stages. In the Expansion stage, an offset learning branch in a deformable convolution layer, referred as “expansion sampler” seeks for sampling increasingly less discriminative object regions，driven by an inverse supervision signal that maximizes image-level classification loss. The located more complete object in the Expansion stage is then gradually narrowed down to the final object region during the Shrinkage stage. In the Shrinkage stage, the offset learning branch of another deformable convolution layer, referred as “shrinkage sampler”, is introduced to exclude the false positive background regions attended in the Expansion stage to improve the precision of the localization maps. We conduct various experiments on PASCAL VOC 2012 and MS COCO 2014 to well demonstrate the superiority of our method over other state-of-the-art methods for weakly-supervised semantic segmentation.Generating precise class-aware pseudo ground-truths, a.k.a, class activation maps (CAMs), is essential for weakly-supervised semantic segmentation. The original CAM method usually produces incomplete and inaccurate localization maps. To tackle with this issue, this paper proposes an Expansion and Shrinkage scheme based on the offset learning in the deformable convolution, to sequentially improve the recall and precision of the located object in the two respective stages. In the Expansion …
Organizer
NeurIPS 2022
Account · 953 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Inception Transformer
Watch later
Chenyang Si, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Spatial Pruned Sparse Convolution for Efficient 3D Object Detection
Watch later
Jianhui Liu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Mildly Conservative Q-Learning for Offline Reinforcement Learning
Watch later
Jiafei Lyu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Improving the predictions of ML-corrected climate models with novelty detection
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Transform Once: Efficient Operator Learning in Frequency Domain
Watch later
Michael Poli, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%