Self-Erasing Network for Integral Object Attention

Abstract

Recently, adversarial erasing for weakly-supervised object attention has been deeply studied due to its capability in localizing integral object regions. However, such a strategy raises one key problem that attention regions will gradually expand to non-object regions as training iterations continue, which significantly decreases the quality of the produced attention maps. To tackle such an issue as well as promote the quality of object attention, we introduce a simple yet effective Self-Erasing Network (SeeNet) to prohibit attentions from spreading to unexpected background regions. In particular, SeeNet leverages two self-erasing strategies to encourage networks to use reliable object and background cues for learning to attention. In this way, integral object regions can be effectively highlighted without including much more background regions. To test the quality of the generated attention maps, we employ the mined object regions as heuristic cues for learning semantic segmentation models. Experiments on Pascal VOC well demonstrate the superiority of our SeeNet over other state-of-the-art methods.

arXiv commentAccepted by NIPS2018

References in corpus (8)

• Deeply supervised salient object detection with short connections
• Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
• Tell Me Where to Look: Guided Attention Inference Network
• Adversarial Complementary Learning for Weakly Supervised Object Localization
• Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
• Two-Phase Learning for Weakly Supervised Object Localization
• Exploiting saliency for object segmentation from image level labels
• WebSeg: Learning Semantic Segmentation from Web Searches

Cited by in corpus (2)

• Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing
• Beyond Attributes: Adversarial Erasing Embedding Network for Zero-shot Learning