Small Objects Matters in Weakly-supervised Semantic Segmentation
Weakly-supervised semantic segmentation (WSSS) performs pixel-wise classification given only image-level labels for training. Despite the difficulty of this task, the research community has achieved promising results over the last five years. Still, current WSSS literature misses the detailed sense of how well the methods perform on different sizes of objects. Thus we propose a novel evaluation metric to provide a comprehensive assessment across different object sizes and collect a size-balanced evaluation set to complement PASCAL VOC. With these two gadgets, we reveal that the existing WSSS methods struggle in capturing small objects. Furthermore, we propose a size-balanced cross-entropy loss coupled with a proper training strategy. It generally improves existing WSSS methods as validated upon ten baselines on three different datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Semantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic SegmentationSimilar Papers 제목 키워드 기반
Pseudo-mask Matters in Weakly-supervised Semantic Segmentation
Most weakly supervised semantic segmentation (WSSS) methods follow the pipeline that generates pseudo-masks initially and trains the segmentation model with the pseudo-masks in fully supervised manner after. However, we …
SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic SegmentationMulti-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation
Object region mining is a critical step for weakly-supervised semantic segmentation. Most recent methods mine the object regions by expanding the seed regions localized by class activation maps. They generally do not con…
ObjectSegmentationSemantic SegmentationWeakly supervised Semantic Segmentation+1Weakly Supervised Segmentation of Small Buildings With Point Labels
Most supervised image segmentation methods require delicate and time-consuming pixel-level labeling of building or objects, especially for small objects. In this paper, we present a weakly supervised segmentation net…
Image SegmentationSegmentationSemantic SegmentationWeakly supervised segmentationPrecision matters: Precision-aware ensemble for weakly supervised semantic segmentation
Weakly Supervised Semantic Segmentation (WSSS) employs weak supervision, such as image-level labels, to train the segmentation model. Despite the impressive achievement in recent WSSS methods, we identify that introducin…
SegmentationSemantic SegmentationWeakly-Supervised Semantic SegmentationWeakly Supervised Image Annotation and Segmentation with Objects and Attributes
We propose to model complex visual scenes using a non-parametric Bayesian model learned from weakly labelled images abundant on media sharing sites such as Flickr. Given weak image-level annotations of objects and attrib…
AttributeObjectobject-detectionObject Detection+3