637 citations · 855 across the 12 of their papers we have counts for
7 papers · 1 filter
Fewer is More: Efficient Object Detection in Large Aerial Images
Xingxing Xie, Gong Cheng, Qingyang Li +3
Current mainstream object detection methods for large aerial images usually divide large images into patches and then exhaustively detect the objects of interest on all patches, no…
Progressively Dual Prior Guided Few-shot Semantic Segmentation
Qinglong Cao, Yuntian Chen, Xiwen Yao +1
Few-shot semantic segmentation task aims at performing segmentation in query images with a few annotated support samples. Currently, few-shot segmentation methods mainly focus on l…
Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation
Yuanwei Liu, Nian Liu, Xiwen Yao +1
Few-shot semantic segmentation aims to segment the target objects in query under the condition of a few annotated support images. Most previous works strive to mine more effective…
Towards Large-Scale Small Object Detection: Survey and Benchmarks
Gong Cheng, Xiang Yuan, Xiwen Yao +4
With the rise of deep convolutional neural networks, object detection has achieved prominent advances in past years. However, such prosperity could not camouflage the unsatisfactor…
Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation
Chunbo Lang, Binfei Tu, Gong Cheng +1
Few-shot segmentation, which aims to segment unseen-class objects given only a handful of densely labeled samples, has received widespread attention from the community. Existing ap…
Learning Non-target Knowledge for Few-shot Semantic Segmentation
Yuanwei Liu, Nian Liu, Qinglong Cao +3
Existing studies in few-shot semantic segmentation only focus on mining the target object information, however, often are hard to tell ambiguous regions, especially in non-target r…
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
Chunbo Lang, Gong Cheng, Binfei Tu +1
Recently few-shot segmentation (FSS) has been extensively developed. Most previous works strive to achieve generalization through the meta-learning framework derived from classific…