• Publications
  • Influence
R-FCN: Object Detection via Region-based Fully Convolutional Networks
We present region-based, fully convolutional networks for accurate and efficient object detection. In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costlyExpand
  • 2,553
  • 461
  • PDF
Deformable Convolutional Networks
Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in their building modules. In this work, we introduce two newExpand
  • 1,171
  • 206
  • PDF
Instance-Aware Semantic Segmentation via Multi-task Network Cascades
  • Jifeng Dai, Kaiming He, Jian Sun
  • Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 14 December 2015
Semantic segmentation research has recently witnessed rapid progress, but many leading methods are unable to identify object instances. In this paper, we present Multitask Network Cascades forExpand
  • 731
  • 76
  • PDF
Fully Convolutional Instance-Aware Semantic Segmentation
We present the first fully convolutional end-to-end solution for instance-aware semantic segmentation task. It inherits all the merits of FCNs for semantic segmentation [29] and instance maskExpand
  • 454
  • 59
  • PDF
Flow-Guided Feature Aggregation for Video Object Detection
Extending state-of-the-art object detectors from image to video is challenging. The accuracy of detection suffers from degenerated object appearances in videos, e.g., motion blur, video defocus, rareExpand
  • 205
  • 48
  • PDF
Deep Feature Flow for Video Recognition
Deep convolutional neutral networks have achieved great success on image recognition tasks. Yet, it is non-trivial to transfer the state-of-the-art image recognition networks to videos as per-frameExpand
  • 191
  • 46
  • PDF
ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
Large-scale data is of crucial importance for learning semantic segmentation models, but annotating per-pixel masks is a tedious and inefficient procedure. We note that for the topic of interactiveExpand
  • 324
  • 40
  • PDF
BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
  • Jifeng Dai, Kaiming He, Jian Sun
  • Computer Science
  • IEEE International Conference on Computer Vision…
  • 5 March 2015
Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks. Such pixel-accurate supervision demands expensiveExpand
  • 507
  • 38
  • PDF
Relation Networks for Object Detection
Although it is well believed for years that modeling relations between objects would help object recognition, there has not been evidence that the idea is working in the deep learning era. AllExpand
  • 333
  • 38
  • PDF
Deformable ConvNets V2: More Deformable, Better Results
The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects. Through an examination of its adaptive behavior, we observe thatExpand
  • 217
  • 24
  • PDF