• Publications
  • Influence
FCOS: Fully Convolutional One-Stage Object Detection
TLDR
We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Expand
  • 429
  • 115
  • PDF
Detecting Text in Natural Image with Connectionist Text Proposal Network
TLDR
We propose a novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image. Expand
  • 451
  • 74
  • PDF
An End-to-End TextSpotter with Explicit Alignment and Attention
TLDR
We propose a novel text-alignment layer that allows it to precisely compute convolutional features of a text instance in arbitrary orientation, which is the key to boost the performance; (2) a character attention mechanism is introduced by using character spatial information as explicit supervision, leading to large improvements in recognition; (3) two technologies, together with a new RNN branch for word recognition, are integrated seamlessly into a single model. Expand
  • 94
  • 16
  • PDF
Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation
TLDR
We propose a data-dependent upsampling (DUpsampling) to replace bilinear, which takes advantages of the redundancy in label space of semantic segmentation and is able to recover the pixel-wise prediction from low-resolution outputs of CNNs. Expand
  • 62
  • 7
  • PDF
NAS-FCOS: Fast Neural Architecture Search for Object Detection
TLDR
We propose to efficiently search for the feature pyramid network (FPN) as well as the prediction head of a simple object detector, namely FCOS, using a tailored reinforcement learning paradigm. Expand
  • 31
  • 3
  • PDF
Conditional Convolutions for Instance Segmentation
TLDR
We propose a simple yet effective instance segmentation framework that can achieve improved performance in both accuracy and inference speed. Expand
  • 20
  • 2
  • PDF
Knowledge Adaptation for Efficient Semantic Segmentation
TLDR
We propose a knowledge distillation method tailored for semantic segmentation to improve the performance of the compact FCNs with large overall stride. Expand
  • 37
  • 1
  • PDF
Single Shot TextSpotter with Explicit Alignment and Attention
TLDR
We propose a novel text-alignment layer that allows it to precisely compute convolutional features of a text instance in ar- bitrary orientation, which is critical to identify challenging text instances. Expand
  • 4
  • 1