1.9k citations · 6.4k across the 80 of their papers we have counts for
7 papers · 1 filter
Unsupervised Object Detection with LiDAR Clues
Hao Tian, Yuntao Chen, Jifeng Dai +2
Despite the importance of unsupervised object detection, to the best of our knowledge, there is no previous work addressing this problem. One main issue, widely known to the commun…
Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation
Hao Li, Chenxin Tao, Xizhou Zhu +3
Designing proper loss functions is essential in training deep networks. Especially in the field of semantic segmentation, various evaluation metrics have been proposed for diverse…
Deformable DETR: Deformable Transformers for End-to-End Object Detection
Xizhou Zhu, Weijie Su, Lewei Lu +3
DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance. However, it suffers from slow conv…
1st Place Solution of LVIS Challenge 2020: A Good Box is not a Guarantee of a Good Mask
Jingru Tan, Gang Zhang, Hanming Deng +4
This article introduces the solutions of the team lvisTraveler for LVIS Challenge 2020. In this work, two characteristics of LVIS dataset are mainly considered: the long-tailed dis…
Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation
Guolei Sun, Wenguan Wang, Jifeng Dai +1
This paper studies the problem of learning semantic segmentation from image-level supervision only. Current popular solutions leverage object localization maps from classifiers as…
Hierarchical Human Parsing with Typed Part-Relation Reasoning
Wenguan Wang, Hailong Zhu, Jifeng Dai +3
Human parsing is for pixel-wise human semantic understanding. As human bodies are underlying hierarchically structured, how to model human structures is the central theme in this t…
Resolution Adaptive Networks for Efficient Inference
Le Yang, Yizeng Han, Xi Chen +3
Adaptive inference is an effective mechanism to achieve a dynamic tradeoff between accuracy and computational cost in deep networks. Existing works mainly exploit architecture redu…