activity
20192021
most citedC-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection

30 citations · 79 across the 6 of their papers we have counts for

collaborators

9 papers

cs.CV20218 cited

Multiple instance active learning for object detection

Tianning Yuan, Fang Wan, Mengying Fu +4

Despite the substantial progress of active learning for image recognition, there still lacks an instance-level active learning method specified for object detection. In this paper,…

cs.CV2021

TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization

Wei Gao, Fang Wan, Xingjia Pan +5

Weakly supervised object localization (WSOL) is a challenging problem when given image category labels but requires to learn object localization models. Optimizing a convolutional…

cs.CV20202 cited

Domain Contrast for Domain Adaptive Object Detection

Feng Liu, Xiaoxong Zhang, Fang Wan +2

We present Domain Contrast (DC), a simple yet effective approach inspired by contrastive learning for training domain adaptive detectors. DC is deduced from the error bound minimiz…

cs.CV2020

Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning

Zhekun Luo, Devin Guillory, Baifeng Shi +4

Weakly-supervised action localization requires training a model to localize the action segments in the video given only video level action label. It can be solved under the Multipl…

cs.CV2019

FreeAnchor: Learning to Match Anchors for Visual Object Detection

Xiaosong Zhang, Fang Wan, Chang Liu +2

Modern CNN-based object detectors assign anchors for ground-truth objects under the restriction of object-anchor Intersection-over-Unit (IoU). In this study, we propose a learning-…

cs.CV201917 cited

Utilizing the Instability in Weakly Supervised Object Detection

Yan Gao, Boxiao Liu, Nan Guo +4

Weakly supervised object detection (WSOD) focuses on training object detector with only image-level annotations, and is challenging due to the gap between the supervision and the o…