167 citations · 774 across the 23 of their papers we have counts for
5 papers · 1 filter
A Simple Non-i.i.d. Sampling Approach for Efficient Training and Better Generalization
Bowen Cheng, Yunchao Wei, Jiahui Yu +5
While training on samples drawn from independent and identical distribution has been a de facto paradigm for optimizing image classification networks, humans learn new concepts in…
Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection
Bowen Cheng, Yunchao Wei, Rogerio Feris +4
In this paper, we analyze failure cases of state-of-the-art detectors and observe that most hard false positives result from classification instead of localization and they have a…
Revisit Multinomial Logistic Regression in Deep Learning: Data Dependent Model Initialization for Image Recognition
Bowen Cheng, Rong Xiao, Yandong Guo +3
We study in this paper how to initialize the parameters of multinomial logistic regression (a fully connected layer followed with softmax and cross entropy loss), which is widely u…
TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection
Yunchao Wei, Zhiqiang Shen, Bowen Cheng +4
This work provides a simple approach to discover tight object bounding boxes with only image-level supervision, called Tight box mining with Surrounding Segmentation Context (TS2C)…
Revisiting RCNN: On Awakening the Classification Power of Faster RCNN
Bowen Cheng, Yunchao Wei, Honghui Shi +3
Recent region-based object detectors are usually built with separate classification and localization branches on top of shared feature extraction networks. In this paper, we analyz…