Timezone: »
Vanilla models for object detection and instance segmentation suffer from the heavy bias toward detecting frequent objects in the long-tailed setting. Existing methods address this issue mostly during training, e.g., by re-sampling or re-weighting. In this paper, we investigate a largely overlooked approach --- post-processing calibration of confidence scores. We propose NorCal, Normalized Calibration for long-tailed object detection and instance segmentation, a simple and straightforward recipe that reweighs the predicted scores of each class by its training sample size. We show that separately handling the background class and normalizing the scores over classes for each proposal are keys to achieving superior performance. On the LVIS dataset, NorCal can effectively improve nearly all the baseline models not only on rare classes but also on common and frequent classes. Finally, we conduct extensive analysis and ablation studies to offer insights into various modeling choices and mechanisms of our approach. Our code is publicly available at https://github.com/tydpan/NorCal.
Author Information
Tai-Yu Pan (The Ohio State University)
Cheng Zhang (The Ohio State Unversity)
Yandong Li (university of central florida)
Hexiang Hu (University of Southern California)
Dong Xuan (Ohio State University)
Soravit Changpinyo (University of Southern California (USC))
Boqing Gong (Tencent AI Lab)
Wei-Lun Chao (Ohio State University (OSU))
More from the Same Authors
-
2022 : Understanding Federated Learning through Loss Landscape Visualizations: A Pilot Study »
Ziwei Li · Hong-You Chen · Han Wei Shen · Wei-Lun Chao -
2022 Poster: Unsupervised Adaptation from Repeated Traversals for Autonomous Driving »
Yurong You · Cheng Perng Phoo · Katie Luo · Travis Zhang · Wei-Lun Chao · Bharath Hariharan · Mark Campbell · Kilian Weinberger -
2021 Poster: Robust Visual Reasoning via Language Guided Neural Module Networks »
Arjun Akula · Varun Jampani · Soravit Changpinyo · Song-Chun Zhu -
2021 Poster: Gradual Domain Adaptation without Indexed Intermediate Domains »
Hong-You Chen · Wei-Lun Chao -
2021 Poster: VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text »
Hassan Akbari · Liangzhe Yuan · Rui Qian · Wei-Hong Chuang · Shih-Fu Chang · Yin Cui · Boqing Gong -
2020 Poster: Wasserstein Distances for Stereo Disparity Estimation »
Divyansh Garg · Yan Wang · Bharath Hariharan · Mark Campbell · Kilian Weinberger · Wei-Lun Chao -
2020 Spotlight: Wasserstein Distances for Stereo Disparity Estimation »
Divyansh Garg · Yan Wang · Bharath Hariharan · Mark Campbell · Kilian Weinberger · Wei-Lun Chao -
2019 Poster: A New Defense Against Adversarial Images: Turning a Weakness into a Strength »
Shengyuan Hu · Tao Yu · Chuan Guo · Wei-Lun Chao · Kilian Weinberger -
2018 Poster: Synthesize Policies for Transfer and Adaptation across Tasks and Environments »
Hexiang Hu · Liyu Chen · Boqing Gong · Fei Sha -
2018 Spotlight: Synthesize Policies for Transfer and Adaptation across Tasks and Environments »
Hexiang Hu · Liyu Chen · Boqing Gong · Fei Sha -
2014 Poster: Diverse Sequential Subset Selection for Supervised Video Summarization »
Boqing Gong · Wei-Lun Chao · Kristen Grauman · Fei Sha -
2013 Poster: Similarity Component Analysis »
Soravit Changpinyo · Kuan Liu · Fei Sha