Timezone: »
We present Deep Region Competition (DRC), an algorithm designed to extract foreground objects from images in a fully unsupervised manner. Foreground extraction can be viewed as a special case of generic image segmentation that focuses on identifying and disentangling objects from the background. In this work, we rethink the foreground extraction by reconciling energy-based prior with generative image modeling in the form of Mixture of Experts (MoE), where we further introduce the learned pixel re-assignment as the essential inductive bias to capture the regularities of background regions. With this modeling, the foreground-background partition can be naturally found through Expectation-Maximization (EM). We show that the proposed method effectively exploits the interaction between the mixture components during the partitioning process, which closely connects to region competition, a seminal approach for generic image segmentation. Experiments demonstrate that DRC exhibits more competitive performances on complex real-world data and challenging multi-object scenes compared with prior methods. Moreover, we show empirically that DRC can potentially generalize to novel foreground objects even from categories unseen during training.
Author Information
Peiyu Yu (UCLA)
Sirui Xie (UCLA)
Xiaojian Ma (University of California, Los Angeles)
Yixin Zhu (University of California, Los Angeles)
Ying Nian Wu (University of California, Los Angeles)
Song-Chun Zhu (UCLA)
More from the Same Authors
-
2020 : Paper 2: Energy-Based Continuous Inverse Optimal Control »
Yifei Xu · Jianwen Xie · Chris Baker · Yibiao Zhao · Ying Nian Wu -
2021 : IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning »
Pan Lu · Liang Qiu · Jiaqi Chen · Tanglin Xia · Yizhou Zhao · Wei Zhang · Zhou Yu · Xiaodan Liang · Song-Chun Zhu -
2021 : Deep Generative model with Hierarchical Latent Factors for Timeseries Anomaly Detection »
Cristian Challu · Peihong Jiang · Ying Nian Wu · Laurent Callot -
2021 : Unsupervised Meta-Learning via Latent Space Energy-based Model of Symbol Vector Coupling »
Bo Pang · Deqian Kong · Ying Nian Wu -
2021 : Deep Generative model with Hierarchical Latent Factors for Timeseries Anomaly Detection »
Cristian Challu · Peihong Jiang · Ying Nian Wu · Laurent Callot -
2021 : Solving Math Problems by Joint Parsing and Cognitive Reasoning »
Song-Chun Zhu -
2021 Poster: On Path Integration of Grid Cells: Group Representation and Isotropic Scaling »
Ruiqi Gao · Jianwen Xie · Xue-Xin Wei · Song-Chun Zhu · Ying Nian Wu -
2021 Poster: Robust Visual Reasoning via Language Guided Neural Module Networks »
Arjun Akula · Varun Jampani · Soravit Changpinyo · Song-Chun Zhu -
2021 Poster: Iterative Teacher-Aware Learning »
Luyao Yuan · Dongruo Zhou · Junhong Shen · Jingdong Gao · Jeffrey L Chen · Quanquan Gu · Ying Nian Wu · Song-Chun Zhu -
2020 Poster: Learning Latent Space Energy-Based Prior Model »
Bo Pang · Tian Han · Erik Nijkamp · Song-Chun Zhu · Ying Nian Wu -
2019 Poster: Learning Perceptual Inference by Contrasting »
Chi Zhang · Baoxiong Jia · Feng Gao · Yixin Zhu · HongJing Lu · Song-Chun Zhu -
2019 Spotlight: Learning Perceptual Inference by Contrasting »
Chi Zhang · Baoxiong Jia · Feng Gao · Yixin Zhu · HongJing Lu · Song-Chun Zhu -
2019 Poster: PerspectiveNet: 3D Object Detection from a Single RGB Image via Perspective Points »
Siyuan Huang · Yixin Chen · Tao Yuan · Siyuan Qi · Yixin Zhu · Song-Chun Zhu -
2019 Poster: Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Model »
Erik Nijkamp · Mitch Hill · Song-Chun Zhu · Ying Nian Wu -
2018 Poster: Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation »
Siyuan Huang · Siyuan Qi · Yinxue Xiao · Yixin Zhu · Ying Nian Wu · Song-Chun Zhu