Timezone: »
Object detection is a crucial component in autonomous navigation systems. Current object detectors are trained and tested on a fixed number of known classes. However, in real-world or open-world settings, the test set may consist of objects of unknown classes; this results in the unknown objects being falsely detected as known objects leading to the failure in decision making of autonomous navigation systems. We propose Open World Object Detection on Road Scenes (ORDER) to resolve the aforementioned problem. We introduce Feature-Mix that widens the gap between known and unknown classes in latent feature space and improves the unknown object detection in the ORDER framework. We identify the inherent problems present in autonomous datasets: i) a significant proportion of the dataset comprises small objects and ii) intra-class bounding box scale variations. We address the problem of small object detection and intra-class bounding box variations by proposing a novel focal regression loss. Further, the detection of small objects is improved by curriculum learning. We present an extensive evaluation on two road scene datasets: BDD and IDD. Our experimental evaluations on BDD and IDD shows consistent improvement over the current state-of-the-art method. We believe that this work will lay the foundation for real-world object detection for road scenes.
Author Information
Deepak Singh (International Institute of Information Technology, Hyderabad)
Shyam Nandan Rai (IIIT-Hyderabad)
Joseph K J (Indian Institute of Technology Hyderabad)
Rohit Saluja (IIIT-Hyderabad)
Vineeth N Balasubramanian (Indian Institute of Technology, Hyderabad)
Chetan Arora (Indian Institute of Technology Delhi)
Anbumani Subramanian (IIIT-Hyderabad)
C.V. Jawahar (International Institute of Information Technology, Hyderabad)
More from the Same Authors
-
2021 : Classification of histopathology images using ConvNets to detect Lupus Nephritis »
Akash Gupta · Anirudh Reddy · C.V. Jawahar · PK Vinod -
2022 : Counterfactual Generation Under Confounding »
Abbavaram Gowtham Reddy · Saloni Dash · Amit Sharma · Vineeth N Balasubramanian -
2022 Spotlight: Lightning Talks 4B-4 »
Ziyue Jiang · Zeeshan Khan · Yuxiang Yang · Chenze Shao · Yichong Leng · Zehao Yu · Wenguan Wang · Xian Liu · Zehua Chen · Yang Feng · Qianyi Wu · James Liang · C.V. Jawahar · Junjie Yang · Zhe Su · Songyou Peng · Yufei Xu · Junliang Guo · Michael Niemeyer · Hang Zhou · Zhou Zhao · Makarand Tapaswi · Dongfang Liu · Qian Yang · Torsten Sattler · Yuanqi Du · Haohe Liu · Jing Zhang · Andreas Geiger · Yi Ren · Long Lan · Jiawei Chen · Wayne Wu · Dahua Lin · Dacheng Tao · Xu Tan · Jinglin Liu · Ziwei Liu · 振辉 叶 · Danilo Mandic · Lei He · Xiangyang Li · Tao Qin · sheng zhao · Tie-Yan Liu -
2022 Spotlight: Grounded Video Situation Recognition »
Zeeshan Khan · C.V. Jawahar · Makarand Tapaswi -
2022 Poster: Grounded Video Situation Recognition »
Zeeshan Khan · C.V. Jawahar · Makarand Tapaswi -
2021 Poster: Adversarial Robustness without Adversarial Training: A Teacher-Guided Curriculum Learning Approach »
Anindya Sarkar · Anirban Sarkar · Sowrya Gali · Vineeth N Balasubramanian -
2021 Poster: Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networks »
Sandesh Kamath · Amit Deshpande · Subrahmanyam Kambhampati Venkata · Vineeth N Balasubramanian -
2020 Poster: Meta-Consolidation for Continual Learning »
Joseph K J · Vineeth N Balasubramanian -
2014 Poster: Efficient Optimization for Average Precision SVM »
Pritish Mohapatra · C.V. Jawahar · M. Pawan Kumar