| 1. |
- Gustafsson, Fredrik K., et al.
(författare)
-
Accurate 3D Object Detection using Energy-Based Models
- 2021
-
Ingår i: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recogition Workshops (CVPRW 2021). - : Institute of Electrical and Electronics Engineers (IEEE). - 9781665448994 ; , s. 2849-2858
-
Konferensbidrag (refereegranskat)abstract
- Accurate 3D object detection (3DOD) is crucial for safe navigation of complex environments by autonomous robots. Regressing accurate 3D bounding boxes in cluttered environments based on sparse LiDAR data is however a highly challenging problem. We address this task by exploring recent advances in conditional energy-based models (EBMs) for probabilistic regression. While methods employing EBMs for regression have demonstrated impressive performance on 2D object detection in images, these techniques are not directly applicable to 3D bounding boxes. In this work, we therefore design a differentiable pooling operator for 3D bounding boxes, serving as the core module of our EBM network. We further integrate this general approach into the state-of-the-art 3D object detector SA-SSD. On the KITTI dataset, our proposed approach consistently outperforms the SA-SSD baseline across all 3DOD metrics, demonstrating the potential of EBM-based regression for highly accurate 3DOD. Code is available at https://github.com/fregu856/ebms_3dod.
|
|
| 2. |
- Jain, Shipra, et al.
(författare)
-
Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU
- 2021
-
Ingår i: Proceedings of the IEEE International Conference on Computer Vision. - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 7406-7416
-
Konferensbidrag (refereegranskat)abstract
- The state-of-the-art object detection and image classification methods can perform impressively on more than 9k classes. In contrast, the number of classes in semantic segmentation datasets is relatively limited. This is not surprising when the restrictions caused by the lack of labeled data and high computation demand for segmentation are considered. In this paper, we propose a novel training methodology to train and scale the existing semantic segmentation models for a large number of semantic classes without increasing the memory overhead. In our embedding-based scalable segmentation approach, we reduce the space complexity of the segmentation model's output from O
|
|
| 3. |
- Johnander, Joakim, 1993-, et al.
(författare)
-
Video Instance Segmentation with Recurrent Graph Neural Networks
- 2021
-
Ingår i: Pattern Recognition. - Cham : Springer. - 9783030926588 - 9783030926595 ; , s. 206-221
-
Konferensbidrag (refereegranskat)abstract
- Video instance segmentation is one of the core problems in computer vision. Formulating a purely learning-based method, which models the generic track management required to solve the video instance segmentation task, is a highly challenging problem. In this work, we propose a novel learning framework where the entire video instance segmentation problem is modeled jointly. To this end, we design a graph neural network that in each frame jointly processes all detections and a memory of previously seen tracks. Past information is considered and processed via a recurrent connection. We demonstrate the effectiveness of the proposed approach in comprehensive experiments. Our approach, operating at over 25 FPS, outperforms previous video real-time methods. We further conduct detailed ablative experiments that validate the different aspects of our approach.
|
|
| 4. |
- Kristan, Matej, et al.
(författare)
-
The Ninth Visual Object Tracking VOT2021 Challenge Results
- 2021
-
Ingår i: 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021). - : IEEE COMPUTER SOC. - 9781665401913 ; , s. 2711-2738
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative. Results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in recent years. The VOT2021 challenge was composed of four sub-challenges focusing on different tracking domains: (i) VOT-ST2021 challenge focused on short-term tracking in RGB, (ii) VOT-RT2021 challenge focused on "real-time" short-term tracking in RGB, (iii) VOT-LT2021 focused on long-term tracking, namely coping with target disappearance and reappearance and (iv) VOT-RGBD2021 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2021 dataset was refreshed, while VOT-RGBD2021 introduces a training dataset and sequestered dataset for winner identification. The source code for most of the trackers, the datasets, the evaluation kit and the results along with the source code for most trackers are publicly available at the challenge website(1).
|
|
