DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection
Nov 28, 2022
Speakers
Yujie Wang
Speaker · 0 followers
Shanshan Zhang
Speaker · 0 followers
Ding Liang
Speaker · 0 followers
About
The Mean-Teacher (MT) scheme is widely adopted in semi-supervised object detection (SSOD). In MT, sparse pseudo labels, offered by the final predictions of the teacher (e.g., after Non Maximum Suppression (NMS) post-processing), are adopted for the dense supervision for the student via hand-crafted label assignment. However, the "sparse-to-dense” paradigm complicates the pipeline of SSOD, and simultaneously neglects the powerful direct, dense teacher supervision. In this paper, we attempt to directly leverage the dense guidance of teacher to supervise student training, i.e., the "dense-to-dense” paradigm. Specifically, we propose the Inverse NMS Clustering (INC) and Rank Matching (RM) to instantiate the dense supervision, without the widely used, conventional sparse pseudo labels. INC leads the student to group candidate boxes into clusters in NMS as the teacher does, which is implemented by learning grouping information revealed in NMS procedure of the teacher. After obtaining the same grouping scheme as the teacher via INC, the student further imitates the rank distribution of the teacher over clustered candidates through Rank Matching. With the proposed INC and RM, we integrate Dense Teacher Guidance into Semi-Supervised Object Detection (termed "DTG-SSOD”), successfully abandoning sparse pseudo labels and enabling more informative learning on unlabeled data. On COCO benchmark, our DTG-SSOD achieves state-of-the-art performance under various labelling ratios. For example, under 10The Mean-Teacher (MT) scheme is widely adopted in semi-supervised object detection (SSOD). In MT, sparse pseudo labels, offered by the final predictions of the teacher (e.g., after Non Maximum Suppression (NMS) post-processing), are adopted for the dense supervision for the student via hand-crafted label assignment. However, the "sparse-to-dense” paradigm complicates the pipeline of SSOD, and simultaneously neglects the powerful direct, dense teacher supervision. In this paper, we attempt to dir…
Organizer
NeurIPS 2022
Account · 952 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
On Learning Fairness and Accuracy on Multiple Subgroups
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
ShuffleMixer: An Efficient ConvNet for Image Super-Resolution
Watch later
Long Sun, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Kernel similarity matching with Hebbian networks
Watch later
Kyle Luther, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study
Watch later
Yongtao Wu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Mirror Descent with Relative Smoothness in Measure Spaces, with application to Sinkhorn and Expectation-Maximization (EM)
Watch later
Pierre-Cyril Aubin-Frankowski, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Statelessness in Asylum Data
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%