Teach-DETR: Better Training DETR with Teachers

• URL: http://arxiv.org/abs/2211.11953v2
• Date: Wed, 23 Nov 2022 13:17:53 GMT
• Title: Teach-DETR: Better Training DETR with Teachers
• Authors: Linjiang Huang, Kaixin Lu, Guanglu Song, Liang Wang, Si Liu, Yu Liu, Hongsheng Li
• Abstract summary: Teach-DETR is a training scheme to learn better DETR-based detectors from versatile teacher detectors. We improve the state-of-the-art detector DINO with Swin-Large backbone, 4 scales of feature maps and 36-epoch training schedule.
• Score: 43.37671158294093
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we present a novel training scheme, namely Teach-DETR, to learn better DETR-based detectors from versatile teacher detectors. We show that the predicted boxes from teacher detectors are effective medium to transfer knowledge of teacher detectors, which could be either RCNN-based or DETR-based detectors, to train a more accurate and robust DETR model. This new training scheme can easily incorporate the predicted boxes from multiple teacher detectors, each of which provides parallel supervisions to the student DETR. Our strategy introduces no additional parameters and adds negligible computational cost to the original detector during training. During inference, Teach-DETR brings zero additional overhead and maintains the merit of requiring no non-maximum suppression. Extensive experiments show that our method leads to consistent improvement for various DETR-based detectors. Specifically, we improve the state-of-the-art detector DINO with Swin-Large backbone, 4 scales of feature maps and 36-epoch training schedule, from 57.8% to 58.9% in terms of mean average precision on MSCOCO 2017 validation set. Code will be available at https://github.com/LeonHLJ/Teach-DETR.

Related papers

• Rank-DETR for High Quality Object Detection [52.82810762221516]
  A highly performant object detector requires accurate ranking for the bounding box predictions. In this work, we introduce a simple and highly performant DETR-based object detector by proposing a series of rank-oriented designs.
  arXiv  Detail & Related papers  (2023-10-13T04:48:32Z)
• DEYOv3: DETR with YOLO for Real-time Object Detection [0.0]
  We propose a new training method called step-by-step training. In the first stage, the one-to-many pre-trained YOLO detector is used to initialize the end-to-end detector. In the second stage, the backbone and encoder are consistent with the DETR-like model, but only the detector needs to be trained from scratch.
  arXiv  Detail & Related papers  (2023-09-21T07:49:07Z)
• DETRs with Collaborative Hybrid Assignments Training [11.563949886871713]
  We present a novel collaborative hybrid assignments training scheme, namely $mathcalC$o-DETR. This training scheme can easily enhance the encoder's learning ability in end-to-end detectors. We conduct extensive experiments to evaluate the effectiveness of the proposed approach on DETR variants.
  arXiv  Detail & Related papers  (2022-11-22T16:19:52Z)
• D$^3$ETR: Decoder Distillation for Detection Transformer [20.493873634246512]
  We focus on the transformer decoder of DETR-based detectors and explore KD methods for them. The outputs of the transformer decoder lie in random order, which gives no direct correspondence between the predictions of the teacher and the student. We build textbfDecoder textbfDistillation for textbfDEtection textbfTRansformer (D$3$ETR) which distills knowledge in decoder predictions and attention maps from the teachers to students.
  arXiv  Detail & Related papers  (2022-11-17T18:47:24Z)
• Recurrent Glimpse-based Decoder for Detection with Transformer [85.64521612986456]
  We introduce a novel REcurrent Glimpse-based decOder (REGO) in this paper. In particular, the REGO employs a multi-stage recurrent processing structure to help the attention of DETR gradually focus on foreground objects. REGO consistently boosts the performance of different DETR detectors by up to 7% relative gain at the same setting of 50 training epochs.
  arXiv  Detail & Related papers  (2021-12-09T00:29:19Z)
• Meta-Teacher For Face Anti-Spoofing [46.604960860807154]
  Face anti-spoofing (FAS) secures face recognition from presentation attacks (PAs) We propose a novel Meta-Teacher FAS (MT-FAS) method to train a meta-teacher for supervising PA detectors more effectively.
  arXiv  Detail & Related papers  (2021-11-12T10:09:50Z)
• Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera [83.31666463259849]
  We propose a method to automatically generate training labels (called pseudo-labels) for 2D LiDAR-based person detectors. We show that self-supervised detectors, trained or fine-tuned with pseudo-labels, outperform detectors trained using manual annotations. Our method is an effective way to improve person detectors during deployment without any additional labeling effort.
  arXiv  Detail & Related papers  (2020-12-16T12:10:04Z)
• Distilling Object Detectors with Task Adaptive Regularization [97.52935611385179]
  Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a larger teacher model, is one of the promising solutions for model miniaturization.
  arXiv  Detail & Related papers  (2020-06-23T15:58:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.