OD-DETR: Online Distillation for Stabilizing Training of Detection Transformer

• URL: http://arxiv.org/abs/2406.05791v1
• Date: Sun, 9 Jun 2024 14:07:35 GMT
• Title: OD-DETR: Online Distillation for Stabilizing Training of Detection Transformer
• Authors: Shengjian Wu, Li Sun, Qingli Li,
• Abstract summary: This paper aims to stabilize DETR training through the online distillation. It utilizes a teacher model, accumulated by Exponential Moving Average (EMA) Experiments show that the proposed OD-DETR successfully stabilizes the training, and significantly increases the performance without bringing in more parameters.
• Score: 14.714768026997534
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: DEtection TRansformer (DETR) becomes a dominant paradigm, mainly due to its common architecture with high accuracy and no post-processing. However, DETR suffers from unstable training dynamics. It consumes more data and epochs to converge compared with CNN-based detectors. This paper aims to stabilize DETR training through the online distillation. It utilizes a teacher model, accumulated by Exponential Moving Average (EMA), and distills its knowledge into the online model in following three aspects. First, the matching relation between object queries and ground truth (GT) boxes in the teacher is employed to guide the student, so queries within the student are not only assigned labels based on their own predictions, but also refer to the matching results from the teacher. Second, the teacher's initial query is given to the online student, and its prediction is directly constrained by the corresponding output from the teacher. Finally, the object queries from teacher's different decoding stages are used to build the auxiliary groups to accelerate the convergence. For each GT, two queries with the least matching costs are selected into this extra group, and they predict the GT box and participate the optimization. Extensive experiments show that the proposed OD-DETR successfully stabilizes the training, and significantly increases the performance without bringing in more parameters.

Related papers

• Progressive distillation induces an implicit curriculum [44.528775476168654]
  A better teacher does not always yield a better student, to which a common mitigation is to use additional supervision from several teachers. One empirically validated variant of this principle is progressive distillation, where the student learns from successive intermediate checkpoints of the teacher. Using sparse parity as a sandbox, we identify an implicit curriculum as one mechanism through which progressive distillation accelerates the student's learning.
  arXiv  Detail & Related papers  (2024-10-07T19:49:24Z)
• Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models [62.5501109475725]
  Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. This paper introduces Online Knowledge Distillation (OKD), where the teacher network integrates small online modules to concurrently train with the student model. OKD achieves or exceeds the performance of leading methods in various model architectures and sizes, reducing training time by up to fourfold.
  arXiv  Detail & Related papers  (2024-09-19T07:05:26Z)
• Periodically Exchange Teacher-Student for Source-Free Object Detection [7.222926042027062]
  Source-free object detection (SFOD) aims to adapt the source detector to unlabeled target domain data in the absence of source domain data. Most SFOD methods follow the same self-training paradigm using mean-teacher (MT) framework where the student model is guided by only one single teacher model. We propose the Periodically Exchange Teacher-Student (PETS) method, a simple yet novel approach that introduces a multiple-teacher framework consisting of a static teacher, a dynamic teacher, and a student model.
  arXiv  Detail & Related papers  (2023-11-23T11:30:54Z)
• Improving Knowledge Distillation via Regularizing Feature Norm and Direction [16.98806338782858]
  Knowledge distillation (KD) exploits a large well-trained model (i.e., teacher) to train a small student model on the same dataset for the same task. Treating teacher features as knowledge, prevailing methods of knowledge distillation train student by aligning its features with the teacher's, e.g., by minimizing the KL-divergence between their logits or L2 distance between their intermediate features. While it is natural to believe that better alignment of student features to the teacher better distills teacher knowledge, simply forcing this alignment does not directly contribute to the student's performance, e.g.
  arXiv  Detail & Related papers  (2023-05-26T15:05:19Z)
• EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval [83.79667141681418]
  Large neural models (such as Transformers) achieve state-of-the-art performance for information retrieval (IR) We propose a novel distillation approach that leverages the relative geometry among queries and documents learned by the large teacher model. We show that our approach successfully distills from both dual-encoder (DE) and cross-encoder (CE) teacher models to 1/10th size asymmetric students that can retain 95-97% of the teacher performance.
  arXiv  Detail & Related papers  (2023-01-27T22:04:37Z)
• Distantly-Supervised Named Entity Recognition with Adaptive Teacher Learning and Fine-grained Student Ensemble [56.705249154629264]
  Self-training teacher-student frameworks are proposed to improve the robustness of NER models. In this paper, we propose an adaptive teacher learning comprised of two teacher-student networks. Fine-grained student ensemble updates each fragment of the teacher model with a temporal moving average of the corresponding fragment of the student, which enhances consistent predictions on each model fragment against noise.
  arXiv  Detail & Related papers  (2022-12-13T12:14:09Z)
• Directed Acyclic Graph Factorization Machines for CTR Prediction via Knowledge Distillation [65.62538699160085]
  We propose a Directed Acyclic Graph Factorization Machine (KD-DAGFM) to learn the high-order feature interactions from existing complex interaction models for CTR prediction via Knowledge Distillation. KD-DAGFM achieves the best performance with less than 21.5% FLOPs of the state-of-the-art method on both online and offline experiments.
  arXiv  Detail & Related papers  (2022-11-21T03:09:42Z)
• 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)
• Parameter-Efficient and Student-Friendly Knowledge Distillation [83.56365548607863]
  We present a parameter-efficient and student-friendly knowledge distillation method, namely PESF-KD, to achieve efficient and sufficient knowledge transfer. Experiments on a variety of benchmarks show that PESF-KD can significantly reduce the training cost while obtaining competitive results compared to advanced online distillation methods.
  arXiv  Detail & Related papers  (2022-05-28T16:11:49Z)
• Graph Consistency based Mean-Teaching for Unsupervised Domain Adaptive Person Re-Identification [54.58165777717885]
  This paper proposes a Graph Consistency based Mean-Teaching (GCMT) method with constructing the Graph Consistency Constraint (GCC) between teacher and student networks. Experiments on three datasets, i.e., Market-1501, DukeMTMCreID, and MSMT17, show that proposed GCMT outperforms state-of-the-art methods by clear margin.
  arXiv  Detail & Related papers  (2021-05-11T04:09:49Z)

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.