General Instance Distillation for Object Detection
- URL: http://arxiv.org/abs/2103.02340v1
- Date: Wed, 3 Mar 2021 11:41:26 GMT
- Title: General Instance Distillation for Object Detection
- Authors: Xing Dai, Zeren Jiang, Zhao Wu, Yiping Bao, Zhicheng Wang, Si Liu,
Erjin Zhou
- Abstract summary: RetinaNet with ResNet-50 achieves 39.1% in mAP with GID on dataset, which surpasses the baseline 36.2% by 2.9%, and even better than the ResNet-101 based teacher model with 38.1% AP.
- Score: 12.720908566642812
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In recent years, knowledge distillation has been proved to be an effective
solution for model compression. This approach can make lightweight student
models acquire the knowledge extracted from cumbersome teacher models. However,
previous distillation methods of detection have weak generalization for
different detection frameworks and rely heavily on ground truth (GT), ignoring
the valuable relation information between instances. Thus, we propose a novel
distillation method for detection tasks based on discriminative instances
without considering the positive or negative distinguished by GT, which is
called general instance distillation (GID). Our approach contains a general
instance selection module (GISM) to make full use of feature-based,
relation-based and response-based knowledge for distillation. Extensive results
demonstrate that the student model achieves significant AP improvement and even
outperforms the teacher in various detection frameworks. Specifically,
RetinaNet with ResNet-50 achieves 39.1% in mAP with GID on COCO dataset, which
surpasses the baseline 36.2% by 2.9%, and even better than the ResNet-101 based
teacher model with 38.1% AP.
Related papers
- Learning Lightweight Object Detectors via Multi-Teacher Progressive
Distillation [56.053397775016755]
We propose a sequential approach to knowledge distillation that progressively transfers the knowledge of a set of teacher detectors to a given lightweight student.
To the best of our knowledge, we are the first to successfully distill knowledge from Transformer-based teacher detectors to convolution-based students.
arXiv Detail & Related papers (2023-08-17T17:17:08Z) - Class-aware Information for Logit-based Knowledge Distillation [16.634819319915923]
We propose a Class-aware Logit Knowledge Distillation (CLKD) method, that extents the logit distillation in both instance-level and class-level.
CLKD enables the student model mimic higher semantic information from the teacher model, hence improving the distillation performance.
arXiv Detail & Related papers (2022-11-27T09:27:50Z) - Prediction-Guided Distillation for Dense Object Detection [7.5320132424481505]
We show that only a very small fraction of features within a ground-truth bounding box are responsible for a teacher's high detection performance.
We propose Prediction-Guided Distillation (PGD), which focuses distillation on these key predictive regions of the teacher.
Our proposed approach outperforms current state-of-the-art KD baselines on a variety of advanced one-stage detection architectures.
arXiv Detail & Related papers (2022-03-10T16:46:05Z) - Adaptive Instance Distillation for Object Detection in Autonomous
Driving [3.236217153362305]
We propose Adaptive Instance Distillation (AID) to selectively impart teacher's knowledge to the student to improve the performance of knowledge distillation.
Our AID is also shown to be useful for self-distillation to improve the teacher model's performance.
arXiv Detail & Related papers (2022-01-26T18:06:33Z) - Instance-Conditional Knowledge Distillation for Object Detection [59.56780046291835]
We propose an instance-conditional distillation framework to find desired knowledge.
We use observed instances as condition information and formulate the retrieval process as an instance-conditional decoding process.
arXiv Detail & Related papers (2021-10-25T08:23:29Z) - LGD: Label-guided Self-distillation for Object Detection [59.9972914042281]
We propose the first self-distillation framework for general object detection, termed LGD (Label-Guided self-Distillation)
Our framework involves sparse label-appearance encoding, inter-object relation adaptation and intra-object knowledge mapping to obtain the instructive knowledge.
Compared with a classical teacher-based method FGFI, LGD not only performs better without requiring pretrained teacher but also with 51% lower training cost beyond inherent student learning.
arXiv Detail & Related papers (2021-09-23T16:55:01Z) - G-DetKD: Towards General Distillation Framework for Object Detectors via
Contrastive and Semantic-guided Feature Imitation [49.421099172544196]
We propose a novel semantic-guided feature imitation technique, which automatically performs soft matching between feature pairs across all pyramid levels.
We also introduce contrastive distillation to effectively capture the information encoded in the relationship between different feature regions.
Our method consistently outperforms the existing detection KD techniques, and works when (1) components in the framework are used separately and in conjunction.
arXiv Detail & Related papers (2021-08-17T07:44:27Z) - Distilling Object Detectors via Decoupled Features [69.62967325617632]
We present a novel distillation algorithm via decoupled features (DeFeat) for learning a better student detector.
Experiments on various detectors with different backbones show that the proposed DeFeat is able to surpass the state-of-the-art distillation methods for object detection.
arXiv Detail & Related papers (2021-03-26T13:58:49Z) - 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.