Distilling Object Detectors With Global Knowledge

• URL: http://arxiv.org/abs/2210.09022v1
• Date: Mon, 17 Oct 2022 12:44:33 GMT
• Title: Distilling Object Detectors With Global Knowledge
• Authors: Sanli Tang, Zhongyu Zhang, Zhanzhan Cheng, Jing Lu, Yunlu Xu, Yi Niu and Fan He
• Abstract summary: Existing methods regard the knowledge as the feature of each instance or their relations, which is the instance-level knowledge only from the teacher model. A more intrinsic approach is to measure the representations of instances w.r.t. a group of common basis vectors in the two feature spaces of the teacher and the student detectors. We show that our method achieves the best performance for distilling object detectors with various datasets backbones.
• Score: 30.67375886569278
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Knowledge distillation learns a lightweight student model that mimics a cumbersome teacher. Existing methods regard the knowledge as the feature of each instance or their relations, which is the instance-level knowledge only from the teacher model, i.e., the local knowledge. However, the empirical studies show that the local knowledge is much noisy in object detection tasks, especially on the blurred, occluded, or small instances. Thus, a more intrinsic approach is to measure the representations of instances w.r.t. a group of common basis vectors in the two feature spaces of the teacher and the student detectors, i.e., global knowledge. Then, the distilling algorithm can be applied as space alignment. To this end, a novel prototype generation module (PGM) is proposed to find the common basis vectors, dubbed prototypes, in the two feature spaces. Then, a robust distilling module (RDM) is applied to construct the global knowledge based on the prototypes and filtrate noisy global and local knowledge by measuring the discrepancy of the representations in two feature spaces. Experiments with Faster-RCNN and RetinaNet on PASCAL and COCO datasets show that our method achieves the best performance for distilling object detectors with various backbones, which even surpasses the performance of the teacher model. We also show that the existing methods can be easily combined with global knowledge and obtain further improvement. Code is available: https://github.com/hikvision-research/DAVAR-Lab-ML.

Related papers

• Open-World Object Detection with Instance Representation Learning [1.8749305679160366]
  We propose a method to train an object detector that can both detect novel objects and extract semantically rich features in open-world conditions. Our method learns a robust and generalizable feature space, outperforming other OWOD-based feature extraction methods.
  arXiv  Detail & Related papers  (2024-09-24T13:13:34Z)
• Enhancing Visual Continual Learning with Language-Guided Supervision [76.38481740848434]
  Continual learning aims to empower models to learn new tasks without forgetting previously acquired knowledge. We argue that the scarce semantic information conveyed by the one-hot labels hampers the effective knowledge transfer across tasks. Specifically, we use PLMs to generate semantic targets for each class, which are frozen and serve as supervision signals.
  arXiv  Detail & Related papers  (2024-03-24T12:41:58Z)
• Efficient Object Detection in Optical Remote Sensing Imagery via Attention-based Feature Distillation [29.821082433621868]
  We propose Attention-based Feature Distillation (AFD) for object detection. We introduce a multi-instance attention mechanism that effectively distinguishes between background and foreground elements. AFD attains the performance of other state-of-the-art models while being efficient.
  arXiv  Detail & Related papers  (2023-10-28T11:15:37Z)
• Bidirectional Knowledge Reconfiguration for Lightweight Point Cloud Analysis [74.00441177577295]
  Point cloud analysis faces computational system overhead, limiting its application on mobile or edge devices. This paper explores feature distillation for lightweight point cloud models. We propose bidirectional knowledge reconfiguration to distill informative contextual knowledge from the teacher to the student.
  arXiv  Detail & Related papers  (2023-10-08T11:32:50Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph Propagation [68.13453771001522]
  We propose a multimodal intensive ZSL framework that matches regions of images with corresponding semantic embeddings. We conduct extensive experiments and evaluate our model on large-scale real-world data.
  arXiv  Detail & Related papers  (2023-06-14T13:07:48Z)
• Open-World Object Detection via Discriminative Class Prototype Learning [4.055884768256164]
  Open-world object detection (OWOD) is a challenging problem that combines object detection with incremental learning and open-set learning. We propose a novel and efficient OWOD solution from a prototype perspective, which we call OCPL: Open-world object detection via discnative OCPL: Open-world object detection via discriminative OCPL: Open-world object detection via discriminative OCPL: Open-world object detection via discriminative OCPL: Open-world object detection via discriminative OCPL: Open-world object detection via discriminative OCPL: Open-world object detection via
  arXiv  Detail & Related papers  (2023-02-23T03:05:04Z)
• Open World DETR: Transformer based Open World Object Detection [60.64535309016623]
  We propose a two-stage training approach named Open World DETR for open world object detection based on Deformable DETR. We fine-tune the class-specific components of the model with a multi-view self-labeling strategy and a consistency constraint. Our proposed method outperforms other state-of-the-art open world object detection methods by a large margin.
  arXiv  Detail & Related papers  (2022-12-06T13:39:30Z)
• Contrastive Object Detection Using Knowledge Graph Embeddings [72.17159795485915]
  We compare the error statistics of the class embeddings learned from a one-hot approach with semantically structured embeddings from natural language processing or knowledge graphs. We propose a knowledge-embedded design for keypoint-based and transformer-based object detection architectures.
  arXiv  Detail & Related papers  (2021-12-21T17:10:21Z)

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.