Localization Distillation for Object Detection

• URL: http://arxiv.org/abs/2204.05957v1
• Date: Tue, 12 Apr 2022 17:14:34 GMT
• Title: Localization Distillation for Object Detection
• Authors: Zhaohui Zheng, Rongguang Ye, Qibin Hou, Dongwei Ren, Ping Wang, Wangmeng Zuo, Ming-Ming Cheng
• Abstract summary: Previous knowledge distillation (KD) methods for object detection mostly focus on feature imitation instead of mimicking the classification logits. We present a novel localization distillation (LD) method which can efficiently transfer the localization knowledge from the teacher to the student. We show that logit mimicking can outperform feature imitation and the absence of localization distillation is a critical reason for why logit mimicking underperforms for years.
• Score: 134.12664548771534
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Previous knowledge distillation (KD) methods for object detection mostly focus on feature imitation instead of mimicking the classification logits due to its inefficiency in distilling the localization information. In this paper, we investigate whether logit mimicking always lags behind feature imitation. Towards this goal, we first present a novel localization distillation (LD) method which can efficiently transfer the localization knowledge from the teacher to the student. Second, we introduce the concept of valuable localization region that can aid to selectively distill the classification and localization knowledge for a certain region. Combining these two new components, for the first time, we show that logit mimicking can outperform feature imitation and the absence of localization distillation is a critical reason for why logit mimicking underperforms for years. The thorough studies exhibit the great potential of logit mimicking that can significantly alleviate the localization ambiguity, learn robust feature representation, and ease the training difficulty in the early stage. We also provide the theoretical connection between the proposed LD and the classification KD, that they share the equivalent optimization effect. Our distillation scheme is simple as well as effective and can be easily applied to both dense horizontal object detectors and rotated object detectors. Extensive experiments on the MS COCO, PASCAL VOC, and DOTA benchmarks demonstrate that our method can achieve considerable AP improvement without any sacrifice on the inference speed. Our source code and pretrained models are publicly available at https://github.com/HikariTJU/LD.

Related papers

• Object-centric Cross-modal Feature Distillation for Event-based Object Detection [87.50272918262361]
  RGB detectors still outperform event-based detectors due to sparsity of the event data and missing visual details. We develop a novel knowledge distillation approach to shrink the performance gap between these two modalities. We show that object-centric distillation allows to significantly improve the performance of the event-based student object detector.
  arXiv  Detail & Related papers  (2023-11-09T16:33:08Z)
• 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)
• Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection [19.07452370081663]
  We propose a novel distillation method with cross-task consistent protocols, tailored for dense object detection. For classification distillation, we formulate the classification logit maps in both teacher and student models as multiple binary-classification maps and applying a binary-classification distillation loss to each map. Our proposed method is simple but effective, and experimental results demonstrate its superiority over existing methods.
  arXiv  Detail & Related papers  (2023-08-28T03:57:37Z)
• Efficient Feature Distillation for Zero-shot Annotation Object Detection [12.116491963892821]
  We propose a new setting for detecting unseen objects called Zero-shot object Detection (ZAD) It expands the zero-shot object detection setting by allowing the novel objects to exist in the training images. It also restricts the additional information the detector uses to novel category names.
  arXiv  Detail & Related papers  (2023-03-21T19:02:36Z)
• Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization [77.19173283023012]
  Weakly-supervised temporal action localization learns to detect and classify action instances with only category labels. Most methods widely adopt the off-the-shelf Classification-Based Pre-training (CBP) to generate video features for action localization.
  arXiv  Detail & Related papers  (2022-12-19T10:02:50Z)
• Knowledge Distillation Meets Open-Set Semi-Supervised Learning [69.21139647218456]
  We propose a novel em modelname (bfem shortname) method dedicated for distilling representational knowledge semantically from a pretrained teacher to a target student. At the problem level, this establishes an interesting connection between knowledge distillation with open-set semi-supervised learning (SSL) Our shortname outperforms significantly previous state-of-the-art knowledge distillation methods on both coarse object classification and fine face recognition tasks.
  arXiv  Detail & Related papers  (2022-05-13T15:15:27Z)
• Response-based Distillation for Incremental Object Detection [2.337183337110597]
  Traditional object detection are ill-equipped for incremental learning. Fine-tuning directly on a well-trained detection model with only new data will leads to catastrophic forgetting. We propose a fully response-based incremental distillation method focusing on learning response from detection bounding boxes and classification predictions.
  arXiv  Detail & Related papers  (2021-10-26T08:07:55Z)
• Localization Distillation for Object Detection [79.78619050578997]
  We propose localization distillation (LD) for object detection. Our LD can be formulated as standard KD by adopting the general localization representation of bounding box. We suggest a teacher assistant (TA) strategy to fill the possible gap between teacher model and student model.
  arXiv  Detail & Related papers  (2021-02-24T12:26:21Z)
• 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.