Mutual-Learning Knowledge Distillation for Nighttime UAV Tracking

• URL: http://arxiv.org/abs/2312.07884v2
• Date: Fri, 22 Dec 2023 01:33:20 GMT
• Title: Mutual-Learning Knowledge Distillation for Nighttime UAV Tracking
• Authors: Yufeng Liu
• Abstract summary: Nighttime unmanned aerial vehicle (UAV) tracking has been facilitated with indispensable plug-and-play low-light enhancers. This work proposes a novel mutual-learning knowledge distillation framework for nighttime UAV tracking, i.e., MLKD.
• Score: 10.170363860678663
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Nighttime unmanned aerial vehicle (UAV) tracking has been facilitated with indispensable plug-and-play low-light enhancers. However, the introduction of low-light enhancers increases the extra computational burden for the UAV, significantly hindering the development of real-time UAV applications. Meanwhile, these state-of-the-art (SOTA) enhancers lack tight coupling with the advanced daytime UAV tracking approach. To solve the above issues, this work proposes a novel mutual-learning knowledge distillation framework for nighttime UAV tracking, i.e., MLKD. This framework is constructed to learn a compact and fast nighttime tracker via knowledge transferring from the teacher and knowledge sharing among various students. Specifically, an advanced teacher based on a SOTA enhancer and a superior tracking backbone is adopted for guiding the student based only on the tight coupling-aware tracking backbone to directly extract nighttime object features. To address the biased learning of a single student, diverse lightweight students with different distillation methods are constructed to focus on various aspects of the teacher's knowledge. Moreover, an innovative mutual-learning room is designed to elect the superior student candidate to assist the remaining students frame-by-frame in the training phase. Furthermore, the final best student, i.e., MLKD-Track, is selected through the testing dataset. Extensive experiments demonstrate the effectiveness and superiority of MLKD and MLKD-Track. The practicality of the MLKD-Track is verified in real-world tests with different challenging situations. The code is available at https://github.com/lyfeng001/MLKD.

Related papers

• Learning Adaptive and View-Invariant Vision Transformer with Multi-Teacher Knowledge Distillation for Real-Time UAV Tracking [15.597151507814429]
  We introduce AVTrack, an adaptive framework designed to selectively activate transformer blocks for real-time UAV tracking. To tackle the challenges posed by extreme changes in viewing angles, we propose view-invariant representations through mutual information (MI) Building on it, we propose an improved tracker, dubbed AVTrack-MD, which introduces a novel MI-based multi-teacher knowledge distillation (MD) framework.
  arXiv  Detail & Related papers  (2024-12-28T03:57:44Z)
• KBAlign: Efficient Self Adaptation on Specific Knowledge Bases [73.34893326181046]
  Large language models (LLMs) usually rely on retrieval-augmented generation to exploit knowledge materials in an instant manner. We propose KBAlign, an approach designed for efficient adaptation to downstream tasks involving knowledge bases. Our method utilizes iterative training with self-annotated data such as Q&A pairs and revision suggestions, enabling the model to grasp the knowledge content efficiently.
  arXiv  Detail & Related papers  (2024-11-22T08:21:03Z)
• SOAR: Self-supervision Optimized UAV Action Recognition with Efficient Object-Aware Pretraining [65.9024395309316]
  We introduce a novel Self-supervised pretraining algorithm for aerial footage captured by Unmanned Aerial Vehicles (UAVs) We incorporate human object knowledge throughout the pretraining process to enhance UAV video pretraining efficiency and downstream action recognition performance.
  arXiv  Detail & Related papers  (2024-09-26T21:15:22Z)
• FACT: Feature Adaptive Continual-learning Tracker for Multiple Object Tracking [22.53374351982883]
  We propose a new MOT framework called the Feature Adaptive Continual-learning Tracker (FACT) FACT enables real-time tracking and feature learning for targets by utilizing all past tracking information. We demonstrate that the framework can be integrated with various state-of-the-art feature-based trackers.
  arXiv  Detail & Related papers  (2024-09-12T10:14:48Z)
• Towards Discriminative Representations with Contrastive Instances for Real-Time UAV Tracking [5.557099240958562]
  Discriminative correlation filters (DCF)-based trackers can yield high efficiency on a single CPU but with inferior precision. Lightweight Deep learning (DL)-based trackers can achieve a good balance between efficiency and precision but performance gains are limited by the compression rate. This paper aims to enhance the discriminative power of feature representations from a new feature-learning perspective.
  arXiv  Detail & Related papers  (2023-08-22T13:58:45Z)
• Continuity-Aware Latent Interframe Information Mining for Reliable UAV Tracking [5.9397055042513465]
  Unmanned aerial vehicle (UAV) tracking is crucial for autonomous navigation and has broad applications in robotic automation fields. This work proposes a novel framework with continuity-aware latent interframe information mining for reliable UAV tracking, i.e., ClimRT.
  arXiv  Detail & Related papers  (2023-03-08T11:42:57Z)
• Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation [172.15808300686584]
  We describe an approach that learns the two tasks simultaneously and exploits their intrinsic correlations to boost the training of each. Our approach improves the performance of various follower models and produces accurate navigation instructions.
  arXiv  Detail & Related papers  (2022-03-30T18:15:26Z)
• Self-Promoted Supervision for Few-Shot Transformer [178.52948452353834]
  Self-promoted sUpervisioN (SUN) is a few-shot learning framework for vision transformers (ViTs) SUN pretrains the ViT on the few-shot learning dataset and then uses it to generate individual location-specific supervision for guiding each patch token. Experiments show that SUN using ViTs significantly surpasses other few-shot learning frameworks with ViTs and is the first one that achieves higher performance than those CNN state-of-the-arts.
  arXiv  Detail & Related papers  (2022-03-14T12:53:27Z)
• 3D UAV Trajectory and Data Collection Optimisation via Deep Reinforcement Learning [75.78929539923749]
  Unmanned aerial vehicles (UAVs) are now beginning to be deployed for enhancing the network performance and coverage in wireless communication. It is challenging to obtain an optimal resource allocation scheme for the UAV-assisted Internet of Things (IoT) In this paper, we design a new UAV-assisted IoT systems relying on the shortest flight path of the UAVs while maximising the amount of data collected from IoT devices.
  arXiv  Detail & Related papers  (2021-06-06T14:08:41Z)
• Privileged Knowledge Distillation for Online Action Detection [114.5213840651675]
  Online Action Detection (OAD) in videos is proposed as a per-frame labeling task to address the real-time prediction tasks. This paper presents a novel learning-with-privileged based framework for online action detection where the future frames only observable at the training stages are considered as a form of privileged information.
  arXiv  Detail & Related papers  (2020-11-18T08:52:15Z)
• Tracking-by-Trackers with a Distilled and Reinforced Model [24.210580784051277]
  A compact student model is trained via the marriage of knowledge distillation and reinforcement learning. The proposed algorithms compete with real-time state-of-the-art trackers.
  arXiv  Detail & Related papers  (2020-07-08T13:24:04Z)

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.