MambaNUT: Nighttime UAV Tracking via Mamba and Adaptive Curriculum Learning
- URL: http://arxiv.org/abs/2412.00626v1
- Date: Sun, 01 Dec 2024 00:51:23 GMT
- Title: MambaNUT: Nighttime UAV Tracking via Mamba and Adaptive Curriculum Learning
- Authors: You Wu, Xiangyang Yang, Xucheng Wang, Hengzhou Ye, Dan Zeng, Shuiwang Li,
- Abstract summary: We propose a pure Mamba-based tracking framework that employs a state space model with linear complexity as its backbone.
We introduce an adaptive curriculum learning (ACL) approach that dynamically adjusts sampling strategies and loss weights.
Exhaustive experiments on multiple nighttime UAV tracking benchmarks demonstrate that the proposed MambaNUT achieves state-of-the-art performance.
- Score: 5.9089796108568855
- License:
- Abstract: Harnessing low-light enhancement and domain adaptation, nighttime UAV tracking has made substantial strides. However, over-reliance on image enhancement, scarcity of high-quality nighttime data, and neglecting the relationship between daytime and nighttime trackers, which hinders the development of an end-to-end trainable framework. Moreover, current CNN-based trackers have limited receptive fields, leading to suboptimal performance, while ViT-based trackers demand heavy computational resources due to their reliance on the self-attention mechanism. In this paper, we propose a novel pure Mamba-based tracking framework (\textbf{MambaNUT}) that employs a state space model with linear complexity as its backbone, incorporating a single-stream architecture that integrates feature learning and template-search coupling within Vision Mamba. We introduce an adaptive curriculum learning (ACL) approach that dynamically adjusts sampling strategies and loss weights, thereby improving the model's ability of generalization. Our ACL is composed of two levels of curriculum schedulers: (1) sampling scheduler that transforms the data distribution from imbalanced to balanced, as well as from easier (daytime) to harder (nighttime) samples; (2) loss scheduler that dynamically assigns weights based on data frequency and the IOU. Exhaustive experiments on multiple nighttime UAV tracking benchmarks demonstrate that the proposed MambaNUT achieves state-of-the-art performance while requiring lower computational costs. The code will be available.
Related papers
- A Mamba Foundation Model for Time Series Forecasting [13.593170999506889]
We introduce TSMamba, a linear-complexity foundation model for time series forecasting built on the Mamba architecture.
The model captures temporal dependencies through both forward and backward Mamba encoders, achieving high prediction accuracy.
It also achieves competitive or superior full-shot performance compared to task-specific prediction models.
arXiv Detail & Related papers (2024-11-05T09:34:05Z) - MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Tracking [51.28485682954006]
We propose a pure Mamba-based framework (MambaVT) to fully exploit intrinsic-temporal contextual modeling for robust visible-thermal tracking.
Specifically, we devise the long-range cross-frame integration component to globally adapt to target appearance variations.
Experiments show the significant potential of vision Mamba for RGB-T tracking, with MambaVT achieving state-of-the-art performance on four mainstream benchmarks.
arXiv Detail & Related papers (2024-08-15T02:29:00Z) - Exploring Dynamic Transformer for Efficient Object Tracking [58.120191254379854]
We propose DyTrack, a dynamic transformer framework for efficient tracking.
DyTrack automatically learns to configure proper reasoning routes for various inputs, gaining better utilization of the available computational budget.
Experiments on multiple benchmarks demonstrate that DyTrack achieves promising speed-precision trade-offs with only a single model.
arXiv Detail & Related papers (2024-03-26T12:31:58Z) - ACTrack: Adding Spatio-Temporal Condition for Visual Object Tracking [0.5371337604556311]
Efficiently modeling-temporal relations of objects is a key challenge in visual object tracking (VOT)
Existing methods track by appearance-based similarity or long-term relation modeling, resulting in rich temporal contexts between consecutive frames being easily overlooked.
In this paper we present ACTrack, a new framework with additive pre-temporal tracking framework with large memory conditions. It preserves the quality and capabilities of the pre-trained backbone by freezing its parameters, and makes a trainable lightweight additive net to model temporal relations in tracking.
We design an additive siamese convolutional network to ensure the integrity of spatial features and temporal sequence
arXiv Detail & Related papers (2024-02-27T07:34:08Z) - T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learning [22.002220932086693]
We propose an effective pre-training strategy, namely Temporal Masked Auto-Encoders (T-MAE)
T-MAE takes as input temporally adjacent frames and learns temporal dependency.
Our T-MAE pre-training strategy alleviates its demand for annotated data.
arXiv Detail & Related papers (2023-12-15T21:30:49Z) - Efficient Adaptive Human-Object Interaction Detection with
Concept-guided Memory [64.11870454160614]
We propose an efficient Adaptive HOI Detector with Concept-guided Memory (ADA-CM)
ADA-CM has two operating modes. The first mode makes it tunable without learning new parameters in a training-free paradigm.
Our proposed method achieves competitive results with state-of-the-art on the HICO-DET and V-COCO datasets with much less training time.
arXiv Detail & Related papers (2023-09-07T13:10:06Z) - FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via
Dynamic Device Placement [19.639936387834677]
Mixture-of-Experts (MoEs) are becoming more popular and have demonstrated impressive pretraining scalability in various downstream tasks.
MoEs are becoming a new data analytics paradigm in the data life cycle and suffering from unique challenges at scales, complexities, and granularities never before possible.
In this paper, we propose a novel DNN training framework, FlexMoE, which systematically and transparently address the inefficiency caused by dynamic dataflow.
arXiv Detail & Related papers (2023-04-08T07:34:26Z) - Towards Sequence-Level Training for Visual Tracking [60.95799261482857]
This work introduces a sequence-level training strategy for visual tracking based on reinforcement learning.
Four representative tracking models, SiamRPN++, SiamAttn, TransT, and TrDiMP, consistently improve by incorporating the proposed methods in training.
arXiv Detail & Related papers (2022-08-11T13:15:36Z) - Large Scale Time-Series Representation Learning via Simultaneous Low and
High Frequency Feature Bootstrapping [7.0064929761691745]
We propose a non-contrastive self-supervised learning approach efficiently captures low and high-frequency time-varying features.
Our method takes raw time series data as input and creates two different augmented views for two branches of the model.
To demonstrate the robustness of our model we performed extensive experiments and ablation studies on five real-world time-series datasets.
arXiv Detail & Related papers (2022-04-24T14:39:47Z) - Cascaded Regression Tracking: Towards Online Hard Distractor
Discrimination [202.2562153608092]
We propose a cascaded regression tracker with two sequential stages.
In the first stage, we filter out abundant easily-identified negative candidates.
In the second stage, a discrete sampling based ridge regression is designed to double-check the remaining ambiguous hard samples.
arXiv Detail & Related papers (2020-06-18T07:48:01Z) - Convolutional Tensor-Train LSTM for Spatio-temporal Learning [116.24172387469994]
We propose a higher-order LSTM model that can efficiently learn long-term correlations in the video sequence.
This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time.
Our results achieve state-of-the-art performance-art in a wide range of applications and datasets.
arXiv Detail & Related papers (2020-02-21T05:00:01Z)
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.