YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection

• URL: http://arxiv.org/abs/2512.23273v2
• Date: Tue, 30 Dec 2025 12:52:51 GMT
• Title: YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection
• Authors: Xu Lin, Jinlong Peng, Zhenye Gan, Jiawen Zhu, Jun Liu,
• Abstract summary: YOLO-Master is a novel YOLO-like framework that introduces instance-conditional adaptive computation for Real-Time Object Detection.<n>Our model achieves 42.4% AP with 1.62ms latency, outperforming YOLOv13-N by +0.8% mAP and 17.8% faster inference.
• Score: 26.013463778761317
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing Real-Time Object Detection (RTOD) methods commonly adopt YOLO-like architectures for their favorable trade-off between accuracy and speed. However, these models rely on static dense computation that applies uniform processing to all inputs, misallocating representational capacity and computational resources such as over-allocating on trivial scenes while under-serving complex ones. This mismatch results in both computational redundancy and suboptimal detection performance. To overcome this limitation, we propose YOLO-Master, a novel YOLO-like framework that introduces instance-conditional adaptive computation for RTOD. This is achieved through a Efficient Sparse Mixture-of-Experts (ES-MoE) block that dynamically allocates computational resources to each input according to its scene complexity. At its core, a lightweight dynamic routing network guides expert specialization during training through a diversity enhancing objective, encouraging complementary expertise among experts. Additionally, the routing network adaptively learns to activate only the most relevant experts, thereby improving detection performance while minimizing computational overhead during inference. Comprehensive experiments on five large-scale benchmarks demonstrate the superiority of YOLO-Master. On MS COCO, our model achieves 42.4% AP with 1.62ms latency, outperforming YOLOv13-N by +0.8% mAP and 17.8% faster inference. Notably, the gains are most pronounced on challenging dense scenes, while the model preserves efficiency on typical inputs and maintains real-time inference speed. Code will be available.

Related papers

• MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping [52.02659589971978]
  We propose MoDES, the first training-free framework that adaptively skips experts to enable efficient and accurate MoE MLLM inference.<n>MoDES significantly enhances inference speed, improving the prefilling time by 2.16$times$ and the decoding time by 1.26$times$.
  arXiv  Detail & Related papers  (2025-11-19T18:48:27Z)
• LExI: Layer-Adaptive Active Experts for Efficient MoE Model Inference [2.8653469160349077]
  We introduce LExI, a data-free optimization technique that determines the optimal number of active experts per layer in a pretrained MoE model.<n>Experiments on state-of-the-art language and vision MoE benchmarks demonstrate that LExI significantly outperforms traditional MoE pruning approaches in terms of inference efficiency.
  arXiv  Detail & Related papers  (2025-09-02T19:01:46Z)
• DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction [15.261077484922616]
  Mixture of Experts (MoE) has become a mainstream architecture for building Large Language Models (LLMs)<n>We identify dual sparsity at the tensor and neuron levels in pre-trained MoE modules as a key factor for both accuracy and efficiency.<n>We propose DualSparse-MoE, an inference system that integrates dynamic tensor-level dropping with static neuron-level reconstruction.
  arXiv  Detail & Related papers  (2025-08-25T18:08:32Z)
• Multi-Agent Reinforcement Learning for Sample-Efficient Deep Neural Network Mapping [54.65536245955678]
  We present a decentralized multi-agent reinforcement learning (MARL) framework designed to overcome the challenge of sample inefficiency.<n>We introduce an agent clustering algorithm that assigns similar mapping parameters to the same agents based on correlation analysis.<n> Experimental results show our MARL approach improves sample efficiency by 30-300x over standard single-agent RL.
  arXiv  Detail & Related papers  (2025-07-22T05:51:07Z)
• YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception [58.06752127687312]
  We propose YOLOv13, an accurate and lightweight object detector.<n>We propose a Hypergraph-based Adaptive Correlation Enhancement (HyperACE) mechanism.<n>We also propose a Full-Pipeline Aggregation-and-Distribution (FullPAD) paradigm.
  arXiv  Detail & Related papers  (2025-06-21T15:15:03Z)
• Dynamic Action Interpolation: A Universal Approach for Accelerating Reinforcement Learning with Expert Guidance [0.0]
  Reinforcement learning (RL) suffers from severe sample inefficiency, especially during early training.<n>We propose Dynamic Action Interpolation (DAI), a universal yet straightforward framework that interpolates expert and RL actions.<n>Our theoretical analysis shows that DAI reshapes state visitation distributions to accelerate value function learning.
  arXiv  Detail & Related papers  (2025-04-26T02:12:02Z)
• Underlying Semantic Diffusion for Effective and Efficient In-Context Learning [113.4003355229632]
  Underlying Semantic Diffusion (US-Diffusion) is an enhanced diffusion model that boosts underlying semantics learning, computational efficiency, and in-context learning capabilities.<n>We present a Feedback-Aided Learning (FAL) framework, which leverages feedback signals to guide the model in capturing semantic details.<n>We also propose a plug-and-play Efficient Sampling Strategy (ESS) for dense sampling at time steps with high-noise levels.
  arXiv  Detail & Related papers  (2025-03-06T03:06:22Z)
• YOLOv5, YOLOv8 and YOLOv10: The Go-To Detectors for Real-time Vision [0.6662800021628277]
  This paper focuses on the evolution of the YOLO (You Only Look Once) object detection algorithm, focusing on YOLOv5, YOLOv8, and YOLOv10. We analyze the architectural advancements, performance improvements, and suitability for edge deployment across these versions.
  arXiv  Detail & Related papers  (2024-07-03T10:40:20Z)
• YOLOv10: Real-Time End-to-End Object Detection [68.28699631793967]
  YOLOs have emerged as the predominant paradigm in the field of real-time object detection. The reliance on the non-maximum suppression (NMS) for post-processing hampers the end-to-end deployment of YOLOs. We introduce the holistic efficiency-accuracy driven model design strategy for YOLOs.
  arXiv  Detail & Related papers  (2024-05-23T11:44:29Z)
• Efficient Few-Shot Object Detection via Knowledge Inheritance [62.36414544915032]
  Few-shot object detection (FSOD) aims at learning a generic detector that can adapt to unseen tasks with scarce training samples. We present an efficient pretrain-transfer framework (PTF) baseline with no computational increment. We also propose an adaptive length re-scaling (ALR) strategy to alleviate the vector length inconsistency between the predicted novel weights and the pretrained base weights.
  arXiv  Detail & Related papers  (2022-03-23T06:24:31Z)

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.