面向图像与视频的快速推理分割
Fast Reasoning Segmentation for Images and Videos
把推理分割的推理链蒸馏进 0.6B 小模型，用数字孪生表征解耦感知与推理，再以分割精度+推理质量联合奖励做强化微调，为边缘端实时开放词表分割提供可复用范式。
原文依据 the distilled 0.6B variant outperforms models with 20 times more parameters while achieving 7.79 FPS throughput
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论推理分割通过隐式文本查询实现开放集目标分割，因而可作为需在真实环境中自主运行的具身智能体的基础能力。然而，现有推理分割方法依赖参数量达数十亿的多模态大语言模型，超出通常部署具身智能系统的边缘设备的计算能力。蒸馏为压缩这些模型并保持其能力提供了一条途径。但现有蒸馏方法无法迁移推理分割所需的多步推理能力，因为它们侧重于匹配输出预测与中间特征，而非保留推理链。在数字孪生表征上进行推理这一新兴范式通过重新表述问题，为更有效的蒸馏提供了机会。为此，我们提出 FastReasonSeg，利用数字孪生表征将感知与推理解耦，从而实现更有效的蒸馏。我们的蒸馏方案首先在教师模型生成的推理链上进行监督微调，随后采用联合奖励进行强化微调，该奖励同时评估分割精度与推理质量的对齐程度。在两个视频基准（JiTBench、RVTBench）和两个图像基准（ReasonSeg、LLM-Seg40K）上的实验表明，FastReasonSeg 取得了最优的推理分割性能。此外，蒸馏得到的 0.6B 变体在超越参数量为其 20 倍的模型的同时，以仅 2.1GB 的内存占用实现 7.79 FPS 的吞吐量。这一效率使其能够部署于资源受限环境，实现实时推理分割。
英文原文摘要 1784 字符
Reasoning segmentation enables open-set object segmentation via implicit text queries, therefore serving as a foundation for embodied agents that should operate autonomously in real-world environments. However, existing methods for reasoning segmentation require multimodal large language models with billions of parameters that exceed the computational capabilities of edge devices that typically deploy the embodied AI systems. Distillation offers a pathway to compress these models while preserving their capabilities. Yet, existing distillation approaches fail to transfer the multi-step reasoning capabilities that reasoning segmentation demands, as they focus on matching output predictions and intermediate features rather than preserving reasoning chains. The emerging paradigm of reasoning over digital twin representations presents an opportunity for more effective distillation by re-framing the problem. Consequently, we propose FastReasonSeg, which employs digital twin representations that decouple perception from reasoning to enable more effective distillation. Our distillation scheme first relies on supervised fine-tuning on teacher-generated reasoning chains. Then it is followed by reinforcement fine-tuning with joint rewards evaluating both segmentation accuracy and reasoning quality alignment. Experiments on two video (JiTBench, RVTBench) and two image benchmarks (ReasonSeg, LLM-Seg40K) demonstrate that our FastReasonSeg achieves state-of-the-art reasoning segmentation performance. Moreover, the distilled 0.6B variant outperforms models with 20 times more parameters while achieving 7.79 FPS throughput with only 2.1GB memory consumption. This efficiency enables deployment in resource-constrained environments to enable real-time reasoning segmentation.