让分割模型在无提示时也能自动推理，性能更优。
IP-SAM: Rethinking Prompt-Conditioned Segmentation for Prompt-Absent Deployment
- 用图像自动生成提示，替代人工输入
- 在4个隐蔽物体检测数据集上达顶尖性能
- 适合医疗等无需人工提示的场景
提示条件化的基础分割模型已成为主流，通过显式空间提示（如点、框、掩码）引导掩码解码。然而，许多实际部署需要完全自动分割，导致结构不匹配：解码器期望提示，但推理时无法提供。现有方法通常修改中间特征，绕过原生提示接口，削弱了提示引导解码能力。我们提出IP-SAM，从提示空间角度重新思考适配：自提示生成器（SPG）将图像上下文提炼为互补的内在提示，作为粗粒度区域锚点；这些线索经SAM2的冻结提示编码器投影，恢复提示引导解码，无需外部干预。为抑制背景引发的误检，提示空间门控（PSG）利用内在背景提示作为非对称抑制约束，解码前生效。在无外部提示的确定性协议下，IP-SAM在四个隐蔽物体检测基准上达到当前最优，仅需21.26M可训练参数。该策略还泛化至医学息肉分割任务。
原文摘要 · Abstract (English)
Prompt-conditioned foundation segmenters have emerged as a dominant paradigm for image segmentation, where explicit spatial prompts(e.g., points, boxes, masks) guide mask decoding. However, many real-world deployments require fully automatic segmentation, creating a structural mismatch: the decoder expects prompts that are unavailable at inference. Existing adaptations typically modify intermediate features, inadvertently bypassing the model's native prompt interface and weakening prompt-conditioned decoding. We propose IP-SAM, which revisits adaptation from a prompt-space perspective through prompt-space conditioning. Specifically, a Self-Prompt Generator (SPG) distills image context into complementary intrinsic prompts that serve as coarse regional anchors. These cues are projected through SAM2's frozen prompt encoder, restoring prompt-guided decoding without external intervention. To suppress background-induced false positives, Prompt-Space Gating (PSG) leverages the intrinsic background prompt as an asymmetric suppressive constraint prior to decoding. Under a deterministic no-external-prompt protocol, IP-SAM achieves state-of-the-art performance across four camouflaged object detection benchmarks with only 21.26M trainable parameters. Furthermore, the proposed conditioning strategy generalizes beyond COD to medical polyp segmentation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。