主动空间引导：消除视觉Transformer中的注入式位置机制
Active Spatial Guidance: Eliminating Injected Positional Mechanisms in Vision Transformers
AI总结：
提出Active Spatial Guidance (Guidance)训练目标，通过辅助2D坐标回归损失消除位置注入，在ImageNet-100、ADE20K和Hypersim任务上超越强基线，表明空间归纳偏置可通过训练监督塑造。
摘要：
视觉Transformer（ViTs）通常依赖注入式位置机制来解决自注意力的置换不变性。受自然图像空间规律性的启发，我们询问空间组织是否可以从数据中诱导而非显式注入。在受控、匹配的从头训练下，我们提出主动空间引导（Guidance），一种仅训练目标，它禁用位置注入并对最后一层的补丁令牌应用辅助2D坐标回归损失。引导头仅在训练期间使用，推理时移除；部署的模型由无位置注入的ViT编码器和任务特定预测模块组成。使用DINOv3 ViT骨干网络，Guidance在ImageNet-100分类、ADE20K语义分割和Hypersim单目深度估计上持续提升性能，在相同训练协议下优于强注入基线，如学习到的绝对位置嵌入和旋转位置嵌入。在ImageNet-100上，与代表性注入位置设计的更广泛比较进一步支持Guidance的有效性。Guidance还提高了分辨率迁移下的鲁棒性，多分辨率训练进一步增强了不同输入尺寸下的准确性。总体而言，我们的结果表明，ViT中的空间归纳偏置无需架构注入，而是可以通过训练时监督来塑造。用于训练和评估的代码在此https URL公开。
英文摘要：
Vision Transformers (ViTs) commonly rely on injected positional mechanisms to address self-attention's permutation invariance. Motivated by the spatial regularities of natural images, we ask whether spatial organization can be induced from data rather than explicitly injected. Under controlled, matched from-scratch training, we propose Active Spatial Guidance (Guidance), a training-only objective that disables positional injection and applies an auxiliary 2D coordinate-regression loss to the final-layer patch tokens. The guidance head is used only during training and removed for inference; the deployed model consists of a positional-injection-free ViT encoder and the task-specific prediction module. Using DINOv3 ViT backbones, Guidance consistently improves performance on ImageNet-100 classification, ADE20K semantic segmentation, and Hypersim monocular depth estimation, outperforming strong injected baselines such as learned absolute positional embeddings and rotary positional embeddings under identical training protocols. On ImageNet-100, broader comparisons against representative injected positional designs further support Guidance's effectiveness. Guidance also improves robustness under resolution transfer, and multi-resolution training further strengthens accuracy across input sizes. Overall, our results suggest that spatial inductive bias in ViTs need not be architecturally injected, but can be shaped through training-time supervision. The code used for training and evaluation is publicly available in https://github.com/cloudlc/asg.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
