Oriented Semi-DETR 解决旋转框半监督检测的参数歧义问题
Oriented Semi-DETR for Semi-Supervised Aerial Object Detection
做遥感或旋转框检测的可以看看这篇:三个模块都不加参数、不加前向计算,纯改损失和匹配逻辑,就在 DOTA-v2.0 全部标注比例上超过监督基线,严格 IoU 下提升最明显。
arXiv 论文提出 Oriented Semi-DETR,针对半监督 DETR 中旋转框的参数歧义给出解决方案。核心问题在于 (c_x,c_y,w,h,θ) 与 (c_x,c_y,h,w,θ+π/2) 表示同一个旋转矩形,参数到矩形是二对一的映射,导致空间上重合的两个框在训练用的度量上相距甚远。
论文提出三个无参数、无需额外前向传播的模块:Swap-aligned Target Selection 让回归朝向更接近学生预测的编码;Swap-invariant Reliability Cost 在匹配代价内部对两种编码取最小值,使 GMM 过滤器只依据几何判断;Swap-aware Pseudo-label Denoising 提前启动去噪、线性增加损失权重,并按教师分数和编码差加权每个 query。
在 DOTA-v2.0 的所有标注比例下,Oriented Semi-DETR 均超过基于 DETR 的监督与半监督基线,在严格 IoU 阈值下增益最大。此前正确定位的学生框会被回归损失惩罚,并因匹配代价偏高而被 GMM 过滤器丢弃,该方法直接修复了这条训练链路。
Oriented Semi-DETR for Semi-Supervised Aerial Object Detection
Semi-supervised object detection has recently been extended to DETR, where oriented boxes introduce an ambiguity that does not arise for axis-aligned boxes: the map from parameters to rectangles is two-to-one, since $(c_x,c_y,w,h,θ)$ and $(c_x,c_y,h,w,θ+π/2)$ denote the same rotated rectangle. Losses and matching costs are computed from the parameters, so two boxes that coincide in space can be far apart in the metric that drives training. A correctly localized student box is then penalized by the regression loss, and the inflated matching cost leads the Gaussian mixture model (GMM) filter to discard it. We propose Oriented Semi-DETR, which removes this ambiguity wherever a pseudo box enters training. Swap-aligned Target Selection regresses towards the encoding closer to the student prediction. A Swap-invariant Reliability Cost minimizes over the two encodings inside the matching cost, so the filter decides on geometry alone. Swap-aware Pseudo-label Denoising starts denoising earlier, ramps its loss weight linearly, and weights each query by the teacher score and encoding margin. All three are parameter-free and require no additional forward pass. Across all label ratios of DOTA-v2.0, Oriented Semi-DETR outperforms DETR-based supervised and semi-supervised baselines, with the largest gains at the strict IoU threshold.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include DETR, semi-supervised learning, object detection, remote sensing.
Source attribution: curated from arXiv cs.AI (@Yuqiu Li, Jian Xue, Fan Li, Ke Lu).