提出双记忆过滤器，显著减少开放世界检测中误判的未知目标。
DualMem: Bypassing the Objectness Bottleneck for Calibrated Unknown-Stream Filtering in Open-World Object Detection
- 用冻结的SigLIP特征空间做非参数似然比检验，分离真实未知与背景噪声
- 在M-OWODB上将误报的未知目标降低44.9%至66.3%，平均降幅56.6%
- 可调节阈值平衡误删与漏检，适合需高精度未知样本筛选的场景
开放世界目标检测要求模型定位已知类别并识别未知对象以支持未来增量学习。我们发现强模型的未知预测流严重污染：在M-OWODB上，未来任务正例仅占未知预测的不到10%，而背景误报占比达46%-71%。这并非信息缺失，而是物体存在度头造成的瓶颈。在PROB Task 1中，解码器查询的线性探针在256维特征上实现AUROC 0.908，但最终一维物体存在度降至0.642；而冻结的SigLIP特征独立恢复了提案级可分性（AUROC=0.871）。为此，我们提出DualMem，一种校准后处理过滤器，利用小规模图像无关标注校准集，在冻结的SigLIP特征空间中进行非参数似然比检验。它使用k近邻正样本记忆保护未来任务对象，负样本记忆抑制背景类提案。决策阈值通过Neyman-Pearson校准，提供误未知抑制与新类召回之间的显式权衡。在M-OWODB Task 1的PROB、OW-DETR和HypOW上，DualMem使每图像背景型误未知提案减少44.9%-66.3%，平均降幅56.6%。在PROB Task 1上，其效果超过自然K-means原型基线一倍以上，且不影响已知类mAP，因已知检测绕过过滤器。
原文摘要 · Abstract (English)
Open-world object detection (OWOD) requires detectors to localize known classes while identifying unknown objects for future incremental learning. We find that the unknown prediction streams of strong OWOD detectors are heavily polluted: on M-OWODB, across PROB, OW-DETR, and HypOW, future-task positive unknowns make up less than 10% of unknown predictions, whereas background false positives account for 46-71%. We show that this is not a missing-information problem, but an information bottleneck at the objectness head. On PROB Task 1, a linear probe on the 256-D decoder query achieves an AUROC of 0.908 for positive-versus-negative unknown discrimination, but the final one-dimensional objectness scalar drops to 0.642. A frozen SigLIP feature, without access to the detector, independently recovers much of this proposal-level separability at the filtering stage (AUROC = 0.871). Motivated by this finding, we propose DualMem, a calibrated post-hoc filter that assumes a small image-disjoint annotated calibration split of held-out future-task objects and performs a non-parametric likelihood ratio test in frozen SigLIP feature space. DualMem uses a k-nearest-neighbor positive memory to protect future-task objects and a negative memory to suppress background-like proposals. Its decision threshold is chosen by Neyman-Pearson calibration, giving users an explicit trade-off between false-unknown suppression and novel recall. Across PROB, OW-DETR, and HypOW on M-OWODB Task 1, DualMem reduces background-type false unknown proposals per image by 44.9%-66.3%, with a mean reduction of 56.6%. On PROB Task 1, it more than doubles the reduction achieved by a natural K-means prototype baseline, while leaving known-class mAP unchanged because known detections bypass the filter.
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。