arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.12930cs.CV
收藏

基于前景与背景独立建模的动物个体识别

Animal Identification with Independent Foreground and Background Modeling

University of West Bohemia(西波希米亚大学);Inria(法国国家信息与自动化研究所);University of Montpellier(蒙彼利埃大学);CNRS(法国国家科学研究中心);Czech Technical University in Prague(捷克布拉格技术大学)

Lukas Picek, Lukas Neumann, Jiri Matas

AI总结:

提出一种独立建模前景与背景的动物视觉识别方法,利用 Segment Anything 实现自动分离,并通过 Per-Instance Temperature Scaling 结合预测,显著降低相对误差并提升背景漂移下的准确率。

摘要:

我们提出了一种在动物个体视觉识别中稳健利用背景和前景的方法。实验表明,借助 Segment Anything 等方法实现的自动分离,结合独立的前景与背景相关建模,能够改善结果。得益于新颖的 Per-Instance Temperature Scaling,两项预测以有原则的方式结合,帮助分类器处理训练中的外观歧义,并在推理阶段产生校准的输出。针对基于背景的身份预测,我们提出了新颖的空间和时间模型。在两个问题上,相对于基线的相对误差分别降低了 22.3% 和 8.8%。对于物体出现在新位置的情况(即背景漂移的示例),准确率提升了一倍。

英文摘要:

We propose a method that robustly exploits background and foreground in visual identification of individual animals. Experiments show that their automatic separation, made easy with methods like Segment Anything, together with independent foreground and background-related modeling, improves results. The two predictions are combined in a principled way, thanks to novel Per-Instance Temperature Scaling that helps the classifier to deal with appearance ambiguities in training and to produce calibrated outputs in the inference phase. For identity prediction from the background, we propose novel spatial and temporal models. On two problems, the relative error w.r.t. the baseline was reduced by 22.3% and 8.8%, respectively. For cases where objects appear in new locations, an example of background drift, accuracy doubles.

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。

↑