arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.07069cs.CVcs.LG
收藏

F-CAM:通过引导参数升级的全分辨率类激活图

F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling

École de technologie supérieure(高等技术学院);Ericsson(爱立信);McGill University(麦吉尔大学)

Soufiane Belharbi, Aydin Sarraf, Marco Pedersoli, Ismail Ben Ayed, Luke McCaffrey, Eric Granger

摘要:

类激活映射(CAM)方法最近得到了很多关注弱监督对象定位(WSOL)任务。它们允许CNN可视化和解释,而无需在完全注释的图像数据集上进行训练。CAM方法通常集成在现成的CNN骨干中,例如ResNet 50。由于卷积和池化操作,这些主干产生低分辨率CAM,其缩小因子高达32,导致定位不准确。恢复全尺寸CAM需要插值,但它不考虑对象的统计特性,如颜色和纹理,导致激活边界不一致,定位不准确。作为一种替代方案,我们引入了一种通用的方法参数升级的CAM,可以构建准确的全分辨率CAM(F-CAM)。特别是,我们提出了一种可训练的解码架构,可以连接到任何CNN分类器以产生高度准确的CAM定位。给定原始低分辨率CAM,前景和背景像素被随机采样以微调解码器。额外的先验信息,如图像统计和大小约束,也被认为是扩大和细化对象的边界。在CUB-200-2011和OpenImages数据集上的三个CNN主干和六个WSOL基线上进行的广泛实验表明,我们的F-CAM方法在CAM定位精度方面有显着提高。F-CAM的性能与最先进的WSOL方法相比具有竞争力,但它在推理过程中需要更少的计算。

英文摘要:

Class Activation Mapping (CAM) methods have recently gained much attention for weakly-supervised object localization (WSOL) tasks. They allow for CNN visualization and interpretation without training on fully annotated image datasets. CAM methods are typically integrated within off-the-shelf CNN backbones, such as ResNet50. Due to convolution and pooling operations, these backbones yield low resolution CAMs with a down-scaling factor of up to 32, contributing to inaccurate localizations. Interpolation is required to restore full size CAMs, yet it does not consider the statistical properties of objects, such as color and texture, leading to activations with inconsistent boundaries, and inaccurate localizations. As an alternative, we introduce a generic method for parametric upscaling of CAMs that allows constructing accurate full resolution CAMs (F-CAMs). In particular, we propose a trainable decoding architecture that can be connected to any CNN classifier to produce highly accurate CAM localizations. Given an original low resolution CAM, foreground and background pixels are randomly sampled to fine-tune the decoder. Additional priors such as image statistics and size constraints are also considered to expand and refine object boundaries. Extensive experiments, over three CNN backbones and six WSOL baselines on the CUB-200-2011 and OpenImages datasets, indicate that our F-CAM method yields a significant improvement in CAM localization accuracy. F-CAM performance is competitive with state-of-art WSOL methods, yet it requires fewer computations during inference.

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。

↑