Reversible Recursive Instance-level Object Segmentation
Xiaodan Liang† ⋆ Yunchao Wei† Xiaohui Shen∗ Zequn Jie† Jiashi Feng† Liang Lin⋆ Shuicheng Yan † † National University of Singapore ⋆ Sun Yat-sen University ∗ Adobe Research
Abstract
In this work, we propose a novel Reversible Recursive Instance-level Object Segmentation (R2-IOS) framework to address the challenging instance-level object segmentation task. R2-IOS consists of a reversible proposal refinement sub-network that predicts bounding box offsets for refining the object proposal locations, and an instance-level segmentation sub-network that generates the foreground mask of the dominant object instance in each proposal. By being recursive, R2-IOS iteratively optimizes the two sub-networks during joint training, in which the refined object proposals and improved segmentation predictions are alternately fed into each other to progressively increase the network capabilities. By being reversible, the proposal refinement sub-network adaptively determines an optimal number of refinement iterations required for each proposal during both training and testing. Furthermore, to handle multiple overlapped instances within a proposal, an instance-aware denoising autoencoder is introduced into the segmentation sub-network to distinguish the dominant object from other distracting instances. Extensive experiments on the challenging PASCAL VOC 2012 benchmark well demonstr
中文速览
实例级目标分割（instance-level object segmentation）要求对图像中每个对象实例都给出精确的像素级掩码，难点在于候选框质量参差不齐、同一框内多个同类对象相互遮挡。针对这一问题，研究者提出了可逆递归实例级分割框架 R2-IOS，将候选框精化与实例分割两个子网络统一在一起交替迭代训练——分割结果辅助候选框定位，精化后的候选框反过来改善分割掩码，两者相互促进。为了避免对所有候选框都做固定次数的迭代精化，框架引入"可逆门"机制，根据每个候选框在各迭代轮次中的类别置信度自适应地选择最优停止时机，再反向取回该轮的结果。此外，针对同一候选框内多个重叠实例难以区分的问题，子网络中嵌入了一个实例感知去噪自编码器，通过全局推断抑制干扰实例的噪声掩码、突出主体实例。在 PASCAL VOC 2012 基准上，R2-IOS 将实例分割的 AP^r（0.5 IoU）从此前最好的 58.7% 大幅提升至 66.7%，证明了该框架在候选框质量自适应优化与精准实例掩码生成方面的有效性。
原文 arXiv:1511.04517;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1511.04517v2