Macro-Micro Adversarial Network for Human Parsing

TL;DR

This paper introduces the Macro-Micro Adversarial Network (MMAN) with two discriminators to improve human parsing by explicitly enforcing local and semantic consistency, leading to state-of-the-art results.

Contribution

The novel MMAN framework employs two specialized discriminators to address local and semantic inconsistencies separately in human parsing tasks.

Findings

Achieved mIoU of 46.81% on LIP dataset

Achieved mIoU of 59.91% on PASCAL-Person-Part

Demonstrated strong generalization on PPSS dataset

Abstract

In human parsing, the pixel-wise classification loss has drawbacks in its low-level local inconsistency and high-level semantic inconsistency. The introduction of the adversarial network tackles the two problems using a single discriminator. However, the two types of parsing inconsistency are generated by distinct mechanisms, so it is difficult for a single discriminator to solve them both. To address the two kinds of inconsistencies, this paper proposes the Macro-Micro Adversarial Net (MMAN). It has two discriminators. One discriminator, Macro D, acts on the low-resolution label map and penalizes semantic inconsistency, e.g., misplaced body parts. The other discriminator, Micro D, focuses on multiple patches of the high-resolution label map to address the local inconsistency, e.g., blur and hole. Compared with traditional adversarial networks, MMAN not only enforces local and semantic consistency explicitly, but also avoids the poor convergence problem of adversarial networks when handling high resolution images. In our experiment, we validate that the two discriminators are complementary to each other in improving the human parsing accuracy. The proposed framework is capable of producing competitive parsing performance compared with the state-of-the-art methods, i.e., mIoU=46.81% and 59.91% on LIP and PASCAL-Person-Part, respectively. On a relatively small dataset PPSS, our pre-trained model demonstrates impressive generalization ability. The code is publicly available at https://github.com/RoyalVane/MMAN.