Symbiotic Adversarial Learning for Attribute-based Person Search

by   Yu-Tong Cao, et al.

Attribute-based person search is in significant demand for applications where no detected query images are available, such as identifying a criminal from witness. However, the task itself is quite challenging because there is a huge modality gap between images and physical descriptions of attributes. Often, there may also be a large number of unseen categories (attribute combinations). The current state-of-the-art methods either focus on learning better cross-modal embeddings by mining only seen data, or they explicitly use generative adversarial networks (GANs) to synthesize unseen features. The former tends to produce poor embeddings due to insufficient data, while the latter does not preserve intra-class compactness during generation. In this paper, we present a symbiotic adversarial learning framework, called SAL.Two GANs sit at the base of the framework in a symbiotic learning scheme: one synthesizes features of unseen classes/categories, while the other optimizes the embedding and performs the cross-modal alignment on the common embedding space .Specifically, two different types of generative adversarial networks learn collaboratively throughout the training process and the interactions between the two mutually benefit each other. Extensive evaluations show SAL's superiority over nine state-of-the-art methods with two challenging pedestrian benchmarks, PETA and Market-1501. The code is publicly available at: .


CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning

It is known that the inconsistent distribution and representation of dif...

ASMR: Learning Attribute-Based Person Search with Adaptive Semantic Margin Regularizer

Attribute-based person search is the task of finding person images that ...

Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning

We address the problem of segmenting 3D multi-modal medical images in sc...

Generative Adversarial Zero-shot Learning via Knowledge Graphs

Zero-shot learning (ZSL) is to handle the prediction of those unseen cla...

SyncGAN: Synchronize the Latent Space of Cross-modal Generative Adversarial Networks

Generative adversarial network (GAN) has achieved impressive success on ...

Structured Coupled Generative Adversarial Networks for Unsupervised Monocular Depth Estimation

Inspired by the success of adversarial learning, we propose a new end-to...

Memory Regulation and Alignment toward Generalizer RGB-Infrared Person

The domain shift, coming from unneglectable modality gap and non-overlap...

Please sign up or login with your details

Forgot password? Click here to reset