Multi-scale Generative Adversarial Learning for Facial Attribute Transfer

Adversarial learning with multi-scale loss for skin lesion segmentation

2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) ◽

10.1109/isbi.2018.8363707 ◽

2018 ◽

Cited By ~ 10

Author(s):

Yuan Xue ◽

Tao Xu ◽

Xiaolei Huang

Keyword(s):

Skin Lesion ◽

Lesion Segmentation ◽

Adversarial Learning ◽

Multi Scale

Download Full-text

FCA-Net: Adversarial Learning for Skin Lesion Segmentation Based on Multi-Scale Features and Factorized Channel Attention

IEEE Access ◽

10.1109/access.2019.2940418 ◽

2019 ◽

Vol 7 ◽

pp. 130552-130565 ◽

Cited By ~ 5

Author(s):

Vivek Kumar Singh ◽

Mohamed Abdel-Nasser ◽

Hatem A. Rashwan ◽

Farhan Akram ◽

Nidhi Pandey ◽

...

Keyword(s):

Skin Lesion ◽

Lesion Segmentation ◽

Adversarial Learning ◽

Multi Scale

Download Full-text

Semantic Adversarial Network with Multi-Scale Pyramid Attention for Video Classification

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33019030 ◽

2019 ◽

Vol 33 ◽

pp. 9030-9037 ◽

Cited By ~ 3

Author(s):

De Xie ◽

Cheng Deng ◽

Hao Wang ◽

Chao Li ◽

Dapeng Tao

Keyword(s):

Classification Performance ◽

Video Data ◽

Temporal Information ◽

Local Context ◽

Video Classification ◽

Adversarial Learning ◽

Convolutional Networks ◽

Multi Scale ◽

Adversarial Network ◽

Global And Local

Two-stream architecture have shown strong performance in video classification task. The key idea is to learn spatiotemporal features by fusing convolutional networks spatially and temporally. However, there are some problems within such architecture. First, it relies on optical flow to model temporal information, which are often expensive to compute and store. Second, it has limited ability to capture details and local context information for video data. Third, it lacks explicit semantic guidance that greatly decrease the classification performance. In this paper, we proposed a new two-stream based deep framework for video classification to discover spatial and temporal information only from RGB frames, moreover, the multi-scale pyramid attention (MPA) layer and the semantic adversarial learning (SAL) module is introduced and integrated in our framework. The MPA enables the network capturing global and local feature to generate a comprehensive representation for video, and the SAL can make this representation gradually approximate to the real video semantics in an adversarial manner. Experimental results on two public benchmarks demonstrate our proposed methods achieves state-of-the-art results on standard video datasets.

Download Full-text

A Novel Multi-Scale Lightweight Fault Diagnosis Model Based on the Idea of Adversarial Learning

IEEE Transactions on Instrumentation and Measurement ◽

10.1109/tim.2021.3076841 ◽

2021 ◽

pp. 1-1

Author(s):

Ping Zhang ◽

Guangrui Wen ◽

Shuzhi Dong ◽

Hailong Lin ◽

Xin Huang ◽

...

Keyword(s):

Fault Diagnosis ◽

Adversarial Learning ◽

Multi Scale ◽

Model Based ◽

Diagnosis Model

Download Full-text

iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.7015 ◽

2020 ◽

Vol 34 (07) ◽

pp. 13122-13129 ◽

Cited By ~ 3

Author(s):

Chenfan Zhuang ◽

Xintong Han ◽

Weilin Huang ◽

Matthew Scott

Keyword(s):

Object Detection ◽

Best Practice ◽

Domain Adaptation ◽

Metric Learning ◽

Strong Relationship ◽

Adversarial Learning ◽

Multi Scale ◽

Rich Domain ◽

Multiple Alignments ◽

Coarse To Fine

Training an object detector on a data-rich domain and applying it to a data-poor one with limited performance drop is highly attractive in industry, because it saves huge annotation cost. Recent research on unsupervised domain adaptive object detection has verified that aligning data distributions between source and target images through adversarial learning is very useful. The key is when, where and how to use it to achieve best practice. We propose Image-Instance Full Alignment Networks (iFAN) to tackle this problem by precisely aligning feature distributions on both image and instance levels: 1) Image-level alignment: multi-scale features are roughly aligned by training adversarial domain classifiers in a hierarchically-nested fashion. 2) Full instance-level alignment: deep semantic information and elaborate instance representations are fully exploited to establish a strong relationship among categories and domains. Establishing these correlations is formulated as a metric learning problem by carefully constructing instance pairs. Above-mentioned adaptations can be integrated into an object detector (e.g. Faster R-CNN), resulting in an end-to-end trainable framework where multiple alignments can work collaboratively in a coarse-to-fine manner. In two domain adaptation tasks: synthetic-to-real (SIM10K → Cityscapes) and normal-to-foggy weather (Cityscapes → Foggy Cityscapes), iFAN outperforms the state-of-the-art methods with a boost of 10%+ AP over the source-only baseline.

Download Full-text