Home

Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder ## ## ##

styleGAN_v1 A Style-Based Generator Architecture for Generative Adversarial Networks If a latent space is sufficiently disentangled, it should be possible to find direction vectors that consistently correspond to individual factors of variation styleGAN_v2 Analyzing and Improving the Image Quality of StyleGAN ...

Orthogonal Projection Loss

待补实验一 gama和walk_num超参数实验 因为使用了超参数\(\gamma\)控制混合样本时的相似度权重，因此需要取gamma=0.0(mix unsim), 0.2, 0.5(random sim, same weight), 0.8, 1.0(mix sim). 当前对于CUB和AWA数据集还需要补gamma=0.2, 0.8， walk_num=2, 4, 6, 8, 10的实验。 nohup python train_awa2.py --opts gama 0.2 fine_iter_num 5...

绘制3Dbar 添加文本标注 绘图颜色设置 import numpy as np import matplotlib matplotlib.rcParams['font.family'] = 'Times New Roman' matplotlib.rcParams['mathtext.default'] = 'regular' import matplotlib.pyplot as plt # from mpl_toolkits.mplot3d import Axes3D # 设置在jupyter中显示大小 import pylab pylab.rcParams['figure.figsize'] = (15.0, 8.0) # plt.figure(facecolor=...

What Remains of Visual Semantic Embeddings What Remains of Visual Semantic Embeddings

Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation

作者所在实验室网址 PETA和Market-1501数据集下载地址 SAL_ECCV2020 github SAL_ECCV2020