Learning from a limited amount of data, namely Few-Shot Learning, stands out
as a challenging computer vision task. Several works exploit semantics and
design complicated semantic fusion mechanisms to compensate for rare
representative features within restricted data. However, relying on naive
semantics such as class names introduces biases due to their brevity, while
acquiring extensive semantics from external knowledge takes a huge time and
effort. This limitation severely constrains the potential of semantics in
few-shot learning. In this paper, we design an automatic way called Semantic
Evolution to generate high-quality semantics. The incorporation of high-quality
semantics alleviates the need for complex network structures and learning
algorithms used in previous works. Hence, we employ a simple two-layer network
termed Semantic Alignment Network to transform semantics and visual features
into robust class prototypes with rich discriminative features for few-shot
classification. The experimental results show our framework outperforms all
previous methods on five benchmarks, demonstrating a simple network with
high-quality semantics can beat intricate multi-modal modules on few-shot
classification tasks.

利用少量数据进行学习是一项具有挑战性的计算机视觉任务，本文通过引入高质量的语义以及使用简单的网络结构，设计了一个名为 “语义进化” 的自动化方式来解决少样本学习中的问题，实验证明该方法在少样本分类任务中表现优异。

简单语义辅助的少样本学习

Simple Semantic-Aided Few-Shot Learning

How do words change their meaning? Although semantic evolution is driven by a
variety of distinct factors, including linguistic, societal, and technological
ones, we find that there is one law that holds universally across five major
Indo-European languages: that semantic evolution is strongly subdiffusive.
Using an automated pipeline of diachronic distributional semantic embedding
that controls for underlying symmetries, we show that words follow stochastic
trajectories in meaning space with an anomalous diffusion exponent $\alpha=
0.45\pm 0.05$ across languages, in contrast with diffusing particles that
follow $\alpha=1$. Randomization methods indicate that preserving temporal
correlations in semantic change directions is necessary to recover strongly
subdiffusive behavior; however, correlations in change sizes play an important
role too. We furthermore show that strong subdiffusion is a robust phenomenon
under a wide variety of choices in data analysis and interpretation, such as
the choice of fitting an ensemble average of displacements or averaging
best-fit exponents of individual word trajectories.

语义演化受到多种因素的影响，但我们发现，在五种印欧语族的语言中，语义演化普遍具有强烈的次扩散特征。使用一种自动化的历时分布语义嵌入管道，我们控制底层对称性，通过随机行走模型，发现词在意义空间中遵循随机轨迹， 并呈现出 anomalous subdiffusive 特性。我们发现保留变化方向中的时间相关性是必要的，同时变化尺度的相关性也发挥着重要作用。我们进一步表明，强次扩散是一种具有许多数据分析和解释选择的稳健现象。

印欧语系中的亚扩散语义演化

Subdiffusive semantic evolution in Indo-European languages

Text-to-image generation aims at generating realistic images which are
semantically consistent with the given text. Previous works mainly adopt the
multi-stage architecture by stacking generator-discriminator pairs to engage
multiple adversarial training, where the text semantics used to provide
generation guidance remain static across all stages. This work argues that text
features at each stage should be adaptively re-composed conditioned on the
status of the historical stage (i.e., historical stage's text and image
features) to provide diversified and accurate semantic guidance during the
coarse-to-fine generation process. We thereby propose a novel Dynamical
Semantic Evolution GAN (DSE-GAN) to re-compose each stage's text features under
a novel single adversarial multi-stage architecture. Specifically, we design
(1) Dynamic Semantic Evolution (DSE) module, which first aggregates historical
image features to summarize the generative feedback, and then dynamically
selects words required to be re-composed at each stage as well as re-composed
them by dynamically enhancing or suppressing different granularity subspace's
semantics. (2) Single Adversarial Multi-stage Architecture (SAMA), which
extends the previous structure by eliminating complicated multiple adversarial
training requirements and therefore allows more stages of text-image
interactions, and finally facilitates the DSE module. We conduct comprehensive
experiments and show that DSE-GAN achieves 7.48\% and 37.8\% relative FID
improvement on two widely used benchmarks, i.e., CUB-200 and MSCOCO,
respectively.

本文提出了一种新的动态语义演化生成对抗网络（DSE-GAN），采用单个生成器 - 鉴别器对的单个对抗训练架构，在每个阶段根据历史阶段的状态（即历史阶段的文本和图像特征）对文本特征进行自适应重新组合，以在粗到细的生成过程中提供多样化和准确的语义引导。在广泛使用的 CUB-200 和 MSCOCO 数据集上，实验结果表明该模型相对 FID 分别提高 7.48％和 37.8％。