论文标题
强迫症：学会与条件扩散模型过度合适
OCD: Learning to Overfit with Conditional Diffusion Models
论文作者
论文摘要
我们提出了一个动态模型，其中权重在输入样品x上进行条件，并学会了与通过对X及其标签y上的基本模型进行列式获得的匹配的模型。输入样本和网络权重之间的映射通过deo的扩散模型近似。我们采用的扩散模型侧重于修改基本模型的单层，并在该层的输入，激活和输出上进行条件。由于扩散模型本质上是随机的，因此多个初始化会产生不同的网络，形成一个集合，从而导致进一步的改进。我们的实验证明了该方法用于图像分类，3D重建，表格数据，语音分离和自然语言处理的广泛适用性。我们的代码可在https://github.com/shaharlutatipersonal/ocd上找到
We present a dynamic model in which the weights are conditioned on an input sample x and are learned to match those that would be obtained by finetuning a base model on x and its label y. This mapping between an input sample and network weights is approximated by a denoising diffusion model. The diffusion model we employ focuses on modifying a single layer of the base model and is conditioned on the input, activations, and output of this layer. Since the diffusion model is stochastic in nature, multiple initializations generate different networks, forming an ensemble, which leads to further improvements. Our experiments demonstrate the wide applicability of the method for image classification, 3D reconstruction, tabular data, speech separation, and natural language processing. Our code is available at https://github.com/ShaharLutatiPersonal/OCD
