2022-11-05 更新
Broken Neural Scaling Laws
Authors:Ethan Caballero, Kshitij Gupta, Irina Rish, David Krueger
We present a smoothly broken power law functional form that accurately models and extrapolates the scaling behaviors of deep neural networks (i.e. how the evaluation metric of interest varies as the amount of compute used for training, number of model parameters, training dataset size, or upstream performance varies) for each task within a large and diverse set of upstream and downstream tasks, in zero-shot, prompted, and fine-tuned settings. This set includes large-scale vision and unsupervised language tasks, diffusion generative modeling of images, arithmetic, and reinforcement learning. When compared to other functional forms for neural scaling behavior, this functional form yields extrapolations of scaling behavior that are considerably more accurate (root mean squared log error of its extrapolations are 0.86 times that of previous state-of-the-art on average) on this set. Moreover, this functional form accurately models and extrapolates scaling behavior that other functional forms are incapable of expressing such as the non-monotonic transitions present in the scaling behavior of phenomena such as double descent and the delayed, sharp inflection points present in the scaling behavior of tasks such as arithmetic. Code is available at https://github.com/ethancaballero/broken_neural_scaling_laws
PDF
点此查看论文截图
Denoising Masked AutoEncoders are Certifiable Robust Vision Learners
Authors:Quanlin Wu, Hang Ye, Yuntian Gu, Huishuai Zhang, Liwei Wang, Di He
In this paper, we propose a new self-supervised method, which is called Denoising Masked AutoEncoders (DMAE), for learning certified robust classifiers of images. In DMAE, we corrupt each image by adding Gaussian noises to each pixel value and randomly masking several patches. A Transformer-based encoder-decoder model is then trained to reconstruct the original image from the corrupted one. In this learning paradigm, the encoder will learn to capture relevant semantics for the downstream tasks, which is also robust to Gaussian additive noises. We show that the pre-trained encoder can naturally be used as the base classifier in Gaussian smoothed models, where we can analytically compute the certified radius for any data point. Although the proposed method is simple, it yields significant performance improvement in downstream classification tasks. We show that the DMAE ViT-Base model, which just uses 1/10 parameters of the model developed in recent work arXiv:2206.10550, achieves competitive or better certified accuracy in various settings. The DMAE ViT-Large model significantly surpasses all previous results, establishing a new state-of-the-art on ImageNet dataset. We further demonstrate that the pre-trained model has good transferability to the CIFAR-10 dataset, suggesting its wide adaptability. Models and code are available at https://github.com/quanlin-wu/dmae.
PDF
点此查看论文截图
Rethinking Hierarchicies in Pre-trained Plain Vision Transformer
Authors:Yufei Xu, Jing Zhang, Qiming Zhang, Dacheng Tao
Self-supervised pre-training vision transformer (ViT) via masked image modeling (MIM) has been proven very effective. However, customized algorithms should be carefully designed for the hierarchical ViTs, e.g., GreenMIM, instead of using the vanilla and simple MAE for the plain ViT. More importantly, since these hierarchical ViTs cannot reuse the off-the-shelf pre-trained weights of the plain ViTs, the requirement of pre-training them leads to a massive amount of computational cost, thereby incurring both algorithmic and computational complexity. In this paper, we address this problem by proposing a novel idea of disentangling the hierarchical architecture design from the self-supervised pre-training. We transform the plain ViT into a hierarchical one with minimal changes. Technically, we change the stride of linear embedding layer from 16 to 4 and add convolution (or simple average) pooling layers between the transformer blocks, thereby reducing the feature size from 1/4 to 1/32 sequentially. Despite its simplicity, it outperforms the plain ViT baseline in classification, detection, and segmentation tasks on ImageNet, MS COCO, Cityscapes, and ADE20K benchmarks, respectively. We hope this preliminary study could draw more attention from the community on developing effective (hierarchical) ViTs while avoiding the pre-training cost by leveraging the off-the-shelf checkpoints. The code and models will be released at https://github.com/ViTAE-Transformer/HPViT.
PDF Tech report, work in progress
点此查看论文截图
WITT: A Wireless Image Transmission Transformer for Semantic Communications
Authors:Ke Yang, Sixian Wang, Jincheng Dai, Kailin Tan, Kai Niu, Ping Zhang
In this paper, we aim to redesign the vision Transformer (ViT) as a new backbone to realize semantic image transmission, termed wireless image transmission transformer (WITT). Previous works build upon convolutional neural networks (CNNs), which are inefficient in capturing global dependencies, resulting in degraded end-to-end transmission performance especially for high-resolution images. To tackle this, the proposed WITT employs Swin Transformers as a more capable backbone to extract long-range information. Different from ViTs in image classification tasks, WITT is highly optimized for image transmission while considering the effect of the wireless channel. Specifically, we propose a spatial modulation module to scale the latent representations according to channel state information, which enhances the ability of a single model to deal with various channel conditions. As a result, extensive experiments verify that our WITT attains better performance for different image resolutions, distortion metrics, and channel conditions. The code is available at https://github.com/KeYang8/WITT.
PDF
点此查看论文截图