Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userConvNets vs. Transformers: Whose Visual Representations are More Transferable?
149
0
0.0
(
0
)
Added by
Hong-Yu Zhou
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Vision transformers have attracted much attention from computer vision researchers as they are not restricted to the spatial inductive bias of ConvNets. However, although Transformer-based backbones have achieved much progress on ImageNet classification, it is still unclear whether the learned representations are as transferable as or even more transferable than ConvNets features. To address this point, we systematically investigate the transfer learning ability of ConvNets and vision transformers in 15 single-task and multi-task performance evaluations. Given the strong correlation between the performance of pre-trained models and transfer learning, we include 2 residual ConvNets (i.e., R-101x3 and R-152x4) and 3 Transformer-based visual backbones (i.e., ViT-B, ViT-L and Swin-B), which have close error rates on ImageNet, that indicate similar transfer learning performance on downstream datasets. We observe consistent advantages of Transformer-based backbones on 13 downstream tasks (out of 15), including but not limited to fine-grained classification, scene recognition (classification, segmentation and depth estimation), open-domain classification, face recognition, etc. More specifically, we find that two ViT models heavily rely on whole network fine-tuning to achieve performance gains while Swin Transformer does not have such a requirement. Moreover, vision transformers behave more robustly in multi-task learning, i.e., bringing more improvements when managing mutually beneficial tasks and reducing performance losses when tackling irrelevant tasks. We hope our discoveries can facilitate the exploration and exploitation of vision transformers in the future.
rate research
Read More
Modern machine learning models for computer vision exceed humans in accuracy on specific visual recognition tasks, notably on datasets like ImageNet. However, high accuracy can be achieved in many ways. The particular decision function found by a machine learning system is determined not only by the data to which the system is exposed, but also the inductive biases of the model, which are typically harder to characterize. In this work, we follow a recent trend of in-depth behavioral analyses of neural network models that go beyond accuracy as an evaluation metric by looking at patterns of errors. Our focus is on comparing a suite of standard Convolutional Neural Networks (CNNs) and a recently-proposed attention-based network, the Vision Transformer (ViT), which relaxes the translation-invariance constraint of CNNs and therefore represents a model with a weaker set of inductive biases. Attention-based networks have previously been shown to achieve higher accuracy than CNNs on vision tasks, and we demonstrate, using new metrics for examining error consistency with more granularity, that their errors are also more consistent with those of humans. These results have implications both for building more human-like vision models, as well as for understanding visual object recognition in humans.
Vision transformers (ViTs) have demonstrated impressive performance on a series of computer vision tasks, yet they still suffer from adversarial examples. In this paper, we posit that adversarial attacks on transformers should be specially tailored for their architecture, jointly considering both patches and self-attention, in order to achieve high transferability. More specifically, we introduce a dual attack framework, which contains a Pay No Attention (PNA) attack and a PatchOut attack, to improve the transferability of adversarial samples across different ViTs. We show that skipping the gradients of attention during backpropagation can generate adversarial examples with high transferability. In addition, adversarial perturbations generated by optimizing randomly sampled subsets of patches at each iteration achieve higher attack success rates than attacks using all patches. We evaluate the transferability of attacks on state-of-the-art ViTs, CNNs and robustly trained CNNs. The results of these experiments demonstrate that the proposed dual attack can greatly boost transferability between ViTs and from ViTs to CNNs. In addition, the proposed method can easily be combined with existing transfer methods to boost performance.
We present BoTNet, a conceptually simple yet powerful backbone architecture that incorporates self-attention for multiple computer vision tasks including image classification, object detection and instance segmentation. By just replacing the spatial convolutions with global self-attention in the final three bottleneck blocks of a ResNet and no other changes, our approach improves upon the baselines significantly on instance segmentation and object detection while also reducing the parameters, with minimal overhead in latency. Through the design of BoTNet, we also point out how ResNet bottleneck blocks with self-attention can be viewed as Transformer blocks. Without any bells and whistles, BoTNet achieves 44.4% Mask AP and 49.7% Box AP on the COCO Instance Segmentation benchmark using the Mask R-CNN framework; surpassing the previous best published single model and single scale results of ResNeSt evaluated on the COCO validation set. Finally, we present a simple adaptation of the BoTNet design for image classification, resulting in models that achieve a strong performance of 84.7% top-1 accuracy on the ImageNet benchmark while being up to 1.64x faster in compute time than the popular EfficientNet models on TPU-v3 hardware. We hope our simple and effective approach will serve as a strong baseline for future research in self-attention models for vision
Transformers, composed of multiple self-attention layers, hold strong promises toward a generic learning primitive applicable to different data modalities, including the recent breakthroughs in computer vision achieving state-of-the-art (SOTA) standard accuracy with better parameter efficiency. Since self-attention helps a model systematically align different components present inside the input data, it leaves grounds to investigate its performance under model robustness benchmarks. In this work, we study the robustness of the Vision Transformer (ViT) against common corruptions and perturbations, distribution shifts, and natural adversarial examples. We use six different diverse ImageNet datasets concerning robust classification to conduct a comprehensive performance comparison of ViT models and SOTA convolutional neural networks (CNNs), Big-Transfer. Through a series of six systematically designed experiments, we then present analyses that provide both quantitative and qualitative indications to explain why ViTs are indeed more robust learners. For example, with fewer parameters and similar dataset and pre-training combinations, ViT gives a top-1 accuracy of 28.10% on ImageNet-A which is 4.3x higher than a comparable variant of BiT. Our analyses on image masking, Fourier spectrum sensitivity, and spread on discrete cosine energy spectrum reveal intriguing properties of ViT attributing to improved robustness. Code for reproducing our experiments is available here: https://git.io/J3VO0.
In order to learn object segmentation models in videos, conventional methods require a large amount of pixel-wise ground truth annotations. However, collecting such supervised data is time-consuming and labor-intensive. In this paper, we exploit existing annotations in source images and transfer such visual information to segment videos with unseen object categories. Without using any annotations in the target video, we propose a method to jointly mine useful segments and learn feature representations that better adapt to the target frames. The entire process is decomposed into two tasks: 1) solving a submodular function for selecting object-like segments, and 2) learning a CNN model with a transferable module for adapting seen categories in the source domain to the unseen target video. We present an iterative update scheme between two tasks to self-learn the final solution for object segmentation. Experimental results on numerous benchmark datasets show that the proposed method performs favorably against the state-of-the-art algorithms.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
