paper-with-me

홈 › Papers

Adversarial Normalization: I Can Visualize Everything (ICE)

2023-01-01 · CVPR 2023 1 · Hoyoung Choi, Seungwan Jin, Kyungsik Han

Vision transformers use [CLS] tokens to predict image classes. Their explainability visualization has been studied using relevant information from [CLS] tokens or focusing on attention scores during self-attention. Such visualization, however, is challenging because of the dependence of the structure of a vision transformer on skip connections and attention operators, the instability of non-linearities in the learning process, and the limited reflection of self-attention scores on relevance. We argue that the output vectors for each input patch token in a vision transformer retain the image information of each patch location, which can facilitate the prediction of an image class. In this paper, we propose ICE (Adversarial Normalization: I Can visualize Everything), a novel method that enables a model to directly predict a class for each patch in an image; thus, advancing the effective visualization of the explainability of a vision transformer. Our method distinguishes background from foreground regions by predicting background classes for patches that do not determine image classes. We used the DeiT-S model, the most representative model employed in studies, on the explainability visualization of vision transformers. On the ImageNet-Segmentation dataset, ICE outperformed all explainability visualization methods for four cases depending on the model size. We also conducted quantitative and qualitative analyses on the tasks of weakly-supervised object localization and unsupervised object discovery. On the CUB-200-2011 and PASCALVOC07/12 datasets, ICE achieved comparable performance to the state-of-the-art methods. We incorporated ICE into the encoder of DeiT-S and improved efficiency by 44.01% on the ImageNet dataset over that achieved by the original DeiT-S model. We showed performance on the accuracy and efficiency comparable to EViT, the state-of-the-art pruning model, demonstrating the effectiveness of ICE. The code is available at https://github.com/Hanyang-HCC-Lab/ICE.

📄 PDF Abstract BibTeX

Code (1)

hanyang-hcc-lab/ice 공식 구현 pytorch

Tasks

Object DiscoveryObject LocalizationWeakly-Supervised Object Localization

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Pruning 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Prepare for the Worst: Generalizing across Domain Shifts with Adversarial Batch Normalization

2020-09-28 · Manli Shu, Zuxuan Wu, Micah Goldblum, Tom Goldstein

Adversarial training is the industry standard for producing models that are robust to small adversarial perturbations. However, machine learning practitioners need models that are robust to other kinds of changes that o…

Semantic Segmentation

Evaluating the Robustness of the "Ensemble Everything Everywhere" Defense

2024-11-22 · Jie Zhang, Christian Schlarmann, Kristina Nikolić, Nicholas Carlini 외

Ensemble everything everywhere is a defense to adversarial examples that was recently proposed to make image classifiers robust. This defense works by ensembling a model's intermediate representations at multiple noisy i…

Adversarial AttackRobust classification

A Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation

2018-09-14 · Rob Romijnders, Panagiotis Meletis, Gijs Dubbelman

We propose a normalization layer for unsupervised domain adaption in semantic scene segmentation. Normalization layers are known to improve convergence and generalization and are part of many state-of-the-art fully-convo…

Domain AdaptationScene Segmentation

V2XP-ASG: Generating Adversarial Scenes for Vehicle-to-Everything Perception

2022-09-27 · Hao Xiang, Runsheng Xu, Xin Xia, Zhaoliang Zheng 외

Recent advancements in Vehicle-to-Everything communication technology have enabled autonomous vehicles to share sensory information to obtain better perception performance. With the rapid growth of autonomous vehicles an…

Autonomous Vehicles

Gradient Normalization for Generative Adversarial Networks

2021-09-06 · ICCV 2021 10 · Yi-Lun Wu, Hong-Han Shuai, Zhi-Rui Tam, Hong-Yu Chiu

In this paper, we propose a novel normalization method called gradient normalization (GN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space. Unlike existing w…