English
Related papers

Related papers: Generalized Attention Flow: Feature Attribution fo…

200 papers

To enhance the generalization performance of Multi-Task Networks (MTN) in Face Attribute Recognition (FAR), it is crucial to share relevant information across multiple related prediction tasks effectively. Traditional MTN methods create…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Gong Gao , Zekai Wang , Xianhui Liu , Weidong Zhao

We introduce Attention Graphs, a new tool for mechanistic interpretability of Graph Neural Networks (GNNs) and Graph Transformers based on the mathematical equivalence between message passing in GNNs and the self-attention mechanism in…

Machine Learning · Computer Science 2025-02-26 Batu El , Deepro Choudhury , Pietro Liò , Chaitanya K. Joshi

Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…

Machine Learning · Computer Science 2021-02-26 Yujing Wang , Yaming Yang , Jiangang Bai , Mingliang Zhang , Jing Bai , Jing Yu , Ce Zhang , Gao Huang , Yunhai Tong

The probability prediction of multivariate time series is a notoriously challenging but practical task. On the one hand, the challenge is how to effectively capture the cross-series correlations between interacting time series, to achieve…

Machine Learning · Computer Science 2023-07-24 Shibo Feng , Chunyan Miao , Ke Xu , Jiaxiang Wu , Pengcheng Wu , Yang Zhang , Peilin Zhao

We present an attention-based spatial graph convolution (AGC) for graph neural networks (GNNs). Existing AGCs focus on only using node-wise features and utilizing one type of attention function when calculating attention weights. Instead,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-06 Yang Li , Yuichi Tanaka

Two fundamental problems in unsupervised learning are efficient inference for latent-variable models and robust density estimation based on large amounts of unlabeled data. Algorithms for the two tasks, such as normalizing flows and…

Machine Learning · Statistics 2018-08-02 Changyou Chen , Chunyuan Li , Liqun Chen , Wenlin Wang , Yunchen Pu , Lawrence Carin

Transformers, renowned for their self-attention mechanism, have achieved state-of-the-art performance across various tasks in natural language processing, computer vision, time-series modeling, etc. However, one of the challenges with deep…

Machine Learning · Computer Science 2024-11-04 Jeongwhan Choi , Hyowon Wi , Jayoung Kim , Yehjin Shin , Kookjin Lee , Nathaniel Trask , Noseong Park

Explanations obtained from transformer-based architectures in the form of raw attention, can be seen as a class-agnostic saliency map. Additionally, attention-based pooling serves as a form of masking the in feature space. Motivated by this…

Computer Vision and Pattern Recognition · Computer Science 2024-04-24 Felipe Torres , Hanwei Zhang , Ronan Sicre , Stéphane Ayache , Yannis Avrithis

Classifier-Free Guidance (CFG) improves sample quality in diffusion models, but its dual-pass inference and reliance on null-condition training limit its use in few-step regimes. Attention-space guidance has emerged as a complementary…

Machine Learning · Computer Science 2026-05-19 Kwanyoung Kim

Diffusion models have achieved remarkable success across various domains. However, their slow generation speed remains a critical challenge. Existing acceleration methods, while aiming to reduce steps, often compromise sample quality,…

Machine Learning · Computer Science 2025-03-26 Huiyang Shao , Xin Xia , Yuhong Yang , Yuxi Ren , Xing Wang , Xuefeng Xiao

In recent years, deep learning models have demonstrated remarkable success in various domains, such as computer vision, natural language processing, and speech recognition. However, the generalization capabilities of these models can be…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Neelesh Mungoli

The Transformer model is widely used in natural language processing for sentence representation. However, the previous Transformer-based models focus on function words that have limited meaning in most cases and could merely extract…

Computation and Language · Computer Science 2021-07-05 Yu Shi

Generalized Category Discovery (GCD) aims to classify unlabeled data from both known and unknown categories by leveraging knowledge from labeled known categories. While existing methods have made notable progress, they often overlook a…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Qiyu Xu , Zhanxuan Hu , Yu Duan , Ercheng Pei , Yonghang Tai

Existing research largely attributes the global sequence modeling capability of Transformers to the explicit computation of attention weights, a process that inherently incurs quadratic computational complexity. In this work, we offer a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Ruize He , Dongchen Han , Gao Huang

The state-of-the-art speech enhancement has limited performance in speech estimation accuracy. Recently, in deep learning, the Transformer shows the potential to exploit the long-range dependency in speech by self-attention. Therefore, it…

Sound · Computer Science 2023-05-10 Yi Li , Yang Sun , Syed Mohsen Naqvi

The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables. We propose a new type of normalizing flow, inverse autoregressive flow (IAF), that, in contrast to…

Machine Learning · Computer Science 2017-02-01 Diederik P. Kingma , Tim Salimans , Rafal Jozefowicz , Xi Chen , Ilya Sutskever , Max Welling

In this paper, we introduce the novel state-of-the-art Dual-attention Transformer and Discriminative Flow (DADF) framework for visual anomaly detection. Based on only normal knowledge, visual anomaly detection has wide applications in…

Computer Vision and Pattern Recognition · Computer Science 2023-04-03 Haiming Yao , Wei Luo , Wenyong Yu

Data Attribution (DA) methods quantify the influence of individual training data points on model outputs and have broad applications such as explainability, data selection, and noisy label identification. However, existing DA methods are…

Machine Learning · Computer Science 2024-10-22 Dan Ley , Suraj Srinivas , Shichang Zhang , Gili Rusak , Himabindu Lakkaraju

Multimodal learning faces a fundamental tension between deep, fine-grained fusion and computational scalability. While cross-attention models achieve strong performance through exhaustive pairwise fusion, their quadratic complexity is…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Yusuf Shihata

The self-attention mechanism, while foundational to modern Transformer architectures, suffers from a critical inefficiency: it frequently allocates substantial attention to redundant or noisy context. Differential Attention addressed this…