paper-with-me

홈 › Papers

HYDRA -- Hyper Dependency Representation Attentions

2021-09-11 · Ha-Thanh Nguyen, Vu Tran, Tran-Binh Dang, Minh-Quan Bui, Minh-Phuong Nguyen, Le-Minh Nguyen

Attention is all we need as long as we have enough data. Even so, it is sometimes not easy to determine how much data is enough while the models are becoming larger and larger. In this paper, we propose HYDRA heads, lightweight pretrained linguistic self-attention heads to inject knowledge into transformer models without pretraining them again. Our approach is a balanced paradigm between leaving the models to learn unsupervised and forcing them to conform to linguistic knowledge rigidly as suggested in previous studies. Our experiment proves that the approach is not only the boost performance of the model but also lightweight and architecture friendly. We empirically verify our framework on benchmark datasets to show the contribution of linguistic knowledge to a transformer model. This is a promising result for a new approach to transferring knowledge from linguistic resources into transformer-based models.

📄 PDF Abstract BibTeX arXiv:2109.05349

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Hydra: A method for strain-minimizing hyperbolic embedding of network- and distance-based data

2019-03-21 · Martin Keller-Ressel, Stephanie Nargang

We introduce hydra (hyperbolic distance recovery and approximation), a new method for embedding network- or distance-based data into hyperbolic space. We show mathematically that hydra satisfies a certain optimality guar…

Strain-Minimizing Hyperbolic Network Embeddings with Landmarks

2022-07-14 · Martin Keller-Ressel, Stephanie Nargang

We introduce L-hydra (landmarked hyperbolic distance recovery and approximation), a method for embedding network- or distance-based data into hyperbolic space, which requires only the distance measurements to a few 'land…

HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks

2021-02-04 · YuanYuan Chen, Boyang Li, Han Yu, Pengcheng Wu 외

The behaviors of deep neural networks (DNNs) are notoriously resistant to human interpretations. In this paper, we propose Hypergradient Data Relevance Analysis, or HYDRA, which interprets the predictions made by DNNs as…

Rolling Shutter Correction

HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis

2017-09-28 · ICCV 2017 10 · Xihui Liu, Haiyu Zhao, Maoqing Tian, Lu Sheng 외

Pedestrian analysis plays a vital role in intelligent video surveillance and is a key component for security-centric computer vision systems. Despite that the convolutional neural networks are remarkable in learning disc…

AttributePedestrian Attribute RecognitionPerson Re-Identification

HydraMamba: Multi-Head State Space Model for Global Point Cloud Learning

2025-07-26 · Kanglin Qu, Pan Gao, Qun Dai, Yuanhao Sun arxiv

The attention mechanism has become a dominant operator in point cloud learning, but its quadratic complexity leads to limited inter-point interactions, hindering long-range dependency modeling between objects. Due to exc…

Long-range modeling