paper-with-me

Papers

Hadamard Product for Low-rank Bilinear Pooling

2016-10-14 · Jin-Hwa Kim, Kyoung-Woon On, Woosang Lim, Jeonghee Kim, Jung-Woo Ha, Byoung-Tak Zhang

Bilinear models provide rich representations compared with linear models. They have been applied in various visual tasks, such as object recognition, segmentation, and visual question-answering, to get state-of-the-art performances taking advantage of the expanded representations. However, bilinear representations tend to be high-dimensional, limiting the applicability to computationally complex tasks. We propose low-rank bilinear pooling using Hadamard product for an efficient attention mechanism of multimodal learning. We show that our model outperforms compact bilinear pooling in visual question-answering tasks with the state-of-the-art results on the VQA dataset, having a better parsimonious property.

📄 PDF Abstract BibTeX arXiv:1610.04325

Code (11)

jnhwkim/MulLowBiVQA 공식 구현 torch
Adam1679/mutan-article-net pytorch
Cadene/vqa.pytorch pytorch
MindSpore-scientific-2/code-10/tree/main/PR_Product mindspore
MindSpore-scientific-2/code-8/tree/main/PR_Product mindspore
MindSpore-scientific/code-8/tree/main/PR_Product mindspore
facebookresearch/ParlAI pytorch
gabegrand/adversarial-vqa pytorch
jnhwkim/nips-mrn-vqa torch
vuhoangminh/vqa_medical pytorch
yikang-li/iqan pytorch

Tasks

Visual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Hadamard Extensions and the Identification of Mixtures of Product Distributions

2021-01-27 · Spencer L. Gordon, Leonard J. Schulman

The Hadamard Extension of a matrix is the matrix consisting of all Hadamard products of subsets of its rows. This construction arises in the context of identifying a mixture of product distributions on binary random vari…

FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction

2019-05-23 · Tongwen Huang, Zhiqi Zhang, Junlin Zhang

Advertising and feed ranking are essential to many Internet companies such as Facebook and Sina Weibo. Among many real-world advertising and feed ranking systems, click through rate (CTR) prediction plays a central role.…

Click-Through Rate PredictionFeature ImportanceRecommendation Systems

Toward Faster and Simpler Matrix Normalization via Rank-1 Update

2020-08-01 · ECCV 2020 8 · Tan Yu, Yunfeng Cai, Ping Li

Bilinear pooling has achieved an impressive improvement in many computer vision tasks. Recent studies discover that matrix normalization is vital for improving the performance of bilinear pooling. Nevertheless, tradition…

GPU

Low-rank Bilinear Pooling for Fine-Grained Classification

2016-11-16 · CVPR 2017 7 · Shu Kong, Charless Fowlkes

Pooling second-order local feature statistics to form a high-dimensional bilinear feature has been shown to achieve state-of-the-art performance on a variety of fine-grained classification tasks. To address the computati…

ClassificationGeneral Classification

BoHA: Blockwise Hadamard Product Adaptation for Parameter-Efficient Fine-Tuning

2025-09-25 · Feng Yu, Jia Hu, Geyong Min arxiv

Parameter-efficient fine-tuning (PEFT) of large language models trains a small task-specific parameter set while keeping the pretrained model frozen. The dominant Low-Rank Adaptation (LoRA) family makes this trade-off pr…

parameter-efficient fine-tuningArithmetic Reasoning