profile
인공지능 전문가가 될레요

Bidirectional Attention-Recognition Model for Fine-Grained Object Classification 제2부

Fine-grained object classification (FGOC) is a challenging research topic in multimedia computing with machine learning 1–5, which aims to distinguish

2023년 1월 2일
·
0개의 댓글
·

Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learning 제1부

Relying on massive annotated datasets, significant progress has been made on many visual recognition tasks, which is mainly due to the widespread use

2022년 12월 27일
·
0개의 댓글
·

Semantic Feature Extraction for Generalized Zero-Shot Learning 제1부

https://arxiv.org/abs/2112.14478일반화 제로샷 학습을 위한 의미론적 특징 추출Generalized zero-shot learning (GZSL) is a technique to train a deep learning model to i

2022년 12월 27일
·
0개의 댓글
·
post-thumbnail

Transformers in Vision: A Survey 제3부

Inspired by non-local means operation 69 which was mainly designed for image denoising, Wang et al. 70 proposed a differentiable non-local operation f

2022년 12월 15일
·
0개의 댓글
·
post-thumbnail

Transformers in Vision: A Survey 제2부-2

For a given entity in the sequence, the self-attention basically computes the dot-product of the query with all keys, which is then normalized using s

2022년 12월 13일
·
0개의 댓글
·
post-thumbnail

Transformers in Vision: A Survey 제2부

Transformer models 1 have recently demonstrated exemplary performance on a broad range of language tasks e.g., text classification, machine translatio

2022년 12월 13일
·
0개의 댓글
·

Transformers in Vision: A Survey 제1부

Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision

2022년 12월 13일
·
0개의 댓글
·

Learning Deep Bilinear Transformation for Fine-grained Image Representation 제2부

Bilinear pooling 10 is proposed to obtain rich and orderless global representation for the last convolutional feature, which achieved the state-of-the

2022년 11월 2일
·
0개의 댓글
·

Deep Learning on Small Datasets without Pre-Training using Cosine Loss 제2부

The problem of learning from limited data has been approached from various directions. First and foremost, there is a huge body of work in the field o

2022년 10월 30일
·
0개의 댓글
·

Deep Learning on Small Datasets without Pre-Training using Cosine Loss 제1부

코사인 손실을 사용하여 사전 훈련 없이 작은 데이터 세트에 대한 딥 러닝Two things seem to be indisputable in the contemporary deep learning discourse: 1. The categorical cross-entro

2022년 10월 28일
·
0개의 댓글
·
post-thumbnail

Bi-Directional Attention for Joint Instance and Semantic Segmentation in Point Clouds 제2부

Among the tasks of computer vision, instance segmentation is one of the most challenge ones which requires understanding and perceiving the scene in u

2022년 10월 26일
·
0개의 댓글
·

Attribute Prototype Network for Zero-Shot Learning 제1부

Attribute Prototype Network for Zero-Shot Learning Abstract From the beginning of zero-shot learning research, visual attributes have been shown to

2022년 10월 23일
·
0개의 댓글
·

Remote Sensing Image Change Detection With Transformers 제1부

Remote Sensing Image Change Detection With Transformers변압기를 사용한 원격 감지 이미지 변경 감지Modern change detection (CD) has achieved remarkable success by the pow

2022년 10월 21일
·
0개의 댓글
·

TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization 제1부

TransGeo: 횡단면 이미지 지리적 위치 파악에 필요한 것은 변압기뿐입니다.The dominant CNN-based methods for cross-view image geo-localization rely on polar transform and fail to m

2022년 10월 21일
·
0개의 댓글
·
post-thumbnail

MPViT : Multi-Path Vision Transformer for Dense Prediction 제2부

Since its introduction, the Transformer 48 has had a huge impact on natural language processing (NLP) 4, 13, 39. Likewise, the advent of Vision Transf

2022년 10월 21일
·
0개의 댓글
·
post-thumbnail

MPViT : Multi-Path Vision Transformer for Dense Prediction 제1부

MPViT : Multi-Path Vision Transformer for Dense PredictionMPViT : 조밀한 예측을 위한 다중 경로 비전 변압기깃허브 : https://github.com/youngwanLEE/MPViTDense computer

2022년 10월 21일
·
0개의 댓글
·
post-thumbnail

CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows 제2부

Illustration of different self-attention mechanisms, our CSWin is fundamentally different from two aspects. First, we split multi-heads ({h 1 , . . .

2022년 10월 20일
·
0개의 댓글
·

CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows 제1부

논문링크 : https://openaccess.thecvf.com/content/CVPR2022/papers/Dong_CSWin_Transformer_A_General_Vision_Transformer_Backbone_With_Cross-Shaped_Windo

2022년 10월 20일
·
0개의 댓글
·
post-thumbnail

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows 제3부

In computing self-attention, we follow 45, 1, 29, 30 by including a relative position bias B ∈ RM2 × M2 to each head in computing similarity:자기 주의를 계산

2022년 10월 20일
·
0개의 댓글
·

A survey on semi-supervised learning 제1부

A survey on semi-supervised learningSemi-supervised learning is the branch of machine learning concerned with using labelled as well as unlabelled dat

2022년 10월 11일
·
0개의 댓글
·