跳到主要内容

工具箱的深度学习记事簿魔法部日志 GitHub

Authors & About YetAnotherAkasaki

All posts

欢迎来到魔法部日志
The Devil is in the Decoder - Classification, Regression and GANs
Threat of Adversarial Attacks on Deep Learning in Computer Vision - A Survey
Progressive Semantic Segmentation
Decoders Matter for Semantic Segmentation - Data-Dependent Decoding Enables Flexible Feature Aggregation
HLA-Face Joint High-Low Adaptation for Low Light Face Detection
DeepLab Series
Cross-Dataset Collaborative Learning for Semantic Segmentation
Dynamic Neural Networks - A Survey
Feature Pyramid Networks for Object Detection
A Review on Deep Learning Techniques Applied to Semantic Segmentation
MobileNetV2 - Inverted Residuals and Linear Bottlenecks
Fast-SCNN - Fast Semantic Segmentation Network
MobileNets - Efficient Convolutional Neural Networks for Mobile Vision Applications
Gated Channel Transformation for Visual Recognition
Convolutional Block Attention Module
Boundary IoU - Improving Object-Centric Image Segmentation Evaluation
Involution - Inverting the Inherence of Convolution for Visual Recognition
PointRend - Image Segmentation as Rendering
Transformer - Attention is all you need
RefineMask - Towards High-Quality Instance Segmentationwith Fine-Grained Features
GLADNet - Low-Light Enhancement Network with Global Awareness
Squeeze-and-Excitation Networks
BiSeNet - Bilateral Segmentation Network for Real-time Semantic Segmentation
Rethinking BiSeNet For Real-time Semantic Segmentation
CBAM - Convolutional Block Attention Module
Non-local Neural Networks
Non-local Networks Meet Squeeze-Excitation Networks and Beyond
Disentangled Non-Local Neural Networks
Deep Retinex Decomposition for Low-Light Enhancement
MSR-net - Low-light Image Enhancement Using Deep Convolutional Network
LLCNN - A convolutional neural network for low-light image enhancement
VOLO - Vision Outlooker for Visual Recognition
Polarized Self-Attention - Towards High-quality Pixel-wise Regression
SimAM - A Simple, Parameter-Free Attention Module for Convolutional Neural Networks
SOLO - Segmenting Objects by Locations
YOLACT - Real-time Instance Segmentation
You Only Look One-level Feature
Instance-sensitive Fully Convolutional Networks
Learning in the Frequency Domain
CCNet - Criss-Cross Attention for Semantic Segmentation
RepVGG - Making VGG-style ConvNets Great Again
PP-LCNet - A Lightweight CPU Convolutional Neural Network
Swin Transformer - Hierarchical Vision Transformer using Shifted Windows
Demystifying Local Vision Transformer
DCT-Mask - Discrete Cosine Transform Mask Representation for Instance Segmentation
Deep Retinex Decomposition for Low-Light Enhancement
GhostNet - More Features from Cheap Operations
Kindling the Darkness - A Practical Low-light Image Enhancer
How much Position Information Do Convolutional Neural Networks Encode?
Axiomatic Attribution for Deep Networks

标签

A

adversarial attacks1
atrous-convolution1
attention-mechanism16
attribution1

B

backbone11

C

cross-dataset-learning1

D

decoder3
detection5
dynamic-neural-network2

F

fcn1
FPN2
frequency-domain2

I

inductive-bias5
instance-segmentation3
iou1

L

light-weight6
loss-function1
low-light7

M

multi-branch2
multi-scale-learning5

N

non-convolution6

P

param-less1
positional-encoding1

R

refinement5
robustness1

S

segmentation15
survey5

T

transformer3
tricks1

V

visualization1

鲁ICP备2021025239号-2 Copyright © 2023 neet-cv.