Papers with Code 아카이브

Object Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

39

평가표

124

보존된 평가 기록

977

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/ensta-u2is/deeplabv3plus-muad-pytorch

Rethinking Atrous Convolution for Semantic Image Segmentation

https://github.com/ensta-u2is/torch-uncertainty

Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks

https://github.com/enzomuschik/distilfnd

Deep Residual Learning for Image Recognition

https://github.com/eogussla12/Shufflenet_CIFAR10_Pytorch

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

https://github.com/epoc88/PFLD_68pts_Pytorch_2020

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

https://github.com/eps696/aphantasia

Learning Transferable Visual Models From Natural Language Supervision

https://github.com/epsilon-deltta/epsilon-deltta

CBNet: A Composite Backbone Network Architecture for Object Detection

https://github.com/erasaur/adversarial-patch-object-detection

On Physical Adversarial Patches for Object Detection

https://github.com/erbloo/dr

Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction

https://github.com/erezposner/Fast_Dense_Feature_Extraction

Fast Feature Extraction with CNNs with Pooling Layers

https://github.com/eric-ai-lab/pevit

ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models

https://github.com/eric-erki/IdenProf

Deep Residual Learning for Image Recognition

https://github.com/eric-erki/android-yolo

You Only Look Once: Unified, Real-Time Object Detection

https://github.com/eric-erki/darknet

YOLO9000: Better, Faster, Stronger

https://github.com/eric-erki/darknetAB

YOLO9000: Better, Faster, Stronger

https://github.com/eric-erki/yolov3

YOLO9000: Better, Faster, Stronger

https://github.com/ericyinyzy/vlattack

Learning Transferable Visual Models From Natural Language Supervision

https://github.com/erlendd/ddan

Revisiting Batch Normalization For Practical Domain Adaptation

https://github.com/ermongroup/EfficientObjectDetection

Efficient Object Detection in Large Images using Deep Reinforcement Learning

https://github.com/ermuur/darknet

YOLO9000: Better, Faster, Stronger

https://github.com/eshaanagarwal/hr-net-implementation

Deep High-Resolution Representation Learning for Visual Recognition

https://github.com/esimov/pigo

Object Detection with Pixel Intensity Comparisons Organized in Decision Trees

https://github.com/espressif/esp-who

MobileNetV2: Inverted Residuals and Linear Bottlenecks

https://github.com/esteimle/teaser

TEASER: Fast and Certifiable Point Cloud Registration

https://github.com/esw0116/DynaVSR

Deformable Convolutional Networks

https://github.com/etetteh/sota-data-augmentation-and-optimizers

RandAugment: Practical automated data augmentation with a reduced search space

https://github.com/eth-pbl/tinyissimoyolo

Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO

https://github.com/ethanhou99/ml_learn

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/ethanluoyc/transporter-pytorch

Unsupervised Learning of Object Keypoints for Perception and Control

https://github.com/etrommer/dcsr

MobileNetV2: Inverted Residuals and Linear Bottlenecks

https://github.com/eunjnnn/bfstvsr

Deformable ConvNets v2: More Deformable, Better Results

https://github.com/eunki7/flask-deeplearning-service-demo

MobileNetV2: Inverted Residuals and Linear Bottlenecks

https://github.com/eunseo1092/Object-Detection

You Only Look Once: Unified, Real-Time Object Detection

https://github.com/euphoria0-0/Learning-Loss-for-Active-Learning

Learning Loss for Active Learning

https://github.com/europa1610/Tensorflow-Shufflenet

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

https://github.com/euske/derpyolo

You Only Look Once: Unified, Real-Time Object Detection

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.