Papers with Code 아카이브

2D Object Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

15

평가표

20

보존된 평가 기록

57

코드

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

https://github.com/alibaba-miil/solving_imagenet

EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications

https://github.com/alibaba/EasyNLP

Learning Transferable Visual Models From Natural Language Supervision

https://github.com/alibaba/EasyNLP/tree/master/examples/blip_retrieval

BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

https://github.com/alibaba/cluster-contrast

Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net

https://github.com/alibaba/cluster-contrast-reid

Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net

https://github.com/alibaba/graphtranslator

BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

https://github.com/alibabasglab/frcrn

Squeeze-and-Excitation Networks

https://github.com/alicebizeul/pmae

Masked Autoencoders Are Scalable Vision Learners

https://github.com/alicranck/instance-seg

Semantic Instance Segmentation via Deep Metric Learning

https://github.com/alijavidani/local_global_representation_learning

Emerging Properties in Self-Supervised Vision Transformers

https://github.com/alililia/ascend_FaceAttribute

Deep Residual Learning for Image Recognition

https://github.com/alililia/ascend_HRNetW48_cls

Deep High-Resolution Representation Learning for Visual Recognition

https://github.com/alililia/ascend_ISyNet

ISyNet: Convolutional Neural Networks design for AI accelerator

https://github.com/alililia/ascend_SE-Net

Deep Residual Learning for Image Recognition

https://github.com/alililia/ascend_maskrcnn_mobilenetv1

Mask R-CNN

https://github.com/alililia/gpu_maskrcnn_mobilenetv1

Mask R-CNN

https://github.com/alililia/ms_extend/tree/main/ascend_senet

Squeeze-and-Excitation Networks

https://github.com/alililia/ms_extend/tree/main/gpu_efficientnet

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

https://github.com/alililia/ms_extend/tree/main/gpu_resnet

Deep Residual Learning for Image Recognition

https://github.com/alililia/u2net_Ascend

U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection

https://github.com/alililia/u2net_GPU

U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection

https://github.com/alisha17/benchmarks

Deep Residual Learning for Image Recognition

https://github.com/allanzelener/YAD2K

YOLO9000: Better, Faster, Stronger

https://github.com/allen108108/Model-Optimizer_Implementation

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

https://github.com/allenai/dnw

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

https://github.com/alpemek/ais3d

SSD: Single Shot MultiBox Detector

https://github.com/alrhub/arturo

Container: Context Aggregation Network

https://github.com/alrojo/lasagne_residual_network

Deep Residual Learning for Image Recognition

https://github.com/altomator/Introduction_to_Deep_Learning-2-Face_Detection

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

https://github.com/alvarobartt/serving-pytorch-models

Deep Residual Learning for Image Recognition

https://github.com/alvinwan/shiftresnet-cifar

SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving

https://github.com/alvinwen428/featurecp

Fully Convolutional Networks for Semantic Segmentation

https://github.com/alzmzyy/pointtransformer

Point Transformer

https://github.com/aman-garg0001/fruit-classifier

Deep Residual Learning for Image Recognition

https://github.com/amazingcodeLYL/Traffic_signs_detection_darket

YOLOv3: An Incremental Improvement

https://github.com/amazon-research/long-short-term-transformer

Deep Residual Learning for Image Recognition

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