Image Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 33
- 평가표
- 177
- 보존된 평가 기록
- 2,906
Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/BB-Repos/BBaction
Video Classification with Channel-Separated Convolutional Networks
https://github.com/BBDrive/Meta-SGD-RL
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
https://github.com/BIG-CHENG/FaceRec
Very Deep Convolutional Networks for Large-Scale Image Recognition
https://github.com/BIGBALLON/distribuuuu
https://github.com/BOBrown/deeparsing-master
https://github.com/BR-IDL/PaddleViT
https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/CSwin
CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows
https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/CaiT
https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/DeiT
Training data-efficient image transformers & distillation through attention
https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/MLP-Mixer
https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/PVTv2
https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/ResMLP
ResMLP: Feedforward networks for image classification with data-efficient training
https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/Shuffle_Transformer
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/T2T_ViT
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/VOLO
https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/ViT
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/gMLP
https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification
https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/ConvNeXt
https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/CrossViT
CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification
https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/FF_Only
Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet
https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/Focal_Transformer
Focal Self-attention for Local-Global Interactions in Vision Transformers
https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/HaloNet
Scaling Local Self-Attention for Parameter Efficient Visual Backbones
https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/MobileOne
https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/MobileViT
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/PiT
https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/RepLKNet
Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs
https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/RepMLP
RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition
https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/ResT
https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/XCiT
https://github.com/BR-IDL/PaddleViT/tree/develop/self_supervised_learning/dino
https://github.com/BR-IDL/PaddleViT/tree/main/semantic_segmentation
https://github.com/BUPT-PRIV/MAE-priv
https://github.com/Baichenjia/DCGAN-eager
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
https://github.com/Baichenjia/Resnet
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.