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/dnddnjs/pytorch-cifar10
https://github.com/dnouri/cuda-convnet
Improving neural networks by preventing co-adaptation of feature detectors
https://github.com/doc-analysis/DocBank
LayoutLM: Pre-training of Text and Layout for Document Image Understanding
https://github.com/dodoproptit99/deep-speaker
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
https://github.com/dolaram/Capsule-Network-for-MNIST-classification
https://github.com/dolaram/Deep-Reinforcement-Learning-using-Capsule-Network
https://github.com/domainadaptation/salad
https://github.com/dominickrei/limited-data-vits
https://github.com/donand/GAN_pytorch
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
https://github.com/donatoaz/what-do-you-see-zero-shot-image-classification-multimodal-llm
What Do You See? Enhancing Zero-Shot Image Classification with Multimodal Large Language Models
https://github.com/dongdong69/MixAugmentation
https://github.com/dongfangzhizhu/ECViT
ECViT: Efficient Convolutional Vision Transformer with Local-Attention and Multi-scale Stages
https://github.com/donghao51/multiood
DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection
https://github.com/dongkyuk/ConvNext-tensorflow
https://github.com/dongkyuk/PatchConvNet-pytorch
Augmenting Convolutional networks with attention-based aggregation
https://github.com/dootmaan/dsrl
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
https://github.com/dorbodwolf/darknet
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
https://github.com/dorlivne/simple_net_pruning
Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures
https://github.com/dotwang/hknas
Spectral-Spatial Global Graph Reasoning for Hyperspectral Image Classification
https://github.com/dougbrion/pytorch-deep-ensembles
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
https://github.com/dragen1860/CapsNet-Pytorch
https://github.com/dragen1860/DARTS-PyTorch
https://github.com/dragen1860/MAML-Pytorch
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
https://github.com/dragen1860/MAML-Pytorch-RL
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
https://github.com/dragen1860/Reptile-Pytorch
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
https://github.com/dravenww/curated-article
https://github.com/dreamercv/HSResNet-MMAL
Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization
https://github.com/dreamgonfly/GAN-tutorial
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
https://github.com/drewbarot/Un-CNN
https://github.com/drexelai/protein-nets
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
https://github.com/dronefreak/human-action-classification
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
https://github.com/drscotthawley/SPNet
Xception: Deep Learning with Depthwise Separable Convolutions
https://github.com/druidowm/occamnet_socialsci
OccamNet: A Fast Neural Model for Symbolic Regression at Scale
https://github.com/drumpt/ViT
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
https://github.com/drv-agwl/ViViT-pytorch
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.