https://github.com/zhouchichun/pixels_embedding
공식 코드Networks with pixels embedding: a method to improve noise resistance in images classification
Papers with Code 아카이브
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/zhoudaquan/Refiner_ViT
공식 코드https://github.com/zhoudaquan/dvit_repo
공식 코드https://github.com/zhoudw-zdw/cil_survey
공식 코드https://github.com/zhoudw-zdw/tpami-leadnet
공식 코드https://github.com/zhoufangqin/hylite
공식 코드https://github.com/zhoulong0/unem-transductive
공식 코드UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning
https://github.com/zhouweilian1904/HSI_Segmentation
공식 코드When Segmentation Meets Hyperspectral Image: New Paradigm for Hyperspectral Image Classification
https://github.com/zhouweilian1904/mamba-in-mamba
공식 코드https://github.com/zhouyuxuanyx/maximum-suppression-regularization
공식 코드MaxSup: Overcoming Representation Collapse in Label Smoothing
https://github.com/zhouyuxuanyx/multimax
공식 코드https://github.com/zhouzihao11/ccl
공식 코드Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition
https://github.com/zhu-xlab/fgmae
공식 코드Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing
https://github.com/zhu-xlab/ssl4eo-review
공식 코드https://github.com/zhu-xlab/ssl4eo-s12
공식 코드https://github.com/zhu-xlab/unida
공식 코드Universal Domain Adaptation for Remote Sensing Image Scene Classification
https://github.com/zhuang-group/lit
공식 코드https://github.com/zhuang-group/saq
공식 코드https://github.com/zhuang-group/spvit
공식 코드Pruning Self-attentions into Convolutional Layers in Single Path
https://github.com/zhuchen03/gradinit
공식 코드GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training
https://github.com/zhuchen03/maxva
공식 코드MaxVA: Fast Adaptation of Step Sizes by Maximizing Observed Variance of Gradients
https://github.com/zhufengx/SRN_multilabel
공식 코드Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification
https://github.com/zhuliao001/tlc
공식 코드https://github.com/zhunzhong07/Random-Erasing
공식 코드https://github.com/zhuogege1943/dgc
공식 코드Dynamic Group Convolution for Accelerating Convolutional Neural Networks
https://github.com/zhuogege1943/ftbnn
공식 코드FTBNN: Rethinking Non-linearity for 1-bit CNNs and Going Beyond
https://github.com/zhuole1025/llms_as_visual_explainers
공식 코드LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions
https://github.com/zhuqinfeng1999/seg-lstm
공식 코드Seg-LSTM: Performance of xLSTM for Semantic Segmentation of Remotely Sensed Images
https://github.com/zhyhan/transpar
공식 코드Learning Transferable Parameters for Unsupervised Domain Adaptation
https://github.com/zi-y/data-pruning-reid
공식 코드Data Pruning Can Do More: A Comprehensive Data Pruning Approach for Object Re-identification
https://github.com/ziatdinovmax/Semi-Supervised-VAE-nanoparticles
공식 코드https://github.com/zifanw/boundary
공식 코드Robust Models Are More Interpretable Because Attributions Look Normal
https://github.com/zihangJiang/TokenLabeling
공식 코드All Tokens Matter: Token Labeling for Training Better Vision Transformers
https://github.com/zihangm/neural-tmd-layer
공식 코드Neural TMDlayer: Modeling Instantaneous flow of features via SDE Generators
https://github.com/zijian-hu/SimPLE
공식 코드SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification
https://github.com/zijizhu/proto-non-param
공식 코드Interpretable Image Classification via Non-parametric Part Prototype Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.