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/yingyichen-cyy/Nested-Co-teaching
공식 코드https://github.com/yinzhangyue/c2fm
공식 코드https://github.com/yinzhangyue/smoothing-r3
공식 코드https://github.com/yiqiao-yin/YinsRLab
공식 코드https://github.com/yitu-opensource/T2T-ViT
공식 코드Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
https://github.com/yixinliu233/g-ood-d
공식 코드https://github.com/yjhuangcd/fi-ode
공식 코드FI-ODE: Certifiably Robust Forward Invariance in Neural ODEs
https://github.com/yjlee22/kan-ecoc
공식 코드Improving Generalizability of Kolmogorov-Arnold Networks via Error-Correcting Output Codes
https://github.com/yjliu7/neural-adaptive-empirical-bayes
공식 코드https://github.com/ykotseruba/snap
공식 코드SNAP: A Benchmark for Testing the Effects of Capture Conditions on Fundamental Vision Tasks
https://github.com/ykwon0407/wdro_local_perturbation
공식 코드https://github.com/ylingfeng/dynamicmlp
공식 코드https://github.com/yn-sun/cnn-ga
공식 코드Automatically designing CNN architectures using genetic algorithm for image classification
https://github.com/ynu-yangpeng/GLMC
공식 코드Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions
https://github.com/yogiprsty/sparse-vit
공식 코드https://github.com/yoloonme/ema-attention-module
공식 코드Efficient Multi-Scale Attention Module with Cross-Spatial Learning
https://github.com/yongchao97/FRePo
공식 코드https://github.com/yongchao97/diffusion_inversion
공식 코드Training on Thin Air: Improve Image Classification with Generated Data
https://github.com/yonghaoxu/rsen
공식 코드Robust Self-Ensembling Network for Hyperspectral Image Classification
https://github.com/yoonholee/MT-net
공식 코드Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace
https://github.com/yoonholee/divdis
공식 코드Diversify and Disambiguate: Learning From Underspecified Data
https://github.com/yooshincho/pytorch_convunitoptimization
공식 코드Improving Generalization of Batch Whitening by Convolutional Unit Optimization
https://github.com/yorkeyao/VehicleX
공식 코드Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond
https://github.com/yoshitomo-matsubara/bottlefit-split_computing
공식 코드https://github.com/yoshitomo-matsubara/hnd-ghnd-object-detectors
공식 코드Split Computing for Complex Object Detectors: Challenges and Preliminary Results
https://github.com/yoshitomo-matsubara/ladon-multi-task-sc2
공식 코드A Multi-task Supervised Compression Model for Split Computing
https://github.com/yoshitomo-matsubara/torchdistill
공식 코드torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation
https://github.com/youjiangxu/FaMUS
공식 코드https://github.com/youngleox/soft_augmentation
공식 코드https://github.com/youranonymousefriend/plugininversion
공식 코드Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations
https://github.com/youweiliang/evit
공식 코드Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations
https://github.com/ypotdevin/randomized-defenses
공식 코드An Empirical Investigation of Randomized Defenses against Adversarial Attacks
https://github.com/yqtianust/dflare
공식 코드Finding Deviated Behaviors of the Compressed DNN Models for Image Classifications
https://github.com/ysharma1126/ssl_identifiability
공식 코드Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
https://github.com/ysj9909/SHViT
공식 코드SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.