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/mlfoundations/patching
공식 코드https://github.com/mlfoundations/wise-ft
공식 코드https://github.com/mlmed/torchxrayvision
공식 코드TorchXRayVision: A library of chest X-ray datasets and models
https://github.com/mlvlab/EfficientViM
공식 코드EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality
https://github.com/mlvlab/SageMix
공식 코드https://github.com/mlvlab/mctf
공식 코드Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers
https://github.com/mlvlab/tokenmixup
공식 코드TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers
https://github.com/mmaaz60/EdgeNeXt
공식 코드EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications
https://github.com/mmaher22/instance-based-label-smoothing
공식 코드Instance-based Label Smoothing For Better Calibrated Classification Networks
https://github.com/mmasana/FACIL
공식 코드Class-incremental learning: survey and performance evaluation on image classification
https://github.com/mmoayeri/rival10
공식 코드https://github.com/mmunir127/rapidnet-official
공식 코드RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone
https://github.com/moabarar/qna
공식 코드https://github.com/moamirian/CNN_RBFs
공식 코드https://github.com/mobarakol/robustness_stress_testing
공식 코드https://github.com/mocherson/deep-generative-classifiers
공식 코드Deep Generative Classifiers for Thoracic Disease Diagnosis with Chest X-ray Images
https://github.com/modeltc/mqbench
공식 코드QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization
https://github.com/modeltc/united-perception
공식 코드The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition
https://github.com/modestyachts/imagenet-testbed
공식 코드Measuring Robustness to Natural Distribution Shifts in Image Classification
https://github.com/mofanv/darknetz
공식 코드DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments
https://github.com/mohaimenz/pruning-xnor
공식 코드Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devices
https://github.com/mohofar/beta-rank
공식 코드Beta-Rank: A Robust Convolutional Filter Pruning Method For Imbalanced Medical Image Analysis
https://github.com/moiexpositoalonsolab/DivShift
공식 코드https://github.com/momarky/egma
공식 코드Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning
https://github.com/mona4399/featuremixing
공식 코드Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation
https://github.com/monniert/dti-clustering
공식 코드https://github.com/moose-eccv22/moose_eccv2022
공식 코드Probing Contextual Diversity for Dense Out-of-Distribution Detection
https://github.com/mordiggian174/star-ensembling
공식 코드https://github.com/moremnas/MoreMNAS
공식 코드Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search
https://github.com/morganbdt/crumb
공식 코드Tuned Compositional Feature Replays for Efficient Stream Learning
https://github.com/moskomule/dataset-contamination
공식 코드https://github.com/moucheng2017/mismatchssl
공식 코드https://github.com/movinghoon/ESFR
공식 코드Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification
https://github.com/movinghoon/dtem
공식 코드Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers
https://github.com/mowangphy/HOPE-CNN
공식 코드Learning Convolutional Neural Networks using Hybrid Orthogonal Projection and Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.