https://github.com/google-research/sam
공식 코드Sharpness-Aware Minimization for Efficiently Improving Generalization
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/google-research/scenic
공식 코드https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining
공식 코드https://github.com/google-research/scenic/tree/main/scenic/projects/owl_vit
공식 코드Simple Open-Vocabulary Object Detection with Vision Transformers
https://github.com/google-research/simclr
공식 코드A Simple Framework for Contrastive Learning of Visual Representations
https://github.com/google-research/ssl_detection
공식 코드A Simple Semi-Supervised Learning Framework for Object Detection
https://github.com/google-research/syn-rep-learn
공식 코드Learning Vision from Models Rivals Learning Vision from Data
https://github.com/google-research/task_adaptation
공식 코드A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
https://github.com/google-research/uda
공식 코드https://github.com/google-research/vision_transformer
공식 코드An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
https://github.com/google-research/vmoe
공식 코드https://github.com/google/TensorNetwork
공식 코드https://github.com/google/automl/tree/master/efficientnetv2
공식 코드https://github.com/google/explaining-in-style
공식 코드Explaining in Style: Training a GAN to explain a classifier in StyleSpace
https://github.com/google/goldfinch
공식 코드The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
https://github.com/google/mentornet
공식 코드MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels
https://github.com/google/revisiting-self-supervised
공식 코드https://github.com/google/uncertainty-baselines
공식 코드Hyperparameter Ensembles for Robustness and Uncertainty Quantification
https://github.com/google/uncertainty-baselines/blob/master/baselines/cifar/hyperbatchensemble.py
공식 코드Hyperparameter Ensembles for Robustness and Uncertainty Quantification
https://github.com/google/uncertainty-baselines/tree/master/baselines/imagenet
공식 코드https://github.com/googleinterns/learning-bag-of-words
공식 코드https://github.com/googleinterns/wss
공식 코드PseudoSeg: Designing Pseudo Labels for Semantic Segmentation
https://github.com/gortizji/tangent_task_arithmetic
공식 코드Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models
https://github.com/gouki510/grokking-tickets
공식 코드Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks
https://github.com/graldij/transformer-fusion
공식 코드https://github.com/graph-zky/cafo
공식 코드https://github.com/grasp-lyrl/deep_reference_priors
공식 코드Deep Reference Priors: What is the best way to pretrain a model?
https://github.com/grasshlw/snn-neural-similarity-movie
공식 코드https://github.com/grasshopper14/Continued-fraction-of-straight-lines/blob/main/continued_fraction_reg.py
공식 코드https://github.com/gregor-ge/babel-imagenet
공식 코드Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations
https://github.com/gridai-labs/aavae
공식 코드https://github.com/grigorisg9gr/polynomial_nets
공식 코드https://github.com/grigorisg9gr/polynomials-for-augmenting-nns
공식 코드https://github.com/gtshs2/BetaLSTM
공식 코드https://github.com/guanghuifu/medical_dino_eval
공식 코드https://github.com/guanleics/adaplus
공식 코드AdaPlus: Integrating Nesterov Momentum and Precise Stepsize Adjustment on AdamW Basis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.