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/big_vision
공식 코드https://github.com/google-research/compressive-visual-representations
공식 코드https://github.com/google-research/deeplab2
공식 코드Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
https://github.com/google-research/diffstride
공식 코드https://github.com/google-research/dp-imagenet
공식 코드https://github.com/google-research/federated
공식 코드Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning
https://github.com/google-research/fixmatch
공식 코드FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
https://github.com/google-research/fnc
공식 코드Boosting Contrastive Self-Supervised Learning with False Negative Cancellation
https://github.com/google-research/google-research
공식 코드A Benchmark for Interpretability Methods in Deep Neural Networks
https://github.com/google-research/google-research/tree/master/class_balanced_distillation
공식 코드Class-Balanced Distillation for Long-Tailed Visual Recognition
https://github.com/google-research/google-research/tree/master/dp_transfer
공식 코드https://github.com/google-research/google-research/tree/master/extreme_memorization
공식 코드https://github.com/google-research/google-research/tree/master/hypertransformer
공식 코드HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning
https://github.com/google-research/google-research/tree/master/ieg
공식 코드https://github.com/google-research/google-research/tree/master/logit_adjustment
공식 코드https://github.com/google-research/google-research/tree/master/mentormix
공식 코드Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels
https://github.com/google-research/google-research/tree/master/meta_learning_without_memorization
공식 코드https://github.com/google-research/google-research/tree/master/meta_pseudo_labels
공식 코드https://github.com/google-research/google-research/tree/master/muNet
공식 코드An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems
https://github.com/google-research/google-research/tree/master/muller
공식 코드https://github.com/google-research/google-research/tree/master/remote_sensing_representations
공식 코드https://github.com/google-research/google-research/tree/master/scalable_shampoo/jax
공식 코드https://github.com/google-research/google-research/tree/master/supcon
공식 코드https://github.com/google-research/google-research/tree/master/vatt
공식 코드VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
https://github.com/google-research/imagenet-mistakes
공식 코드When does dough become a bagel? Analyzing the remaining mistakes on ImageNet
https://github.com/google-research/jax-influence
공식 코드https://github.com/google-research/l2p
공식 코드https://github.com/google-research/maxvit
공식 코드https://github.com/google-research/meta-dataset
공식 코드Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
https://github.com/google-research/mixmatch
공식 코드https://github.com/google-research/nested-transformer
공식 코드https://github.com/google-research/noisystudent
공식 코드Self-training with Noisy Student improves ImageNet classification
https://github.com/google-research/remixmatch
공식 코드ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
https://github.com/google-research/rigl
공식 코드https://github.com/google-research/robustness_metrics/tree/master/robustness_metrics/projects/revisiting_calibration
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.