https://github.com/Harry1993/GhostImage
공식 코드GhostImage: Remote Perception Attacks against Camera-based Image Classification Systems
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/HauschildLab/MGPATH
공식 코드MGPATH: Vision-Language Model with Multi-Granular Prompt Learning for Few-Shot WSI Classification
https://github.com/HazyResearch/butterfly
공식 코드Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps
https://github.com/HazyResearch/hidden-stratification
공식 코드No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems
https://github.com/HazyResearch/hippo-code
공식 코드https://github.com/HazyResearch/learning-circuits
공식 코드Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps
https://github.com/HazyResearch/structured-nets
공식 코드https://github.com/HeliosZhao/NCDSS
공식 코드https://github.com/Heliot7/open-set-da
공식 코드https://github.com/HelloZicky/DUET
공식 코드https://github.com/Hengwei-Zhao96/HOneCls
공식 코드One-Class Risk Estimation for One-Class Hyperspectral Image Classification
https://github.com/Henrymachiyu/ProtoViT
공식 코드Interpretable Image Classification with Adaptive Prototype-based Vision Transformers
https://github.com/HewlettPackard/trust-ml
공식 코드Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness
https://github.com/HobbitLong/CMC
공식 코드https://github.com/HobbitLong/SupContrast
공식 코드https://github.com/HolmesShuan/Compact-Global-Descriptor
공식 코드https://github.com/HongshengHu/membership-inference-machine-learning-literature
공식 코드https://github.com/HotanLee/DeFT
공식 코드https://github.com/Howal/Cross-iterationBatchNorm
공식 코드https://github.com/Howardqlz/Meta-MTL
공식 코드https://github.com/HsinYingLee/OPN
공식 코드https://github.com/Hua-YS/Multi-Scene-Recognition
공식 코드MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Images
https://github.com/Hyh200/Hyh200.github.io
공식 코드https://github.com/IBM/AutoVP
공식 코드AutoVP: An Automated Visual Prompting Framework and Benchmark
https://github.com/IBM/CrossViT
공식 코드CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification
https://github.com/IBM/OoD/tree/master/IRM_games
공식 코드https://github.com/IBM/RegionViT
공식 코드RegionViT: Regional-to-Local Attention for Vision Transformers
https://github.com/IBM/probabilistic-federated-neural-matching
공식 코드Bayesian Nonparametric Federated Learning of Neural Networks
https://github.com/ICHISubmission/Metric-Breast-Cancer
공식 코드https://github.com/IDU-CVLab/COV19D
공식 코드Deep Learning Based Automated COVID-19 Classification from Computed Tomography Images
https://github.com/IRVLUTD/Proto-CLIP
공식 코드Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning
https://github.com/IST-DASLab/WoodFisher
공식 코드WoodFisher: Efficient Second-Order Approximation for Neural Network Compression
https://github.com/ISorokos/SafeML
공식 코드SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measure
https://github.com/IVRL/FG-NIC
공식 코드Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks
https://github.com/IdanAzuri/glico-learning-small-sample
공식 코드Generative Latent Implicit Conditional Optimization when Learning from Small Sample
https://github.com/IdeasLabUT/EDA-Artifact-Detection
공식 코드Unsupervised Motion Artifact Detection in Wrist-Measured Electrodermal Activity Data
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.