https://github.com/theot1/dign
공식 코드Diverse Gaussian Noise Consistency Regularization for Robustness and Uncertainty Calibration
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/thestephencasper/latent_adversarial_training
공식 코드Defending Against Unforeseen Failure Modes with Latent Adversarial Training
https://github.com/thezingaro/multimodal-side-tuning
공식 코드https://github.com/thjashin/multires-conv
공식 코드https://github.com/thomasbudd/ctarr
공식 코드https://github.com/thomasjo/nemo
공식 코드Towards detection and classification of microscopic foraminifera using transfer learning
https://github.com/thomasnorr/q-senn
공식 코드Take 5: Interpretable Image Classification with a Handful of Features
https://github.com/thomasverelst/dynconv
공식 코드Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference
https://github.com/thotranhuu99/Neural-Collapse-in-Deep-Linear-Networks
공식 코드Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data
https://github.com/thu-ml/ares
공식 코드https://github.com/thu-nics/framefusion
공식 코드https://github.com/thudzj/StructuredGAN
공식 코드https://github.com/thudzj/neuraleigenfunction
공식 코드https://github.com/thulas/dac-label-noise
공식 코드https://github.com/thumbe3/label-noise-nlp
공식 코드Towards Robustness to Label Noise in Text Classification via Noise Modeling
https://github.com/thuml/debiased-self-training
공식 코드https://github.com/thunlp/TR-BERT
공식 코드TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference
https://github.com/thuwuyinjun/Chef
공식 코드CHEF: A Cheap and Fast Pipeline for Iteratively Cleaning Label Uncertainties (Technical Report)
https://github.com/thuwzy/Cluster-Attack
공식 코드Cluster Attack: Query-based Adversarial Attacks on Graphs with Graph-Dependent Priors
https://github.com/thwjoy/adats
공식 코드Sample-dependent Adaptive Temperature Scaling for Improved Calibration
https://github.com/tianfang-zhang/cas-vit
공식 코드CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications
https://github.com/tiangeluo/fsl-global
공식 코드https://github.com/tianheyu927/PCGrad
공식 코드https://github.com/tianhuilab/falcon
공식 코드https://github.com/tianrun-chen/xLSTM-UNet-PyTorch
공식 코드https://github.com/tiendatnguyen-vision/orbit-symmetrize
공식 코드Learning Symmetrization for Equivariance with Orbit Distance Minimization
https://github.com/tiepvupsu/tensorsparsity
공식 코드Classifying Multi-channel UWB SAR Imagery via Tensor Sparsity Learning Techniques
https://github.com/tifat58/irr-with-cbm-rag
공식 코드Towards Interpretable Radiology Report Generation via Concept Bottlenecks using a Multi-Agentic RAG
https://github.com/timgaripov/swa
공식 코드Averaging Weights Leads to Wider Optima and Better Generalization
https://github.com/timmhess/kaaff
공식 코드Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting
https://github.com/timok93/blind_knowledge_distillation
공식 코드Blind Knowledge Distillation for Robust Image Classification
https://github.com/timqqt/MERA_Image_Classification
공식 코드Quantum Tensor Network in Machine Learning: An Application to Tiny Object Classification
https://github.com/timqqt/pytorch-zoom-in-network
공식 코드Efficient Classification of Very Large Images with Tiny Objects
https://github.com/tinkoff-ai/exact
공식 코드https://github.com/tiwarylab/terp
공식 코드Thermodynamics-inspired Explanations of Artificial Intelligence
https://github.com/tjddus9597/Proxy-Anchor-CVPR2020
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.