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/lfb-1/gnl
공식 코드Partial Label Supervision for Agnostic Generative Noisy Label Learning
https://github.com/lfz/Guided-Denoise
공식 코드Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser
https://github.com/lgcnsai/ps-kd-pytorch
공식 코드Self-Knowledge Distillation with Progressive Refinement of Targets
https://github.com/lgm70/smug
공식 코드SMUG: Towards robust MRI reconstruction by smoothed unrolling
https://github.com/lgrativol/fl_exps
공식 코드Federated learning compression designed for lightweight communications
https://github.com/lgrco/l-greco
공식 코드L-GreCo: Layerwise-Adaptive Gradient Compression for Efficient and Accurate Deep Learning
https://github.com/lgx1123/gm4lt
공식 코드SAU: A Dual-Branch Network to Enhance Long-Tailed Recognition via Generative Models
https://github.com/lhf-labs/tm-dataset
공식 코드The Large Labelled Logo Dataset (L3D): A Multipurpose and Hand-Labelled Continuously Growing Dataset
https://github.com/lhoyer/mic
공식 코드MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
https://github.com/li-yapeng/mambahsi
공식 코드MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image Classification
https://github.com/li-zi-qi/SCCRC
공식 코드https://github.com/liam0949/llm-ood
공식 코드VI-OOD: A Unified Representation Learning Framework for Textual Out-of-distribution Detection
https://github.com/liangyn22/mcuformer
공식 코드MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory
https://github.com/lidq92/VSFA
공식 코드https://github.com/lifelong-ml/shels
공식 코드SHELS: Exclusive Feature Sets for Novelty Detection and Continual Learning Without Class Boundaries
https://github.com/lightdxy/bootmae
공식 코드Bootstrapped Masked Autoencoders for Vision BERT Pretraining
https://github.com/lijichang/flnl-feddiv
공식 코드FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels
https://github.com/lijichang/lnl-nce
공식 코드Neighborhood Collective Estimation for Noisy Label Identification and Correction
https://github.com/lijiefan/advcl
공식 코드When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?
https://github.com/likenneth/acton
공식 코드https://github.com/likyoo/SPANet
공식 코드Salient Positions based Attention Network for Image Classification
https://github.com/lili0415/dpu-ood-detection
공식 코드DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection
https://github.com/limapku/qsam
공식 코드Picking Up Quantization Steps for Compressed Image Classification
https://github.com/limbo0000/InstanceLoc
공식 코드Instance Localization for Self-supervised Detection Pretraining
https://github.com/limchaos/likelihood-ood
공식 코드Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representations
https://github.com/limengyang1992/lpl
공식 코드https://github.com/linasnas/dexter
공식 코드https://github.com/linqinliang/decowa
공식 코드Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping
https://github.com/linqs/dickens-arxiv24
공식 코드https://github.com/lins-lab/capaboost
공식 코드Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning
https://github.com/linusericsson/ssl-transfer
공식 코드https://github.com/linzhiqiu/continual-learning
공식 코드The CLEAR Benchmark: Continual LEArning on Real-World Imagery
https://github.com/lioujheyu/cuda_evolve
공식 코드https://github.com/lipang/special
공식 코드SPECIAL: Zero-shot Hyperspectral Image Classification With CLIP
https://github.com/litaoyang-jet/tpmil
공식 코드TPMIL: Trainable Prototype Enhanced Multiple Instance Learning for Whole Slide Image Classification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.