https://github.com/inkiinki/mi-uap
공식 코드Interpreting Vulnerabilities of Multi-Instance Learning to Adversarial Perturbations
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/innaprop/innaprop
공식 코드A second-order-like optimizer with adaptive gradient scaling for deep learning
https://github.com/inspire-group/PatchCleanser
공식 코드PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier
https://github.com/inspire-group/SSD
공식 코드SSD: A Unified Framework for Self-Supervised Outlier Detection
https://github.com/inspire-group/detectorguard
공식 코드DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks
https://github.com/inspire-group/proxy-distributions
공식 코드Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?
https://github.com/intel/neural-compressor
공식 코드https://github.com/intellabs/fp8-emulation-toolkit
공식 코드https://github.com/intelligent-computing-lab-yale/rate-vs-direct
공식 코드https://github.com/invoker-ll/wsi-finetuning
공식 코드https://github.com/ipmi-icns-uke/sparsam
공식 코드https://github.com/irfanICMLL/structure_knowledge_distillation
공식 코드https://github.com/irom-lab/Task_Relevant_OOD_Detection
공식 코드Task-Driven Detection of Distribution Shifts with Statistical Guarantees for Robot Learning
https://github.com/isabelayepes/Image-Classification-Using-Singular-Value-Decomposition-and-Optimization
공식 코드Image Classification Using Singular Value Decomposition and Optimization
https://github.com/isbrycee/gem
공식 코드GEM: Boost Simple Network for Glass Surface Segmentation via Vision Foundation Models
https://github.com/isega24/ReVel
공식 코드https://github.com/ishohei220/adopt
공식 코드ADOPT: Modified Adam Can Converge with Any $β_2$ with the Optimal Rate
https://github.com/isl-cv/udi
공식 코드https://github.com/isl-org/MiDaS
공식 코드MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation
https://github.com/islam-nassar/semco
공식 코드All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training
https://github.com/ispamm/MMD-Bayesian-Neural-Network
공식 코드Bayesian Neural Networks With Maximum Mean Discrepancy Regularization
https://github.com/ist-daslab/cram
공식 코드https://github.com/istarjun/TapNet
공식 코드TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning
https://github.com/itsnotacie/information-fusion-sglp
공식 코드SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Models
https://github.com/ituvisionlab/EvidentialCalibration
공식 코드https://github.com/ituvisionlab/bfl-p
공식 코드How to Combine Variational Bayesian Networks in Federated Learning
https://github.com/ituvisionlab/evidentialturingprocess
공식 코드https://github.com/ivMCL/AttentiveNorm_Detection
공식 코드https://github.com/ivan-chai/exact
공식 코드https://github.com/ivanDonadello/semantic-PASCAL-Part
공식 코드https://github.com/ivandrokin/torch-conv-kan
공식 코드Kolmogorov-Arnold Convolutions: Design Principles and Empirical Studies
https://github.com/ividja/Probabilistic-PII
공식 코드Confidence-Aware and Self-Supervised Image Anomaly Localisation
https://github.com/ivmcl/pacavit
공식 코드PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers
https://github.com/izmailovpavel/flowgmm
공식 코드https://github.com/j-cb/breaking_down_ood_detection
공식 코드https://github.com/j-cb/ninco
공식 코드In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.