https://github.com/EdwinKim3069/XtarNet
공식 코드XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning
Papers with Code 아카이브
Novel Concepts
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Measures the ability of models to uncover an underlying concept that unites several ostensibly disparate entities, which hopefully would not co-occur frequently. This provides a limited test of a model's ability to creatively construct the necessary abstraction to make sense of a situation that it cannot have memorized in training.
Source: BIG-bench
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/MIFA-Lab/SAFE
공식 코드SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models
https://github.com/MrShininnnnn/CECW
공식 코드https://github.com/MyChocer/KGTN
공식 코드https://github.com/NVlabs/Bongard-LOGO
공식 코드Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
https://github.com/Rhyssiyan/DER-ClassIL.pytorch
공식 코드DER: Dynamically Expandable Representation for Class Incremental Learning
https://github.com/RongKaiWeskerMA/INSTA
공식 코드Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learning
https://github.com/USArmyResearchLab/ARL-HuRDL
공식 코드How Should Agents Ask Questions For Situated Learning? An Annotated Dialogue Corpus
https://github.com/XuyangAbert/CDSC-AL
공식 코드https://github.com/alieto/DEGARI
공식 코드https://github.com/alinlab/ifseg
공식 코드IFSeg: Image-free Semantic Segmentation via Vision-Language Model
https://github.com/bytedance/omniscient-model
공식 코드Towards Open-Ended Visual Recognition with Large Language Model
https://github.com/chang-ml-thu/FGH-flow
공식 코드Understanding MCMC Dynamics as Flows on the Wasserstein Space
https://github.com/chongzhou96/maskclip
공식 코드https://github.com/csiro-robotics/l3dmc
공식 코드L3DMC: Lifelong Learning using Distillation via Mixed-Curvature Space
https://github.com/csiro-robotics/sdcl
공식 코드https://github.com/cv516buaa/ov-vg
공식 코드https://github.com/dr-bell/crossl
공식 코드CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent Masking
https://github.com/dvruette/concept-guidance
공식 코드https://github.com/ebennequin/meta-domain-shift
공식 코드Bridging Few-Shot Learning and Adaptation: New Challenges of Support-Query Shift
https://github.com/eth-sri/diffai
공식 코드https://github.com/forest-art/dfsp
공식 코드Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning
https://github.com/gidariss/FewShotWithoutForgetting
공식 코드https://github.com/groundlight/vlm-visual-demonstrations
공식 코드Can Vision Language Models Learn from Visual Demonstrations of Ambiguous Spatial Reasoning?
https://github.com/gt-ripl/coda-prompt
공식 코드CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning
https://github.com/hlr/nesycoco
공식 코드NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional Generalization
https://github.com/isekai-portal/Link-Context-Learning
공식 코드https://github.com/ivalab/wdiscood
공식 코드WDiscOOD: Out-of-Distribution Detection via Whitened Linear Discriminant Analysis
https://github.com/jarch-ma/AFANet
공식 코드AFANet: Adaptive Frequency-Aware Network for Weakly-Supervised Few-Shot Semantic Segmentation
https://github.com/jaychempan/LAE-DINO
공식 코드Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community
https://github.com/kamwoh/dreamcreature
공식 코드DreamCreature: Crafting Photorealistic Virtual Creatures from Imagination
https://github.com/kreimanlab/VariationalPrototypeReplaysCL
공식 코드https://github.com/lexisnexis-risk-open-source/ledetection
공식 코드LEDetection: A Simple Framework for Semi-Supervised Few-Shot Object Detection
https://github.com/lorebianchi98/fg-clip
공식 코드Is CLIP the main roadblock for fine-grained open-world perception?
https://github.com/mashijie1028/happy-cgcd
공식 코드Happy: A Debiased Learning Framework for Continual Generalized Category Discovery
https://github.com/ml-research/bowll
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.