Papers with Code 아카이브
Few-Shot Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 12
- 평가표
- 27
- 보존된 평가 기록
- 52
Few-Shot Learning is an example of meta-learning, where a learner is trained on several related tasks, during the meta-training phase, so that it can generalize well to unseen (but related) tasks with just few examples, during the meta-testing phase. An effective approach to the Few-Shot Learning problem is to learn a common representation for various tasks and train task specific classifiers on top of this representation.
Source: Penalty Method for Inversion-Free Deep Bilevel Optimization
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/qdo1010/SRPM_GPM
공식 코드A Feature-based Generalizable Prediction Model for Both Perceptual and Abstract Reasoning
https://github.com/qgao21/corediff
공식 코드https://github.com/qityy/droppatch
공식 코드https://github.com/qiushisun/bbt-rgb
공식 코드https://github.com/qiyanhero/tdsnet
공식 코드A Task-aware Dual Similarity Network for Fine-grained Few-shot Learning
https://github.com/qizhongtan/d2st-adapter
공식 코드D$^2$ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition
https://github.com/qqsuhao/One-shot-Learning-with-Absolute-Genelization
공식 코드https://github.com/quiil/benchmarkingpathologyfoundationmodels
공식 코드Benchmarking Pathology Foundation Models: Adaptation Strategies and Scenarios
https://github.com/raflaf/few-and-fewer
공식 코드Few and Fewer: Learning Better from Few Examples Using Fewer Base Classes
https://github.com/raflaf/fsl-benchmark-again
공식 코드Oops, I Sampled it Again: Reinterpreting Confidence Intervals in Few-Shot Learning
https://github.com/rahulvigneswaran/tailcalibx
공식 코드https://github.com/rajiv1990/DEff-GAN-Data-Efficient-GAN
공식 코드DEff-GAN: Diverse Attribute Transfer for Few-Shot Image Synthesis
https://github.com/raldir/aut-few
공식 코드Automated Few-shot Classification with Instruction-Finetuned Language Models
https://github.com/raoyongming/CAL
공식 코드Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification
https://github.com/raphael-baena/FIERCE-repo
공식 코드Preserving Fine-Grain Feature Information in Classification via Entropic Regularization
https://github.com/rashindrie/dipa
공식 코드https://github.com/rayneholland/collabdm
공식 코드https://github.com/rb080/wss_pole
공식 코드https://github.com/redabensaidds/foundation_fewshot
공식 코드A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Models
https://github.com/remiMZ/HTS-ECCV22
공식 코드Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation
https://github.com/remimz/metacoco-iclr24
공식 코드MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation
https://github.com/renmengye/inc-few-shot-attractor-public
공식 코드Incremental Few-Shot Learning with Attention Attractor Networks
https://github.com/renmengye/oc-fewshot-public
공식 코드Wandering Within a World: Online Contextualized Few-Shot Learning
https://github.com/renmengye/online-unsup-proto-net
공식 코드Online Unsupervised Learning of Visual Representations and Categories
https://github.com/rezazad68/fewshot-segmentation
공식 코드https://github.com/richardaecn/dataset-granularity
공식 코드https://github.com/rizar/CLOSURE
공식 코드CLOSURE: Assessing Systematic Generalization of CLEVR Models
https://github.com/rl-vig/libfewshot
공식 코드https://github.com/rlacombe/climatex
공식 코드ClimateX: Do LLMs Accurately Assess Human Expert Confidence in Climate Statements?
https://github.com/rlqja1107/torch-LLM4SGG
공식 코드LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation
https://github.com/robertoshea/forward_projection
공식 코드https://github.com/robinlu1209/st-gfsl
공식 코드Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer
https://github.com/robotic-vision-lab/few-shot-fruit-segmentation-via-transfer-learning
공식 코드https://github.com/rohitrango/STNAdversarial
공식 코드MA 3 : Model Agnostic Adversarial Augmentation for Few Shot learning
https://github.com/roysoumya/genemask
공식 코드GeneMask: Fast Pretraining of Gene Sequences to Enable Few-Shot Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.