https://github.com/monalissaa/disendiff
공식 코드Attention Calibration for Disentangled Text-to-Image Personalization
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/nvlabs/bongard-hoi
공식 코드Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions
https://github.com/oatmealliu/msc-incd
공식 코드Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery
https://github.com/pnnl/neuromancer
공식 코드https://github.com/sharonal10/langint
공식 코드https://github.com/shaunak27/grain-clip
공식 코드Grounding Descriptions in Images informs Zero-Shot Visual Recognition
https://github.com/shininglab/systematic-generalization-via-meaningful-learning
공식 코드https://github.com/siyuyuan/scar
공식 코드https://github.com/snap-stanford/zeroc
공식 코드ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time
https://github.com/sstary/ssrs
공식 코드SAM-Assisted Remote Sensing Imagery Semantic Segmentation with Object and Boundary Constraints
https://github.com/tankche1/Semantic-Feature-Augmentation-in-Few-shot-Learning
공식 코드Multi-level Semantic Feature Augmentation for One-shot Learning
https://github.com/ucbdrive/tafe-net
공식 코드Task-Aware Feature Generation for Zero-Shot Compositional Learning
https://github.com/wx-zhang/igczsl
공식 코드Continual Zero-Shot Learning through Semantically Guided Generative Random Walks
https://github.com/xeniaohmer/hierarchical_reference_game
공식 코드Emergence of hierarchical reference systems in multi-agent communication
https://github.com/xzhe-vision/personamagic
공식 코드PersonaMagic: Stage-Regulated High-Fidelity Face Customization with Tandem Equilibrium
https://github.com/yixxin/xcon
공식 코드XCon: Learning with Experts for Fine-grained Category Discovery
https://github.com/zhang943/lpn-pytorch
공식 코드https://github.com/LisaAnne/DCC
Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data
https://github.com/Pranav21091996/Semantic_Fidelity-and-Egoshots
https://github.com/ViswanathaReddyGajjala/FewShotWithoutForgetting
https://github.com/aimagelab/mammoth
CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning
https://github.com/alexnwang/SketchEmbedNet-public
SketchEmbedNet: Learning Novel Concepts by Imitating Drawings
https://github.com/allenai/dolma
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
https://github.com/bramiozo/PubScience
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
https://github.com/chrisociepa/allamo
https://github.com/conceptofmind/PaLM-flax
https://github.com/ctrlovefly/df4lcz
SAM-Assisted Remote Sensing Imagery Semantic Segmentation with Object and Boundary Constraints
https://github.com/facebookresearch/edin
EDIN: An End-to-end Benchmark and Pipeline for Unknown Entity Discovery and Indexing
https://github.com/facebookresearch/taskmodularnets
Task-Driven Modular Networks for Zero-Shot Compositional Learning
https://github.com/foundation-model-stack/fms-fsdp
https://github.com/g-u-n/pycil
DER: Dynamically Expandable Representation for Class Incremental Learning
https://github.com/google/paxml
https://github.com/jaekyeom/mabas
https://github.com/kamwoh/partcraft
DreamCreature: Crafting Photorealistic Virtual Creatures from Imagination
https://github.com/karpathy/llama2.c
https://github.com/lorebianchi98/fg-ovd
Is CLIP the main roadblock for fine-grained open-world perception?
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.