Papers with Code 아카이브

Inductive Bias

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

0

보존된 평가 기록

0

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/gabriel-sgama/semantic-superpoint

Leveraging convergence behavior to balance conflicting tasks in multi-task learning

https://github.com/genforce/eqgan

Improving GAN Equilibrium by Raising Spatial Awareness

https://github.com/goldblum/AdversarialQuerying

Prototypical Networks for Few-shot Learning

https://github.com/google-research/google-research/tree/master/mutual_information_representation_learning

On Mutual Information Maximization for Representation Learning

https://github.com/gyhui14/spottune

SpotTune: Transfer Learning through Adaptive Fine-tuning

https://github.com/hananshafi/vits-for-small-scale-datasets

Vision Transformer for Small-Size Datasets

https://github.com/haofanwang/video-swin-transformer-pytorch

Video Swin Transformer

https://github.com/hav4ik/Hydra

Multi-Task Learning as Multi-Objective Optimization

https://github.com/hero9968/Graph_nets

Relational inductive biases, deep learning, and graph networks

https://github.com/heshandevaka/Trade-Off-MOL

Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach

https://github.com/hila-chefer/robustvit

How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers

https://github.com/holyseven/PSPNet-TF-Reproduce

Explicit Inductive Bias for Transfer Learning with Convolutional Networks

https://github.com/hongpeng-guo/deep-image-prior

Deep Image Prior

https://github.com/hrdwsong/ProtoNet-Paddle

Prototypical Networks for Few-shot Learning

https://github.com/huawei-noah/Efficient-AI-Backbones

Brain-inspired Multilayer Perceptron with Spiking Neurons

https://github.com/hubiodatalab/druggen

A Generalization of Transformer Networks to Graphs

https://github.com/huggingface/hmtl

A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks

https://github.com/huggingface/transformers

CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation

https://github.com/hui-design/aand

PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration

https://github.com/hw666666666666/CoAtNet

CoAtNet: Marrying Convolution and Attention for All Data Sizes

https://github.com/hwwang55/KGNN-LS

Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems

https://github.com/hyeonseobnam/sagnet

Reducing Domain Gap by Reducing Style Bias

https://github.com/hyeonseobnam/style-agnostic-networks

Reducing Domain Gap by Reducing Style Bias

https://github.com/hyn2028/llm-cxr

Taming Transformers for High-Resolution Image Synthesis

https://github.com/ibm/graph_ensemble_learning

AMR Parsing with Action-Pointer Transformer

https://github.com/innat/VideoSwin

Video Swin Transformer

https://github.com/innat/mae-spatiotemporal

Masked Autoencoders As Spatiotemporal Learners

https://github.com/isl-org/multiobjectiveoptimization

Multi-Task Learning as Multi-Objective Optimization

https://github.com/ixiaohuihuihui/ao2-detr

AO2-DETR: Arbitrary-Oriented Object Detection Transformer

https://github.com/jaemuzzin/plagnn

Inductive Relation Prediction by Subgraph Reasoning

https://github.com/jaketae/alibi

Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

https://github.com/jiamian-wang/iterative-soft-shrinkage-sr

Cross Aggregation Transformer for Image Restoration

https://github.com/jinmang2/hierarchical-transformer-1d

H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences

https://github.com/joanrod/ocr-vqgan

Taming Transformers for High-Resolution Image Synthesis

https://github.com/joh-fischer/PlantLDM

Taming Transformers for High-Resolution Image Synthesis

https://github.com/john-ai-lab/noisyrollout

NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.