Papers with Code 아카이브
Unsupervised Pre-training
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 2
- 보존된 평가 기록
- 7
Pre-training a neural network using unsupervised (self-supervised) auxiliary tasks on unlabeled data.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model
Foundation Model for Wireless Technology Recognition Using IQ Timeseries
Is MixIT Really Unsuitable for Correlated Sources? Exploring MixIT for Unsupervised Pre-training in Music Source Separation
The Efficiency of Pre-training with Objective Masking in Pseudo Labeling for Semi-Supervised Text Classification
Latte: Transfering LLMs` Latent-level Knowledge for Few-shot Tabular Learning
Risk Assessment Framework for Code LLMs via Leveraging Internal States
ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object Segmentation
CrystalFormer-RL: Reinforcement Fine-Tuning for Materials Design
ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object Segmentation with Zero-Shot Method
How much do LLMs learn from negative examples?
Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation
Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models
HindiLLM: Large Language Model for Hindi
FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning
Transferring self-supervised pre-trained models for SHM data anomaly detection with scarce labeled data
CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning
Point Cloud Unsupervised Pre-training via 3D Gaussian Splatting
Take Package as Language: Anomaly Detection Using Transformer
DepthSplat: Connecting Gaussian Splatting and Depth
SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual Representations
Calibrating Language Models with Adaptive Temperature Scaling
Range-aware Positional Encoding via High-order Pretraining: Theory and Practice
GFlowNet Pretraining with Inexpensive Rewards
TraIL-Det: Transformation-Invariant Local Feature Networks for 3D LiDAR Object Detection with Unsupervised Pre-Training
PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-Identification
From Recognition to Prediction: Leveraging Sequence Reasoning for Action Anticipation
Large Language Model Enabled Semantic Communication Systems
Learning Unsupervised Gaze Representation via Eye Mask Driven Information Bottleneck
ConStyle v2: A Strong Prompter for All-in-One Image Restoration
ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts
An Investigation of Noise Robustness for Flow-Matching-Based Zero-Shot TTS
Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI
PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning
Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation
Self-Supervised Modality-Agnostic Pre-Training of Swin Transformers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.