Multi-Task Learning
8개 벤치마크 · 논문 4,109편 · 이 태스크의 논문 보기 →
Benchmarks
QM9
Cityscapes test
NYUv2
OMNIGLOT
CelebA
ChestX-ray14
UTKFace
wireframe dataset
Most implemented
RetinaFace: Single-stage Dense Face Localisation in the Wild
Language Models are Few-Shot Learners
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
Language Models are Unsupervised Multitask Learners
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
Measuring Massive Multitask Language Understanding
Papers
UniH^3: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration
All-in-One medical image restoration (MedIR) aims to address diverse tasks across modalities and degradation types using a single universal model. Existing methods typically prioritize modeling inter-task heterogeneity (…
Multi-Task LearningImage RestorationMulti-Functional Embedding Models for Funder Name Disambiguation in Scientific Publication Records
Understanding the historical allocation and distribution of research funding advances our knowledge of how scientific research is supported across fields, institutions, and regions. However, large-scale analyses are hind…
Multi-Task LearningFederated Multi-Task Learning for Bladder Tumor Segmentation and MIBC Classification Using a Hybrid CNN-Transformer Architecture
Accurate bladder tumor segmentation and assessment of mus- cle invasion from T2-weighted MRI are important for treatment plan- ning, but developing robust models across institutions is challenging be- cause patient data …
Multi-Task LearningTumor SegmentationMonroe: A Molecular Foundation Model for In-Context Probabilistic Inference
Bioassay activity prediction is often data-limited because drug-discovery datasets rely on time-consuming and expensive wet-lab experiments for data generation and evaluation. This challenge has inspired recent research …
Activity PredictionMulti-Task LearningLearning Unified Video and Image Representation for Video Face Forgery Detection
Face forgery detection is crucial for preserving the security and integrity of facial data given the rapid developments in face manipulation techniques and deep generative models. Existing methods for video face forgery …
Multi-Task LearningEnhancing Scientific Named Entity Recognition via Large Language Models: A Type-driven Multi-task Learning Approach
Scientific named entity recognition (SciNER) plays a crucial role in information extraction and knowledge discovery from scientific texts. Recently, large language models (LLMs) have demonstrated the capacity to achieve …
Information ExtractionMulti-Task LearningEntity Typing