Ingredient-oriented multi-degradation learning for image restoration
Learning to leverage the relationship among diverse image restoration tasks is quite
beneficial for unraveling the intrinsic ingredients behind the degradation. Recent years have …
beneficial for unraveling the intrinsic ingredients behind the degradation. Recent years have …
Reasonable effectiveness of random weighting: A litmus test for multi-task learning
Multi-Task Learning (MTL) has achieved success in various fields. However, how to balance
different tasks to achieve good performance is a key problem. To achieve the task balancing …
different tasks to achieve good performance is a key problem. To achieve the task balancing …
Auto-lambda: Disentangling dynamic task relationships
Understanding the structure of multiple related tasks allows for multi-task learning to improve
the generalisation ability of one or all of them. However, it usually requires training each …
the generalisation ability of one or all of them. However, it usually requires training each …
Mtmamba: enhancing multi-task dense scene understanding by mamba-based decoders
Multi-task dense scene understanding, which learns a model for multiple dense prediction
tasks, has a wide range of application scenarios. Modeling long-range dependency and …
tasks, has a wide range of application scenarios. Modeling long-range dependency and …
Three-way trade-off in multi-objective learning: Optimization, generalization and conflict-avoidance
Multi-objective learning (MOL) often arises in emerging machine learning problems when
multiple learning criteria or tasks need to be addressed. Recent works have developed …
multiple learning criteria or tasks need to be addressed. Recent works have developed …
Effective structured prompting by meta-learning and representative verbalizer
Prompt tuning for pre-trained masked language models (MLM) has shown promising
performance in natural language processing tasks with few labeled examples. It tunes a …
performance in natural language processing tasks with few labeled examples. It tunes a …
Direction-oriented multi-objective learning: Simple and provable stochastic algorithms
Multi-objective optimization (MOO) has become an influential framework in many machine
learning problems with multiple objectives such as learning with multiple criteria and multi …
learning problems with multiple objectives such as learning with multiple criteria and multi …
[PDF][PDF] Mitigating gradient bias in multi-objective learning: A provably convergent approach
Machine learning problems with multiple objectives appear either i) in learning with multiple
criteria where learning has to make a trade-off between multiple performance metrics such …
criteria where learning has to make a trade-off between multiple performance metrics such …
Improvable gap balancing for multi-task learning
In multi-task learning (MTL), gradient balancing has recently attracted more research interest
than loss balancing since it often leads to better performance. However, loss balancing is …
than loss balancing since it often leads to better performance. However, loss balancing is …
Online constrained meta-learning: Provable guarantees for generalization
Meta-learning has attracted attention due to its strong ability to learn experiences from
known tasks, which can speed up and enhance the learning process for new tasks …
known tasks, which can speed up and enhance the learning process for new tasks …