Cross-Task Consistency Learning Framework for Multi-Task Learning
Multi-task learning (MTL) is an active field in deep learning in which we train a model to jointly learn multiple tasks by exploiting relationships between the tasks. It has been shown that MTL helps the model share the learned features between tasks and enhance predictions compared to when learning each task independently. We propose a new learning framework for 2-task MTL problem that uses the predictions of one task as inputs to another network to predict the other task. We define two new loss terms inspired by cycle-consistency loss and contrastive learning, alignment loss and cross-task consistency loss. Both losses are designed to enforce the model to align the predictions of multiple tasks so that the model predicts consistently. We theoretically prove that both losses help the model learn more efficiently and that cross-task consistency loss is better in terms of alignment with the straight-forward predictions. Experimental results also show that our proposed model achieves significant performance on the benchmark Cityscapes and NYU dataset.
Code (1)
Tasks
Contrastive LearningMulti-Task LearningSimilar Papers 제목 키워드 기반
Robust Learning Through Cross-Task Consistency
Visual perception entails solving a wide set of tasks, e.g., object detection, depth estimation, etc. The predictions made for multiple tasks from the same image are not independent, and therefore, are expected to be con…
3D ReconstructionDepth EstimationMulti-Task Learningobject-detection+2Robust Learning Through Cross-Task Consistency
Visual perception entails solving a wide set of tasks (e.g., object detection, depth estimation, etc). The predictions made for different tasks out of one image are not independent, and therefore, are expected to be 'con…
3D ReconstructionDepth EstimationMonocular Depth Estimationobject-detection+3HCDG: A Hierarchical Consistency Framework for Domain Generalization on Medical Image Segmentation
Modern deep neural networks struggle to transfer knowledge and generalize across diverse domains when deployed to real-world applications. Currently, domain generalization (DG) is introduced to learn a universal represen…
Data AugmentationDomain GeneralizationImage SegmentationMedical Image Segmentation+3Beyond Accuracy: Benchmarking Cross-Task Consistency in Unified Multimodal Models
Unified Multimodal Models (uMMs) aim to support both visual understanding and visual generation within a shared representation. However, existing evaluation protocols assess these two capabilities independently and do no…
Contrastive Multi-Task Dense Prediction
This paper targets the problem of multi-task dense prediction which aims to achieve simultaneous learning and inference on a bunch of multiple dense prediction tasks in a single framework. A core objective in design is h…
Contrastive LearningPredictionRepresentation Learning