Mmap: Multi-modal alignment prompt for cross-domain multi-task learning

Y Xin, J Du, Q Wang, K Yan, S Ding - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Multi-Task Learning (MTL) is designed to train multiple correlated tasks simultaneously,
thereby enhancing the performance of individual tasks. Typically, a multi-task network …

Prompt learning in computer vision: a survey

Y Lei, J Li, Z Li, Y Cao, H Shan - Frontiers of Information Technology & …, 2024 - Springer
Prompt learning has attracted broad attention in computer vision since the large pre-trained
vision-language models (VLMs) exploded. Based on the close relationship between vision …

Deep model fusion: A survey

W Li, Y Peng, M Zhang, L Ding, H Hu… - arXiv preprint arXiv …, 2023 - arxiv.org
Deep model fusion/merging is an emerging technique that merges the parameters or
predictions of multiple deep learning models into a single one. It combines the abilities of …

Dualcoop++: Fast and effective adaptation to multi-label recognition with limited annotations

P Hu, X Sun, S Sclaroff… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Multi-label image recognition in the low-label regime is a task of great challenge and
practical significance. Previous works have focused on learning the alignment between …

Global and local prompts cooperation via optimal transport for federated learning

H Li, W Huang, J Wang, Y Shi - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Prompt learning in pretrained visual-language models has shown remarkable flexibility
across various downstream tasks. Leveraging its inherent lightweight nature recent research …

Freestyleret: Retrieving images from style-diversified queries

H Li, Y Jia, P Jin, Z Cheng, K Li, J Sui, C Liu… - European Conference on …, 2025 - Springer
Image Retrieval aims to retrieve corresponding images based on a given query. In
application scenarios, users intend to express their retrieval intent through various query …

AAPL: Adding Attributes to Prompt Learning for Vision-Language Models

G Kim, S Kim, S Lee - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Recent advances in large pre-trained vision-language models have demonstrated
remarkable performance on zero-shot downstream tasks. Building upon this recent studies …

ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models

X Tian, S Zou, Z Yang, J Zhang - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Although soft prompt tuning is effective in efficiently adapting Vision-Language (V&L)
models for downstream tasks it shows limitations in dealing with distribution shifts. We …

A comprehensive survey on meta-learning: Applications, advances, and challenges

J Wang - Authorea Preprints, 2024 - techrxiv.org
Meta-learning, or" learning to learn", enables machines to acquire general priors with
minimal supervision and rapidly adapt to new tasks. Unlike traditional AI methods that …

One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning

D Kim, S Yoon, D Park, Y Lee, H Song, J Bang… - arXiv preprint arXiv …, 2023 - arxiv.org
In real-world continual learning scenarios, tasks often exhibit intricate and unpredictable
semantic shifts, posing challenges for fixed prompt management strategies. We identify the …