English
Related papers

Related papers: Efficient Stitchable Task Adaptation

200 papers

The pretrain-then-finetune paradigm has been widely used in various unimodal and multimodal tasks. However, finetuning all the parameters of a pre-trained model becomes prohibitive as the model size grows exponentially. To address this…

Multimedia · Computer Science 2023-08-29 Hongye Liu , Xianhai Xie , Yang Gao , Size Li , Zhou YU

While the enormous parameter scale endows Large Models (LMs) with unparalleled performance, it also limits their adaptability across specific tasks. Parameter-Efficient Fine-Tuning (PEFT) has emerged as a critical approach for effectively…

Machine Learning · Computer Science 2025-12-22 Dong Chen , Zhengqing Hu , Shixing Zhao , Yibo Guo

It has been proven that transfer learning provides an easy way to achieve state-of-the-art accuracies on several vision tasks by training a simple classifier on top of features obtained from pre-trained neural networks. The goal of this…

Machine Learning · Computer Science 2016-06-07 Milad Mohammadi , Subhasis Das

Recent advanced studies have spent considerable human efforts on optimizing network architectures for stereo matching but hardly achieved both high accuracy and fast inference speed. To ease the workload in network design, neural…

Computer Vision and Pattern Recognition · Computer Science 2022-07-21 Qiang Wang , Shaohuai Shi , Kaiyong Zhao , Xiaowen Chu

Deep Reinforcement Learning (DRL) has become a powerful tool for developing control policies in queueing networks, but the common use of Multi-layer Perceptron (MLP) neural networks in these applications has significant drawbacks. MLP…

Machine Learning · Computer Science 2025-01-22 Jerrod Wigmore , Brooke Shrader , Eytan Modiano

Models pre-trained on large-scale datasets are often fine-tuned to support newer tasks and datasets that arrive over time. This process necessitates storing copies of the model over time for each task that the pre-trained model is…

Computer Vision and Pattern Recognition · Computer Science 2023-09-22 Chaitanya Devaguptapu , Samarth Sinha , K J Joseph , Vineeth N Balasubramanian , Animesh Garg

Domain shift is a major problem for deploying deep networks in clinical practice. Network performance drops significantly with (target) images obtained differently than its (source) training data. Due to a lack of target label data, most…

Computer Vision and Pattern Recognition · Computer Science 2020-07-08 Yufan He , Aaron Carass , Lianrui Zuo , Blake E. Dewey , Jerry L. Prince

Fine-tuning large pre-trained models on downstream tasks has been adopted in a variety of domains recently. However, it is costly to update the entire parameter set of large pre-trained models. Although recently proposed parameter-efficient…

Computation and Language · Computer Science 2022-11-01 Yi-Lin Sung , Jaemin Cho , Mohit Bansal

Real-world deployment often exposes models to distribution shifts, making test-time adaptation (TTA) critical for robustness. Yet most TTA methods are unfriendly to edge deployment, as they rely on backpropagation, activation buffering, or…

Machine Learning · Computer Science 2026-05-08 Xinyu Luo , Jie Liu , Kecheng Chen , Junyi Yang , Bo Ding , Arindam Basu , Haoliang Li

Capitalizing on large pre-trained models for various downstream tasks of interest have recently emerged with promising performance. Due to the ever-growing model size, the standard full fine-tuning based task adaptation strategy becomes…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Junting Pan , Ziyi Lin , Xiatian Zhu , Jing Shao , Hongsheng Li

Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art (SOTA) semantic segmentation and object detection approaches reuse neural network architectures designed for image classification as…

Computer Vision and Pattern Recognition · Computer Science 2020-12-17 Jiemin Fang , Yuzhu Sun , Qian Zhang , Kangjian Peng , Yuan Li , Wenyu Liu , Xinggang Wang

Pretrained models have revolutionized deep learning by enabling significant performance improvements across a wide range of tasks, leveraging large-scale, pre-learned knowledge representations. However, deploying these models in real-world…

Machine Learning · Computer Science 2024-11-26 Tian Bowen , Lai Songning , Wu Jiemin , Shuai Zhihao , Ge Shiming , Yue Yutao

Machine learning (ML) is increasingly applied to optimize system performance in tasks such as resource management and network simulation. Unlike traditional ML tasks (e.g., image classification), networked systems often operate in…

Machine Learning · Computer Science 2026-05-15 Daiyang Yu , Xinyu Chen , Yihan Zhang , Yan Liang , Yaqi Qiao , Fan Lai

Pretrained vision-language models (VLMs) like CLIP show strong zero-shot performance but struggle with generalization under distribution shifts. Test-Time Adaptation (TTA) addresses this by adapting VLMs to unlabeled test data in new…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Hamidreza Dastmalchi , Aijun An , Ali cheraghian

In recent years, there has been a rapid development of spatio-temporal prediction techniques in response to the increasing demands of traffic management and travel planning. While advanced end-to-end models have achieved notable success in…

Machine Learning · Computer Science 2023-11-09 Zhonghang Li , Lianghao Xia , Yong Xu , Chao Huang

Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art (SOTA) semantic segmentation and object detection approaches reuse neural network architectures designed for image classification as…

Computer Vision and Pattern Recognition · Computer Science 2020-04-10 Jiemin Fang , Yuzhu Sun , Kangjian Peng , Qian Zhang , Yuan Li , Wenyu Liu , Xinggang Wang

Large Language Models (LLMs) face the "knowledge cutoff" challenge, where their frozen parametric memory prevents direct internalization of new information. While Supervised Fine-Tuning (SFT) is commonly used to update model knowledge, it…

Machine Learning · Computer Science 2026-05-12 Pingzhi Tang , Yiding Wang , Muhan Zhang

Large neural networks are typically trained for a fixed computational budget, creating a rigid trade-off between performance and efficiency that is ill-suited for deployment in resource-constrained or dynamic environments. Existing…

Machine Learning · Computer Science 2026-03-05 Paulius Rauba , Mihaela van der Schaar

Model merging offers an effective strategy to combine the strengths of multiple finetuned models into a unified model that preserves the specialized capabilities of each. Existing methods merge models in a global manner, performing…

Machine Learning · Computer Science 2025-01-08 Yifei He , Yuzheng Hu , Yong Lin , Tong Zhang , Han Zhao

Responding to rising global food security needs, precision agriculture and deep learning-based plant disease diagnosis have become crucial. Yet, deploying high-precision models on edge devices is challenging. Most lightweight networks use…

Computer Vision and Pattern Recognition · Computer Science 2025-09-05 Zongsen Qiu