English
Related papers

Related papers: Test-Time Distillation for Continual Model Adaptat…

200 papers

As Large Language Models (LLMs) scale up, inference efficiency becomes a critical bottleneck. Multi-Token Prediction (MTP) could accelerate LLM inference by predicting multiple future tokens in parallel. However, existing MTP approaches…

Computation and Language · Computer Science 2026-03-26 Guoliang Zhao , Ruobing Xie , An Wang , Shuaipeng Li , Huaibing Xie , Xingwu Sun

Test-time adaptation (TTA) adapts the pre-trained models to test distributions during the inference phase exclusively employing unlabeled test data streams, which holds great value for the deployment of models in real-world applications.…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Shuang Li , Longhui Yuan , Binhui Xie , Tao Yang

Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference. One popular approach involves fine-tuning model with cross-entropy loss according to estimated pseudo-labels.…

Machine Learning · Computer Science 2024-01-26 Guowei Wang , Changxing Ding , Wentao Tan , Mingkui Tan

Despite exciting progress in pre-training for visual-linguistic (VL) representations, very few aspire to a small VL model. In this paper, we study knowledge distillation (KD) to effectively compress a transformer-based large VL model into a…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Zhiyuan Fang , Jianfeng Wang , Xiaowei Hu , Lijuan Wang , Yezhou Yang , Zicheng Liu

Conventional test-time adaptation (TTA) approaches typically adapt the model using only a small fraction of test samples, often those with low-entropy predictions, thereby failing to fully leverage the available information in the test…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Nam Nguyen Phuong , Duc Nguyen The Minh , Phi Le Nguyen , Ehsan Abbasnejad , Minh Hoai

Real-world vision models in dynamic environments face rapid shifts in domain distributions, leading to decreased recognition performance. Using unlabeled test data, continuous test-time adaptation (CTTA) directly adjusts a pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2025-01-28 Sarthak Kumar Maharana , Baoming Zhang , Yunhui Guo

Since autonomous driving systems usually face dynamic and ever-changing environments, continual test-time adaptation (CTTA) has been proposed as a strategy for transferring deployed models to continually changing target domains. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-04-01 Jiayi Ni , Senqiao Yang , Ran Xu , Jiaming Liu , Xiaoqi Li , Wenyu Jiao , Zehui Chen , Yi Liu , Shanghang Zhang

Benefiting from prompt tuning, recent years have witnessed the promising performance of pre-trained vision-language models, e.g., CLIP, on versatile downstream tasks. In this paper, we focus on a particular setting of learning adaptive…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Chun-Mei Feng , Kai Yu , Yong Liu , Salman Khan , Wangmeng Zuo

Continual Test Time Adaptation (CTTA) has emerged as a critical approach for bridging the domain gap between the controlled training environments and the real-world scenarios, enhancing model adaptability and robustness. Existing CTTA…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Hyewon Park , Hyejin Park , Jueun Ko , Dongbo Min

We tackle the challenging issue of aggressive fine-tuning encountered during the process of transfer learning of pre-trained language models (PLMs) with limited labeled downstream data. This problem primarily results in a decline in…

Computation and Language · Computer Science 2023-12-13 Ibtihel Amara , Vinija Jain , Aman Chadha

Dataset Distillation is used to create a concise, yet informative, synthetic dataset that can replace the original dataset for training purposes. Some leading methods in this domain prioritize long-range matching, involving the unrolling of…

Computer Vision and Pattern Recognition · Computer Science 2024-07-22 Dai Liu , Jindong Gu , Hu Cao , Carsten Trinitis , Martin Schulz

Healthcare providers are increasingly using machine learning to predict patient outcomes to make meaningful interventions. However, despite innovations in this area, deep learning models often struggle to match performance of shallow linear…

Machine Learning · Computer Science 2020-12-18 Rohan S. Kodialam , Rebecca Boiarsky , Justin Lim , Neil Dixit , Aditya Sai , David Sontag

Medical foundation models pre-trained on large-scale datasets have shown powerful versatile performance. However, when adapting medical foundation models for specific medical scenarios, it remains the inevitable challenge due to the gap…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Siyuan Du , Yuhang Zhou , Haolin Li , Jiangchao Yao , Haishuai Wang , Hui Lin , Ya Zhang , Yanfeng Wang

Consistency distillation methods have demonstrated significant success in accelerating generative tasks of diffusion models. However, since previous consistency distillation methods use simple and straightforward strategies in selecting…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Cunzheng Wang , Ziyuan Guo , Yuxuan Duan , Huaxia Li , Nemo Chen , Xu Tang , Yao Hu

Learning to adapt pretrained language models to unlabeled, out-of-distribution data is a critical challenge, as models often falter on structurally novel reasoning tasks even while excelling within their training distribution. We introduce…

Computation and Language · Computer Science 2025-05-29 Mohammad Mahdi Moradi , Hossam Amer , Sudhir Mudur , Weiwei Zhang , Yang Liu , Walid Ahmed

Knowledge Distillation (KD) has been used in image classification for model compression. However, rare studies apply this technology on single-stage object detectors. Focal loss shows that the accumulated errors of easily-classified samples…

Computer Vision and Pattern Recognition · Computer Science 2019-01-15 Shitao Tang , Litong Feng , Wenqi Shao , Zhanghui Kuang , Wei Zhang , Yimin Chen

We propose a simple yet effective method to compress an RNN-Transducer (RNN-T) through the well-known knowledge distillation paradigm. We show that the transducer's encoder outputs naturally have a high entropy and contain rich information…

Computation and Language · Computer Science 2021-06-16 Rupak Vignesh Swaminathan , Brian King , Grant P. Strimel , Jasha Droppo , Athanasios Mouchtaris

Dataset distillation compresses a large training set into a small synthetic set that preserves downstream training utility. While most existing methods target training networks from scratch, modern visual transfer learning often uses frozen…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Bincheng Peng , Guang Li , Ping Liu , Takahiro Ogawa , Miki Haseyama

The objective of Continual Test-time Domain Adaptation (CTDA) is to gradually adapt a pre-trained model to a sequence of target domains without accessing the source data. This paper proposes a Dynamic Sample Selection (DSS) method for CTDA.…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Yanshuo Wang , Jie Hong , Ali Cheraghian , Shafin Rahman , David Ahmedt-Aristizabal , Lars Petersson , Mehrtash Harandi

Transformers recently are adapted from the community of natural language processing as a promising substitute of convolution-based neural networks for visual learning tasks. However, its supremacy degenerates given an insufficient amount of…

Computer Vision and Pattern Recognition · Computer Science 2021-06-24 Sucheng Ren , Zhengqi Gao , Tianyu Hua , Zihui Xue , Yonglong Tian , Shengfeng He , Hang Zhao