English
Related papers

Related papers: TrAct: Making First-layer Pre-Activations Trainabl…

200 papers

Recent works have empirically analyzed in-context learning and shown that transformers trained on synthetic linear regression tasks can learn to implement ridge regression, which is the Bayes-optimal predictor, given sufficient capacity…

Machine Learning · Computer Science 2023-07-10 Arvind Mahankali , Tatsunori B. Hashimoto , Tengyu Ma

Task arithmetic has recently emerged as a cost-effective and scalable approach to edit pre-trained models directly in weight space: By adding the fine-tuned weights of different tasks, the model's performance can be improved on these tasks,…

Machine Learning · Computer Science 2023-11-22 Guillermo Ortiz-Jimenez , Alessandro Favero , Pascal Frossard

The first layer of a deep CNN backbone applies filters to an image to extract the basic features available to later layers. During training, some filters may go inactive, mean ing all weights in the filter approach zero. An inactive fil ter…

Computer Vision and Pattern Recognition · Computer Science 2023-12-06 Aman Bhatta , Domingo Mery , Haiyu Wu , Kevin W. Bowyer

To utilize pre-trained neural networks on edge and mobile devices, we often require efficient adaptation to user-specific runtime data distributions while operating under limited compute and memory resources. On-device retraining with a…

Machine Learning · Computer Science 2026-03-04 Irene Tenison , Soumyajit Chatterjee , Fahim Kawsar , Mohammad Malekzadeh

Modern neural networks are often quite wide, causing large memory and computation costs. It is thus of great interest to train a narrower network. However, training narrow neural nets remains a challenging task. We ask two theoretical…

Machine Learning · Computer Science 2022-10-24 Jiawei Zhang , Yushun Zhang , Mingyi Hong , Ruoyu Sun , Zhi-Quan Luo

The gradients used to train neural networks are typically computed using backpropagation. While an efficient way to obtain exact gradients, backpropagation is computationally expensive, hinders parallelization, and is biologically…

Machine Learning · Computer Science 2026-01-14 Katharina Flügel , Daniel Coquelin , Marie Weiel , Charlotte Debus , Achim Streit , Markus Götz

Deep-neural-network-based image reconstruction has demonstrated promising performance in medical imaging for under-sampled and low-dose scenarios. However, it requires large amount of memory and extensive time for the training. It is…

Computer Vision and Pattern Recognition · Computer Science 2019-06-12 Dufan Wu , Kyungsang Kim , Quanzheng Li

We present a neat yet effective recursive operation on vision transformers that can improve parameter utilization without involving additional parameters. This is achieved by sharing weights across the depth of transformer networks. The…

Computer Vision and Pattern Recognition · Computer Science 2022-07-27 Zhiqiang Shen , Zechun Liu , Eric Xing

Deep learning sometimes appears to work in unexpected ways. In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate model of a trained neural network consisting of a sequence of…

Machine Learning · Computer Science 2024-11-04 Alan Jeffares , Alicia Curth , Mihaela van der Schaar

In this paper, we will show an unprecedented method to accelerate training and improve performance, which called random gradient (RG). This method can be easier to the training of any model without extra calculation cost, we use Image…

Machine Learning · Computer Science 2018-08-22 Jiakai Wei

This work targets to merge various Vision Transformers (ViTs) trained on different tasks (i.e., datasets with different object categories) or domains (i.e., datasets with the same categories but different environments) into one unified…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Peng Ye , Chenyu Huang , Mingzhu Shen , Tao Chen , Yongqi Huang , Yuning Zhang , Wanli Ouyang

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extragradient), limiting SGD…

Machine Learning · Computer Science 2022-03-23 Amirkeivan Mohtashami , Martin Jaggi , Sebastian U. Stich

Deep Neural Networks (DNNs) are extensively employed in safety-critical applications where ensuring hardware reliability is a primary concern. To enhance the reliability of DNNs against hardware faults, activation restriction techniques…

Machine Learning · Computer Science 2026-03-10 Seyedhamidreza Mousavi , Mohammad Hasan Ahmadilivani , Jaan Raik , Maksim Jenihhin , Masoud Daneshtalab

Training deep neural networks for scientific computing remains computationally expensive due to the slow formation of diverse feature representations in early training stages. Recent studies identify a staircase phenomenon in training…

Numerical Analysis · Mathematics 2025-07-17 Tao Tang , Jiang Yang , Yuxiang Zhao , Quanhui Zhu

We introduce a novel framework for learning in neural networks by decomposing each neuron's weight vector into two distinct parts, $W_1$ and $W_2$, thereby modeling contrastive information directly at the neuron level. Traditional gradient…

Machine Learning · Computer Science 2025-03-19 Xi Wang

Low-rank matrix estimation is a canonical problem that finds numerous applications in signal processing, machine learning and imaging science. A popular approach in practice is to factorize the matrix into two compact low-rank factors, and…

Machine Learning · Computer Science 2021-06-16 Tian Tong , Cong Ma , Yuejie Chi

With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown. In this paper, we propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that…

Computer Vision and Pattern Recognition · Computer Science 2023-11-01 Xialei Liu , Xusheng Cao , Haori Lu , Jia-wen Xiao , Andrew D. Bagdanov , Ming-Ming Cheng

We propose a simple yet effective neural network-based framework for global illumination rendering. Recently, rendering techniques that learn neural radiance caches by minimizing the difference (i.e., residual) between the left and right…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 In-Young Cho , Jaewoong Cho

At present, the mechanisms of in-context learning in Transformers are not well understood and remain mostly an intuition. In this paper, we suggest that training Transformers on auto-regressive objectives is closely related to…

This paper proposes a GeneraLIst encoder-Decoder (GLID) pre-training method for better handling various downstream computer vision tasks. While self-supervised pre-training approaches, e.g., Masked Autoencoder, have shown success in…

Computer Vision and Pattern Recognition · Computer Science 2024-04-12 Jihao Liu , Jinliang Zheng , Yu Liu , Hongsheng Li