English
Related papers

Related papers: Training Compute-Optimal Vision Transformers for B…

200 papers

In human-level NLP tasks, such as predicting mental health, personality, or demographics, the number of observations is often smaller than the standard 768+ hidden state sizes of each layer within modern transformer-based language models,…

Computation and Language · Computer Science 2023-06-05 Adithya V Ganesan , Matthew Matero , Aravind Reddy Ravula , Huy Vu , H. Andrew Schwartz

We developed a tool for visualizing and analyzing large pre-trained vision models by mapping them onto the brain, thus exposing their hidden inside. Our innovation arises from a surprising usage of brain encoding: predicting brain fMRI…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Huzheng Yang , James Gee , Jianbo Shi

Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention score calculations. However, streaming speech recognition…

Machine Learning · Computer Science 2024-01-22 Yang Li , Liangzhen Lai , Yuan Shangguan , Forrest N. Iandola , Zhaoheng Ni , Ernie Chang , Yangyang Shi , Vikas Chandra

Vision Transformers trained only on image classification routinely transfer to tasks that demand spatial understanding, yet they receive no spatial supervision during pretraining. We ask where and how robustly such structure is encoded.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Jainum Sanghavi

Learned image compression has achieved great success due to its excellent modeling capacity, but seldom further considers the Rate-Distortion Optimization (RDO) of each input image. To explore this potential in the learned codec, we make…

Image and Video Processing · Electrical Eng. & Systems 2022-03-31 Dezhao Wang , Wenhan Yang , Yueyu Hu , Jiaying Liu

The release of large datasets and developments in AI have led to dramatic improvements in decoding methods that reconstruct seen images from human brain activity. We evaluate the prospect of further improving recent decoding methods by…

Neurons and Cognition · Quantitative Biology 2023-12-14 Reese Kneeland , Jordyn Ojeda , Ghislain St-Yves , Thomas Naselaris

Several studies have investigated the reasons behind the effectiveness of fine-tuning, usually through the lens of probing. However, these studies often neglect the role of the size of the dataset on which the model is fine-tuned. In this…

Computation and Language · Computer Science 2022-03-21 Houman Mehrafarin , Sara Rajaee , Mohammad Taher Pilehvar

Recent large language models (LLMs) have revealed strong abilities to understand natural language. Since most of them share the same basic structure, i.e. the transformer block, possible contributors to their success in the training process…

Computation and Language · Computer Science 2023-10-31 Changjiang Gao , Shujian Huang , Jixing Li , Jiajun Chen

Masked image modeling (MIM) pre-training for large-scale vision transformers (ViTs) has enabled promising downstream performance on top of the learned self-supervised ViT features. In this paper, we question if the \textit{extremely simple}…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Jin Gao , Shubo Lin , Shaoru Wang , Yutong Kou , Zeming Li , Liang Li , Congxuan Zhang , Xiaoqin Zhang , Yizheng Wang , Weiming Hu

Most efforts to improve the reasoning capabilities of large language models (LLMs) involve either scaling the number of parameters and the size of training data, or scaling inference computation by letting models generate complex chains of…

Machine Learning · Computer Science 2025-10-10 Yeskendir Koishekenov , Aldo Lipani , Nicola Cancedda

Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Daquan Zhou , Bingyi Kang , Xiaojie Jin , Linjie Yang , Xiaochen Lian , Zihang Jiang , Qibin Hou , Jiashi Feng

We present unit scaling, a paradigm for designing deep learning models that simplifies the use of low-precision number formats. Training in FP16 or the recently proposed FP8 formats offers substantial efficiency gains, but can lack…

Machine Learning · Computer Science 2023-06-01 Charlie Blake , Douglas Orr , Carlo Luschi

This paper investigates the performance of the Contrastive Language-Image Pre-training (CLIP) when scaled down to limited computation budgets. We explore CLIP along three dimensions: data, architecture, and training strategies. With regards…

Computer Vision and Pattern Recognition · Computer Science 2024-04-17 Zichao Li , Cihang Xie , Ekin Dogus Cubuk

Recent progress in encoder-decoder neural network architecture design has led to significant performance improvements in a wide range of medical image segmentation tasks. However, state-of-the-art networks for a given task may be too…

Image and Video Processing · Electrical Eng. & Systems 2021-12-22 Tariq M. Khan , Syed S. Naqvi , Erik Meijering

Multi-bit spiking neural networks (SNNs) have recently become a heated research spot, pursuing energy-efficient and high-accurate AI. However, with more bits involved, the associated memory and computation demands escalate to the point…

Neural and Evolutionary Computing · Computer Science 2025-12-02 Xingting Yao , Qinghao Hu , Fei Zhou , Tielong Liu , Gang Li , Peisong Wang , Jian Cheng

Fine-tuning pre-trained transformers is a powerful technique for enhancing the performance of base models on specific tasks. From early applications in models like BERT to fine-tuning Large Language Models (LLMs), this approach has been…

Computation and Language · Computer Science 2025-02-25 Suneel Nadipalli

Multi-encoding implies encoding the same content in multiple spatial resolutions and multiple bitrates. This work evaluates the encoder analysis correlations across 2160p, 1080p, and 540p encodings of the same video for conventional ABR…

Multimedia · Computer Science 2023-01-31 Vignesh V Menon

When it comes to the classification of brain signals in real-life applications, the training and the prediction data are often described by different distributions. Furthermore, diverse data sets, e.g., recorded from various subjects or…

End-to-end trainable models have reached the performance of traditional handcrafted compression techniques on videos and images. Since the parameters of these models are learned over large training sets, they are not optimal for any given…

Image and Video Processing · Electrical Eng. & Systems 2022-10-12 Oussama Jourairi , Muhammet Balcilar , Anne Lambert , François Schnitzler

Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism,…

Computer Vision and Pattern Recognition · Computer Science 2024-05-06 Lorenzo Papa , Paolo Russo , Irene Amerini , Luping Zhou