English
Related papers

Related papers: Interpreting ResNet-based CLIP via Neuron-Attentio…

200 papers

In this paper, we introduce Channel-wise recurrent convolutional neural networks (RecNets), a family of novel, compact neural network architectures for computer vision tasks inspired by recurrent neural networks (RNNs). RecNets build upon…

Machine Learning · Computer Science 2020-03-23 George Retsinas , Athena Elafrou , Georgios Goumas , Petros Maragos

The CLIP (Contrastive Language-Image Pre-training) model and its variants are becoming the de facto backbone in many applications. However, training a CLIP model from hundreds of millions of image-text pairs can be prohibitively expensive.…

Computer Vision and Pattern Recognition · Computer Science 2023-05-10 Liangliang Cao , Bowen Zhang , Chen Chen , Yinfei Yang , Xianzhi Du , Wencong Zhang , Zhiyun Lu , Yantao Zheng

Attention plays a critical role in human visual experience. Furthermore, it has recently been demonstrated that attention can also play an important role in the context of applying artificial neural networks to a variety of tasks from…

Computer Vision and Pattern Recognition · Computer Science 2017-02-14 Sergey Zagoruyko , Nikos Komodakis

Tensor decomposition methods are widely used for model compression and fast inference in convolutional neural networks (CNNs). Although many decompositions are conceivable, only CP decomposition and a few others have been applied in…

Machine Learning · Computer Science 2019-11-28 Kohei Hayashi , Taiki Yamaguchi , Yohei Sugawara , Shin-ichi Maeda

Intracranial hemorrhages in head CT scans serve as a first line tool to help specialists diagnose different types. However, their types have diverse shapes in the same type but similar confusing shape, size and location between types. To…

Image and Video Processing · Electrical Eng. & Systems 2023-12-19 Chia Shuo Chang , Tian Sheuan Chang , Jiun Lin Yan , Li Ko

Prior work has offered evidence for functional localization in the brain; different anatomical regions preferentially activate for certain types of visual input. For example, the fusiform face area preferentially activates for visual…

Machine Learning · Computer Science 2024-10-02 Cory Efird , Alex Murphy , Joel Zylberberg , Alona Fyshe

Brain decoding is a field of computational neuroscience that uses measurable brain activity to infer mental states or internal representations of perceptual inputs. Therefore, we propose a novel approach to brain decoding that also relies…

Computer Vision and Pattern Recognition · Computer Science 2023-03-23 Matteo Ferrante , Tommaso Boccato , Nicola Toschi

Skeleton extraction is a task focused on providing a simple representation of an object by extracting the skeleton from the given binary or RGB image. In recent years many attractive works in skeleton extraction have been made. But as far…

Computer Vision and Pattern Recognition · Computer Science 2022-05-25 Zixuan Huang , Yunfeng Wang , Zhiwen Chen , Xin Gao , Ruili Feng , Xiaobo Li

Self-attention has been a huge success for many downstream tasks in NLP, which led to exploration of applying self-attention to speech problems as well. The efficacy of self-attention in speech applications, however, seems not fully blown…

Computation and Language · Computer Science 2019-10-03 Kyu J. Han , Ramon Prieto , Kaixing Wu , Tao Ma

Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly…

Computation and Language · Computer Science 2017-11-22 Tao Shen , Tianyi Zhou , Guodong Long , Jing Jiang , Shirui Pan , Chengqi Zhang

Multi-head attention advances neural machine translation by working out multiple versions of attention in different subspaces, but the neglect of semantic overlapping between subspaces increases the difficulty of translation and…

Computation and Language · Computer Science 2019-09-04 Shuhao Gu , Yang Feng

CLIP models learn transferable multi-modal features via image-text contrastive learning on internet-scale data. They are widely used in zero-shot classification, multi-modal retrieval, text-to-image diffusion, and as image encoders in large…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Marc-Antoine Lavoie , Anas Mahmoud , Aldo Zaimi , Arsene Fansi Tchango , Steven L. Waslander

The brain's spatial orientation system uses different neuron ensembles to aid in environment-based navigation. Two of the ways brains encode spatial information is through head direction cells and grid cells. Brains use head direction cells…

Neural and Evolutionary Computing · Computer Science 2023-09-07 Edward C. Mitchell , Brittany Story , David Boothe , Piotr J. Franaszczuk , Vasileios Maroulas

A satisfactory understanding of information processing in spiking neural networks requires appropriate computational abstractions of neural activity. Traditionally, the neural population state vector has been the most common abstraction…

Neural and Evolutionary Computing · Computer Science 2023-06-30 Bradley H. Theilman , Felix Wang , Fred Rothganger , James B. Aimone

Large-scale vision-language pre-training has achieved promising results on downstream tasks. Existing methods highly rely on the assumption that the image-text pairs crawled from the Internet are in perfect one-to-one correspondence.…

Computer Vision and Pattern Recognition · Computer Science 2022-05-31 Yuting Gao , Jinfeng Liu , Zihan Xu , Jun Zhang , Ke Li , Rongrong Ji , Chunhua Shen

Clipping, as a current nonlinear distortion, often occurs due to the limited dynamic range of audio recorders. It degrades the speech quality and intelligibility and adversely affects the performances of speech and speaker recognitions. In…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-29 Hamidreza Baradaran Kashani , Ata Jodeiri , Mohammad Mohsen Goodarzi , Shabnam Gholamdokht Firooz

We introduce switched linear projections for expressing the activity of a neuron in a deep neural network in terms of a single linear projection in the input space. The method works by isolating the active subnetwork, a series of linear…

Machine Learning · Computer Science 2020-02-10 Lech Szymanski , Brendan McCane , Craig Atkinson

Learning to capture long-range relations is fundamental to image/video recognition. Existing CNN models generally rely on increasing depth to model such relations which is highly inefficient. In this work, we propose the "double attention…

Computer Vision and Pattern Recognition · Computer Science 2018-10-30 Yunpeng Chen , Yannis Kalantidis , Jianshu Li , Shuicheng Yan , Jiashi Feng

Deep ReLU Networks can be decomposed into a collection of linear models, each defined in a region of a partition of the input space. This paper provides three results extending this theory. First, we extend this linear decompositions to…

Machine Learning · Computer Science 2023-05-17 Mattia Jacopo Villani , Peter McBurney

Convolutional Neural Networks (CNNs) have exhibited great performance in discriminative feature learning for complex visual tasks. Besides discrimination power, interpretability is another important yet under-explored property for CNNs. One…

Computer Vision and Pattern Recognition · Computer Science 2023-12-20 Wengang Guo , Jiayi Yang , Huilin Yin , Qijun Chen , Wei Ye