We provide visualizations of individual neurons of a deep image recognition network during the temporal process of transfer learning. These visualizations qualitatively demonstrate various novel properties of the transfer learning process regarding the speed and characteristics of adaptation, neuron reuse, spatial scale of the represented image features, and behavior of transfer learning to small data. We publish the large-scale dataset that we have created for the purposes of this analysis.
Many research efforts have been committed to unsupervised domain adaptation (DA) problems that transfer knowledge learned from a labeled source domain to an unlabeled target domain. Various DA methods have achieved remarkable results recently in terms of predicting ability, which implies the effectiveness of the aforementioned knowledge transferring. However, state-of-the-art methods rarely probe deeper into the transferred mechanism, leaving the true essence of such knowledge obscure. Recognizing its importance in the adaptation process, we propose an interpretive model of unsupervised domain…
Recently vision transformers (ViT) have been applied successfully for various tasks in computer vision. However, important questions such as why they work or how they behave still remain largely unknown. In this paper, we propose an effective visualization technique, to assist us in exposing the information carried in neurons and feature embeddings across the ViT's layers. Our approach departs from the computational process of ViTs with a focus on visualizing the local and global information in input images and the latent feature embeddings at multiple levels. Visualizations at the input and e…
Seoul National University（首尔国立大学）；Hanyang University（汉阳大学）；NAVER Corp（NAVER公司）
An activation boundary for a neuron refers to a separating hyperplane that determines whether the neuron is activated or deactivated. It has been long considered in neural networks that the activations of neurons, rather than their exact output values, play the most important role in forming classification friendly partitions of the hidden feature space. However, as far as we know, this aspect of neural networks has not been considered in the literature of knowledge transfer. In this paper, we propose a knowledge transfer method via distillation of activation boundaries formed by hidden neuron…
A source model trained on source data and a target model learned through unsupervised domain adaptation (UDA) usually encode different knowledge. To understand the adaptation process, we portray their knowledge difference with image translation. Specifically, we feed a translated image and its original version to the two models respectively, formulating two branches. Through updating the translated image, we force similar outputs from the two branches. When such requirements are met, differences between the two images can compensate for and hence represent the knowledge difference between mode…
Recent advancements in language representation models such as BERT have led to a rapid improvement in numerous natural language processing tasks. However, language models usually consist of a few hundred million trainable parameters with embedding space distributed across multiple layers, thus making them challenging to be fine-tuned for a specific task or to be transferred to a new domain. To determine whether there are task-specific neurons that can be exploited for unsupervised transfer learning, we introduce a method for selecting the most important neurons to solve a specific classificati…
Deep learning is increasingly used in decision-making tasks. However, understanding how neural networks produce final predictions remains a fundamental challenge. Existing work on interpreting neural network predictions for images often focuses on explaining predictions for single images or neurons. As predictions are often computed from millions of weights that are optimized over millions of images, such explanations can easily miss a bigger picture. We present Summit, an interactive system that scalably and systematically summarizes and visualizes what features a deep learning model has lear…
Purpose: We present image classifiers based on Dense Convolutional Networks and transfer learning to classify chest X-ray images according to three labels: COVID-19, pneumonia and normal. Methods: We fine-tuned neural networks pretrained on ImageNet and applied a twice transfer learning approach, using NIH ChestX-ray14 dataset as an intermediate step. We also suggested a novelty called output neuron keeping, which changes the twice transfer learning technique. In order to clarify the modus operandi of the models, we used Layer-wise Relevance Propagation (LRP) to generate heatmaps. Results: We …
On the Adversarial Vulnerabilities of Transfer Learning in Remote Sensing
School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电子与电气工程学院）；Computer Vision Laboratory (CVL) at the Department of Electrical Engineering (ISY), Linköping University（林雪平大学电子工程系计算机视觉实验室）
Transfer learning is a popular practice in deep neural networks, but fine-tuning of large number of parameters is a hard task due to the complex wiring of neurons between splitting layers and imbalance distributions of data in pretrained and transferred domains. The reconstruction of the original wiring for the target domain is a heavy burden due to the size of interconnections across neurons. We propose a distributed scheme that tunes the convolutional filters individually while backpropagates them jointly by means of basic probability assignment. Some of the most recent advances in evidence …
Australian National University（澳大利亚国立大学）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织Data61）；Microsoft Research（微软研究院）
Although 3D Convolutional Neural Networks (CNNs) are essential for most learning based applications involving dense 3D data, their applicability is limited due to excessive memory and computational requirements. Compressing such networks by pruning therefore becomes highly desirable. However, pruning 3D CNNs is largely unexplored possibly because of the complex nature of typical pruning algorithms that embeds pruning into an iterative optimization paradigm. In this work, we introduce a Resource Aware Neuron Pruning (RANP) algorithm that prunes 3D CNNs at initialization to high sparsity levels.…
Florida State University（佛罗里达州立大学）；University of South Carolina（南卡罗来纳大学）；Oak Ridge National Laboratory（橡树岭国家实验室）
Transfer learning for partial differential equations (PDEs) is to develop a pre-trained neural network that can be used to solve a wide class of PDEs. Existing transfer learning approaches require much information of the target PDEs such as its formulation and/or data of its solution for pre-training. In this work, we propose to construct transferable neural feature spaces from purely function approximation perspectives without using PDE information. The construction of the feature space involves re-parameterization of the hidden neurons and uses auxiliary functions to tune the resulting featu…
Institute of Technologies and Management of Digital Transformation（数字化转型技术与管理研究所）；Institute of Information Management in Mechanical Engineering（机械工程信息管理研究所）
The need for more transparency of the decision-making processes in artificial neural networks steadily increases driven by their applications in safety critical and ethically challenging domains such as autonomous driving or medical diagnostics. We address today's lack of transparency of neural networks and shed light on the roles of single neurons and groups of neurons within the network fulfilling a learned task. Inspired by research in the field of neuroscience, we characterize the learned representations by activation patterns and network ablations, revealing functional neuron populations …
Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons
Nanjing University of Science and Technology（南京理工大学）；National University of Singapore（新加坡国立大学）；Harbin Institute of Technology（哈尔滨工业大学）；Nanjing University（南京大学）
Despite deep neural networks have demonstrated extraordinary power in various applications, their superior performances are at expense of high storage and computational costs. Consequently, the acceleration and compression of neural networks have attracted much attention recently. Knowledge Transfer (KT), which aims at training a smaller student network by transferring knowledge from a larger teacher model, is one of the popular solutions. In this paper, we propose a novel knowledge transfer method by treating it as a distribution matching problem. Particularly, we match the distributions of n…
Hong Kong University of Science and Technology（香港科技大学）；Microsoft Research Asia（微软亚洲研究院）
Deep convolutional neural networks (CNNs) have achieved remarkable success in various fields. However, training an excellent CNN is practically a trial-and-error process that consumes a tremendous amount of time and computer resources. To accelerate the training process and reduce the number of trials, experts need to understand what has occurred in the training process and why the resulting CNN behaves as such. However, current popular training platforms, such as TensorFlow, only provide very little and general information, such as training/validation errors, which is far from enough to serve…
DINeuro: Distilling Knowledge from 2D Natural Images via Deformable Tubular Transferring Strategy for 3D Neuron Reconstruction
School of Computer Science, The University of Sydney（悉尼大学计算机学院）；SEU-ALLEN Joint Center, Institute for Brain and Intelligence, Southeast University（东南大学SEU-ALLEN联合中心）；Harvard Medical School（哈佛医学院）；Brigham and Women’s Hospital（布莱根妇女医院）
Technical University of Denmark（丹麦技术大学）；Terma A/S（Terma公司）
Convolutional Neural Networks (Convnets) have achieved good results in a range of computer vision tasks the recent years. Though given a lot of attention, visualizing the learned representations to interpret Convnets, still remains a challenging task. The high dimensionality of internal representations and the high abstractions of deep layers are the main challenges when visualizing Convnet functionality. We present in this paper a technique based on clustering internal Convnet representations with a Dirichlet Process Gaussian Mixture Model, for visualization of learned representations in Conv…
University of Exeter（埃克塞特大学）；Aalto University（阿尔托大学）；MarkableAI（MarkableAI公司）
Recently, data-driven deep saliency models have achieved high performance and have outperformed classical saliency models, as demonstrated by results on datasets such as the MIT300 and SALICON. Yet, there remains a large gap between the performance of these models and the inter-human baseline. Some outstanding questions include what have these models learned, how and where they fail, and how they can be improved. This article attempts to answer these questions by analyzing the representations learned by individual neurons located at the intermediate layers of deep saliency models. To this end,…
Mirror neurons have been observed in the primary motor cortex of primate species, in particular in humans and monkeys. A mirror neuron fires when a person performs a certain action, and also when he observes the same action being performed by another person. A crucial step towards building fully autonomous intelligent systems with human-like learning abilities is the capability in modeling the mirror neuron. On one hand, the abundance of egocentric cameras in the past few years has offered the opportunity to study a lot of vision problems from the first-person perspective. A great deal of inte…
Falling of elderly people who are staying alone at home leads to health risks. If they are not attended immediately even it may lead to fatal danger to their life. In this paper a novel computer vision-based system for smart monitoring of elderly people using Series Convolutional Neural Network (SCNN) with transfer learning is proposed. When CNN is trained by the frames of the videos directly, it learns from all pixels including the background pixels. Generally, the background in a video does not contribute anything in identifying the action and actually it will mislead the action classificati…
We present Smooth Grad-CAM++, a technique which combines two recent techniques: SMOOTHGRAD and Grad-CAM++. Smooth Grad-CAM++ has the capability of either visualizing a layer, subset of feature maps, or subset of neurons within a feature map at each instance. We experimented with few images, and we discovered that Smooth Grad-CAM++ produced more visually sharp maps with larger number of salient pixels highlighted in the given input images when compared with other methods. Smooth Grad-CAM++ will give insight into what our deep CNN models (including models trained on medical scan or imagery) lear…
Hanoi University of Science and Technology（河内理工大学）；University of Aizu（会津大学）；Eastern International University（东方国际大学）
Recently, style transfer is a research area that attracts a lot of attention, which transfers the style of an image onto a content target. Extensive research on style transfer has aimed at speeding up processing or generating high-quality stylized images. Most approaches only produce an output from a content and style image pair, while a few others use complex architectures and can only produce a certain number of outputs. In this paper, we propose a simple method for representing style features in many ways called Deep Feature Rotation (DFR), while not only producing diverse outputs but also …
Universal style transfer aims to transfer arbitrary visual styles to content images. Existing feed-forward based methods, while enjoying the inference efficiency, are mainly limited by inability of generalizing to unseen styles or compromised visual quality. In this paper, we present a simple yet effective method that tackles these limitations without training on any pre-defined styles. The key ingredient of our method is a pair of feature transforms, whitening and coloring, that are embedded to an image reconstruction network. The whitening and coloring transforms reflect a direct matching of…
Boosting 3D Neuron Segmentation with 2D Vision Transformer Pre-trained on Natural Images
School of Computer Science, The University of Sydney（悉尼大学计算机科学学院）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织Data61）；SEU-ALLEN Joint Center, Institute for Brain and Intelligence, Southeast University（东南大学SEU-ALLEN联合中心脑与智能研究院）
We present an automated method to track and identify neurons in C. elegans, called "fast Deep Learning Correspondence" or fDLC, based on the transformer network architecture. The model is trained once on empirically derived synthetic data and then predicts neural correspondence across held-out real animals via transfer learning. The same pre-trained model both tracks neurons across time and identifies corresponding neurons across individuals. Performance is evaluated against hand-annotated datasets, including NeuroPAL [1]. Using only position information, the method achieves 80.0% accuracy at …
