Empirical Performance Analysis of Conventional Deep Learning Models for Recognition of Objects in 2-D Images

• URL: http://arxiv.org/abs/2011.06639v1
• Date: Thu, 12 Nov 2020 20:14:03 GMT
• Title: Empirical Performance Analysis of Conventional Deep Learning Models for Recognition of Objects in 2-D Images
• Authors: Sangeeta Satish Rao, Nikunj Phutela, V R Badri Prasad
• Abstract summary: We have varied parameters like learning rate, filter size, the number of hidden layers, stride size and the activation function among others to analyze the performance of the model. The model classifies images into 3 categories, namely, cars, faces and aeroplanes.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Artificial Neural Networks, an essential part of Deep Learning, are derived from the structure and functionality of the human brain. It has a broad range of applications ranging from medical analysis to automated driving. Over the past few years, deep learning techniques have improved drastically - models can now be customized to a much greater extent by varying the network architecture, network parameters, among others. We have varied parameters like learning rate, filter size, the number of hidden layers, stride size and the activation function among others to analyze the performance of the model and thus produce a model with the highest performance. The model classifies images into 3 categories, namely, cars, faces and aeroplanes.

Related papers

• Beyond Accuracy: What Matters in Designing Well-Behaved Models? [53.252827682118955]
  We show that vision-language models exhibit high fairness on ImageNet-1k classification and strong robustness against domain changes. We conclude our study by introducing the QUBA score, a novel metric that ranks models across multiple dimensions of quality.
  arXiv  Detail & Related papers  (2025-03-21T12:54:18Z)
• Exploring Deep Learning Models for EEG Neural Decoding [2.0099933815960256]
  THINGS initiative provides a large EEG dataset of 46 subjects watching rapidly shown images. We test the feasibility of using this method for decoding high-level object features using recent deep learning models. We show that the linear model is not able to solve the decoding task, while almost all the deep learning models are successful.
  arXiv  Detail & Related papers  (2025-03-20T08:02:09Z)
• Multi-aspect Knowledge Distillation with Large Language Model [2.317771311576205]
  We propose a multi-aspect knowledge distillation method using Multimodal Large Language Models (MLLMs) We primarily apply our method to image classification, and to explore the potential for extending our model, such as object detection.
  arXiv  Detail & Related papers  (2025-01-23T02:45:35Z)
• Towards Scalable and Versatile Weight Space Learning [51.78426981947659]
  This paper introduces the SANE approach to weight-space learning. Our method extends the idea of hyper-representations towards sequential processing of subsets of neural network weights.
  arXiv  Detail & Related papers  (2024-06-14T13:12:07Z)
• Diffusion-Based Neural Network Weights Generation [80.89706112736353]
  D2NWG is a diffusion-based neural network weights generation technique that efficiently produces high-performing weights for transfer learning. Our method extends generative hyper-representation learning to recast the latent diffusion paradigm for neural network weights generation. Our approach is scalable to large architectures such as large language models (LLMs), overcoming the limitations of current parameter generation techniques.
  arXiv  Detail & Related papers  (2024-02-28T08:34:23Z)
• A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU [0.40498500266986387]
  Deep learning (DL) has emerged as a powerful subset of machine learning (ML) and artificial intelligence (AI) Its impact spans across various domains, including speech recognition, healthcare, autonomous vehicles, cybersecurity, predictive analytics, and more. We conduct a comprehensive survey of various deep learning models, including CNNs, Recurrent Neural Networks (RNNs), Generative Models, Deep Reinforcement Learning (DRL), and Deep Transfer Learning.
  arXiv  Detail & Related papers  (2023-05-27T13:23:21Z)
• IterMiUnet: A lightweight architecture for automatic blood vessel segmentation [10.538564380139483]
  This paper proposes IterMiUnet, a new lightweight convolution-based segmentation model. It overcomes its heavily parametrized nature by incorporating the encoder-decoder structure of MiUnet model within it. The proposed model has a lot of potential to be utilized as a tool for the early diagnosis of many diseases.
  arXiv  Detail & Related papers  (2022-08-02T14:33:14Z)
• Revisiting Facial Key Point Detection: An Efficient Approach Using Deep Neural Networks [0.0]
  We develop efficient deep learning models in terms of model size, parameters, and inference time. MobileNetV2 architecture produced the lowest RMSE and inference time. manually optimized CNN architectures performed similarly to Auto Keras tuned architecture.
  arXiv  Detail & Related papers  (2022-05-14T19:49:03Z)
• 3D Neural Scene Representations for Visuomotor Control [78.79583457239836]
  We learn models for dynamic 3D scenes purely from 2D visual observations. A dynamics model, constructed over the learned representation space, enables visuomotor control for challenging manipulation tasks.
  arXiv  Detail & Related papers  (2021-07-08T17:49:37Z)
• The FaceChannel: A Fast & Furious Deep Neural Network for Facial Expression Recognition [71.24825724518847]
  Current state-of-the-art models for automatic Facial Expression Recognition (FER) are based on very deep neural networks that are effective but rather expensive to train. We formalize the FaceChannel, a light-weight neural network that has much fewer parameters than common deep neural networks. We demonstrate how our model achieves a comparable, if not better, performance to the current state-of-the-art in FER.
  arXiv  Detail & Related papers  (2020-09-15T09:25:37Z)
• Understanding the Role of Individual Units in a Deep Neural Network [85.23117441162772]
  We present an analytic framework to systematically identify hidden units within image classification and image generation networks. First, we analyze a convolutional neural network (CNN) trained on scene classification and discover units that match a diverse set of object concepts. Second, we use a similar analytic method to analyze a generative adversarial network (GAN) model trained to generate scenes.
  arXiv  Detail & Related papers  (2020-09-10T17:59:10Z)
• Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN [52.851990439671475]
  We propose a novel end-to-end GAN architecture that can generate high-resolution 3D images. We achieve this goal by using different configurations between training and inference. Experiments on 3D thorax CT and brain MRI demonstrate that our approach outperforms state of the art in image generation.
  arXiv  Detail & Related papers  (2020-08-05T02:33:04Z)
• Deep Learning of Unified Region, Edge, and Contour Models for Automated Image Segmentation [2.0305676256390934]
  convolutional neural networks (CNNs) have gained traction in the design of automated segmentation pipelines. CNN-based models are adept at learning abstract features from raw image data, but their performance is dependent on the availability and size of suitable training datasets. In this thesis, we devise novel methodologies that address these issues and establish robust representation learning frameworks for fully-automatic semantic segmentation.
  arXiv  Detail & Related papers  (2020-06-23T02:54:55Z)
• Multi-task pre-training of deep neural networks for digital pathology [8.74883469030132]
  We first assemble and transform many digital pathology datasets into a pool of 22 classification tasks and almost 900k images. We show that our models used as feature extractors either improve significantly over ImageNet pre-trained models or provide comparable performance.
  arXiv  Detail & Related papers  (2020-05-05T08:50:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.