Explorations in Self-Supervised Learning: Dataset Composition Testing for Object Classification

2024-12-01 · Raynor Kirkson E. Chavez, Kyle Gabriel M. Reynoso

This paper investigates the impact of sampling and pretraining using datasets with different image characteristics on the performance of self-supervised learning (SSL) models for object classification. To do this, we sample two apartment datasets from the Omnidata platform based on modality, luminosity, image size, and camera field of view and use them to pretrain a SimCLR model. The encodings generated from the pretrained model are then transferred to a supervised Resnet-50 model for object classification. Through A/B testing, we find that depth pretrained models are more effective on low resolution images, while RGB pretrained models perform better on higher resolution images. We also discover that increasing the luminosity of training images can improve the performance of models on low resolution images without negatively affecting their performance on higher resolution images.

📄 PDF Abstract BibTeX arXiv:2412.00770

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learning

Methods 이 논문이 사용한 방법론

Bitcoin Customer Service Number +1-833-534-1729 설명 없음

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Average Pooling 설명 없음

Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Kaiming Initialization 설명 없음

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…

Unsupervised multi-branch Capsule for Hyperspectral and LiDAR classification

2022-06-15 · Quanfeng Xu, Yi Tang, Yumei She

With the convenient availability of remote sensing data, how to make models to interpret complex remote sensing data attracts wide attention. In remote sensing data, hyperspectral images contain spectral information and …

Classification

Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language

2022-10-02 · Zhenlin Xu, Marc Niethammer, Colin Raffel

Deep learning models struggle with compositional generalization, i.e. the ability to recognize or generate novel combinations of observed elementary concepts. In hopes of enabling compositional generalization, various un…

Disentanglement Representation Learning

Explorations in the Speakers' Interaction Experience and Self-Assessments

2012-12-01 · COLING 2012 12 · Kristiina Jokinen

To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection

2021-09-04 · Yongri Piao, Jian Wang, Miao Zhang, Zhengxuan Ma 외

Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. Despite of the success of previous works, explorations on an effective training strategy for the saliency n…

object-detection Object Detection Salient Object Detection Weakly-supervised Learning

Canonical Capsules: Self-Supervised Capsules in Canonical Pose

2020-12-08 · NeurIPS 2021 12 · Weiwei Sun, Andrea Tagliasacchi, Boyang Deng, Sara Sabour 외

We propose a self-supervised capsule architecture for 3D point clouds. We compute capsule decompositions of objects through permutation-equivariant attention, and self-supervise the process by training with pairs of rand…

3D Point Cloud Reconstruction General Classification Object Point cloud reconstruction