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

• URL: http://arxiv.org/abs/2412.00770v1
• Date: Sun, 01 Dec 2024 11:21:01 GMT
• Title: Explorations in Self-Supervised Learning: Dataset Composition Testing for Object Classification
• Authors: Raynor Kirkson E. Chavez, Kyle Gabriel M. Reynoso,
• Abstract summary: We investigate the impact of sampling and pretraining using datasets with different image characteristics on the performance of self-supervised learning (SSL) models for object classification. We find that depth pretrained models are more effective on low resolution images, while RGB pretrained models perform better on higher resolution images.
• Score: 0.0
• License:
• Abstract: 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.

Related papers

• Reinforcing Pre-trained Models Using Counterfactual Images [54.26310919385808]
  This paper proposes a novel framework to reinforce classification models using language-guided generated counterfactual images. We identify model weaknesses by testing the model using the counterfactual image dataset. We employ the counterfactual images as an augmented dataset to fine-tune and reinforce the classification model.
  arXiv  Detail & Related papers  (2024-06-19T08:07:14Z)
• An evaluation of pre-trained models for feature extraction in image classification [0.0]
  This work aims to compare the performance of different pre-trained neural networks for feature extraction in image classification tasks. Our results demonstrate that the best general performance along the datasets was achieved by CLIP-ViT-B and ViT-H-14, where the CLIP-ResNet50 model had similar performance but with less variability.
  arXiv  Detail & Related papers  (2023-10-03T13:28:14Z)
• An Ensemble Model for Distorted Images in Real Scenarios [0.0]
  In this paper, we apply the object detector YOLOv7 to detect distorted images from the CDCOCO dataset. Through carefully designed optimizations, our model achieves excellent performance on the CDCOCO test set. Our denoising detection model can denoise and repair distorted images, making the model useful in a variety of real-world scenarios and environments.
  arXiv  Detail & Related papers  (2023-09-26T15:12:55Z)
• Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration [79.04007257606862]
  This paper introduces an innovative method termed 'learning from history', which dynamically generates negative samples from the target model itself. Our approach, named Model Contrastive Learning for Image Restoration (MCLIR), rejuvenates latency models as negative models, making it compatible with diverse image restoration tasks.
  arXiv  Detail & Related papers  (2023-09-12T07:50:54Z)
• The effectiveness of MAE pre-pretraining for billion-scale pretraining [65.98338857597935]
  We introduce an additional pre-pretraining stage that is simple and uses the self-supervised MAE technique to initialize the model. We measure the effectiveness of pre-pretraining on 10 different visual recognition tasks spanning image classification, video recognition, object detection, low-shot classification and zero-shot recognition.
  arXiv  Detail & Related papers  (2023-03-23T17:56:12Z)
• Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model [97.9548609175831]
  We resort to plain vision transformers with about 100 million parameters and make the first attempt to propose large vision models customized for remote sensing tasks. Specifically, to handle the large image size and objects of various orientations in RS images, we propose a new rotated varied-size window attention. Experiments on detection tasks demonstrate the superiority of our model over all state-of-the-art models, achieving 81.16% mAP on the DOTA-V1.0 dataset.
  arXiv  Detail & Related papers  (2022-08-08T09:08:40Z)
• Salient Objects in Clutter [130.63976772770368]
  This paper identifies and addresses a serious design bias of existing salient object detection (SOD) datasets. This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets. We propose a new high-quality dataset and update the previous saliency benchmark.
  arXiv  Detail & Related papers  (2021-05-07T03:49:26Z)
• Rethinking Natural Adversarial Examples for Classification Models [43.87819913022369]
  ImageNet-A is a famous dataset of natural adversarial examples. We validated the hypothesis by reducing the background influence in ImageNet-A examples with object detection techniques. Experiments showed that the object detection models with various classification models as backbones obtained much higher accuracy than their corresponding classification models.
  arXiv  Detail & Related papers  (2021-02-23T14:46:48Z)
• VinVL: Revisiting Visual Representations in Vision-Language Models [96.39332942534368]
  We develop an improved object detection model to provide object-centric representations of images. New visual features significantly improve the performance across all vision language (VL) tasks. We will release the new object detection model to public.
  arXiv  Detail & Related papers  (2021-01-02T23:35:27Z)
• Improving Learning Effectiveness For Object Detection and Classification in Cluttered Backgrounds [6.729108277517129]
  This paper develops a framework that permits to autonomously generate a training dataset in heterogeneous cluttered backgrounds. It is clear that the learning effectiveness of the proposed framework should be improved in complex and heterogeneous environments. The performance of the proposed framework is investigated through empirical tests and compared with that of the model trained with the COCO dataset.
  arXiv  Detail & Related papers  (2020-02-27T22:28:48Z)

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.