Improving the trustworthiness of image classification models by
utilizing bounding-box annotations
- URL: http://arxiv.org/abs/2108.10131v1
- Date: Sun, 15 Aug 2021 15:09:07 GMT
- Title: Improving the trustworthiness of image classification models by
utilizing bounding-box annotations
- Authors: Dharma KC, Chicheng Zhang
- Abstract summary: We propose to optimize a training objective that incorporates bounding box information, which is available in many image classification datasets.
Preliminary experimental results show that the proposed algorithm achieves better performance in accuracy, robustness, and interpretability compared with baselines.
- Score: 16.936384403276925
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We study utilizing auxiliary information in training data to improve the
trustworthiness of machine learning models. Specifically, in the context of
image classification, we propose to optimize a training objective that
incorporates bounding box information, which is available in many image
classification datasets. Preliminary experimental results show that the
proposed algorithm achieves better performance in accuracy, robustness, and
interpretability compared with baselines.
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) - Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems [80.62854148838359]
Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate.
We use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data.
Our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples.
arXiv Detail & Related papers (2024-03-23T22:32:06Z) - Improving Image Clustering through Sample Ranking and Its Application to
remote--sensing images [14.531733039462058]
We propose a novel method by first ranking samples within each cluster based on the confidence in their belonging to the current cluster.
For ranking the samples, we developed a method for computing the likelihood of samples belonging to the current clusters based on whether they are situated in densely populated neighborhoods.
We show that our method can be effectively applied to remote-sensing images.
arXiv Detail & Related papers (2022-09-26T12:10:02Z) - Prefix Conditioning Unifies Language and Label Supervision [84.11127588805138]
We show that dataset biases negatively affect pre-training by reducing the generalizability of learned representations.
In experiments, we show that this simple technique improves the performance in zero-shot image recognition accuracy and robustness to the image-level distribution shift.
arXiv Detail & Related papers (2022-06-02T16:12:26Z) - Robust Cross-Modal Representation Learning with Progressive
Self-Distillation [7.676408770854477]
The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets.
We introduce a novel training framework based on cross-modal contrastive learning that uses progressive self-distillation and soft image-text alignments to more efficiently learn robust representations from noisy data.
arXiv Detail & Related papers (2022-04-10T03:28:18Z) - Multi-Label Image Classification with Contrastive Learning [57.47567461616912]
We show that a direct application of contrastive learning can hardly improve in multi-label cases.
We propose a novel framework for multi-label classification with contrastive learning in a fully supervised setting.
arXiv Detail & Related papers (2021-07-24T15:00:47Z) - Revisiting The Evaluation of Class Activation Mapping for
Explainability: A Novel Metric and Experimental Analysis [54.94682858474711]
Class Activation Mapping (CAM) approaches provide an effective visualization by taking weighted averages of the activation maps.
We propose a novel set of metrics to quantify explanation maps, which show better effectiveness and simplify comparisons between approaches.
arXiv Detail & Related papers (2021-04-20T21:34:24Z) - Unifying Remote Sensing Image Retrieval and Classification with Robust
Fine-tuning [3.6526118822907594]
We aim at unifying remote sensing image retrieval and classification with a new large-scale training and testing dataset, SF300.
We show that our framework systematically achieves a boost of retrieval and classification performance on nine different datasets compared to an ImageNet pretrained baseline.
arXiv Detail & Related papers (2021-02-26T11:01:30Z) - Instance Localization for Self-supervised Detection Pretraining [68.24102560821623]
We propose a new self-supervised pretext task, called instance localization.
We show that integration of bounding boxes into pretraining promotes better task alignment and architecture alignment for transfer learning.
Experimental results demonstrate that our approach yields state-of-the-art transfer learning results for object detection.
arXiv Detail & Related papers (2021-02-16T17:58:57Z) - Unsupervised machine learning via transfer learning and k-means
clustering to classify materials image data [0.0]
This paper demonstrates how to construct, use, and evaluate a high performance unsupervised machine learning system for classifying images.
We use the VGG16 convolutional neural network pre-trained on the ImageNet dataset of natural images to extract feature representations for each micrograph.
The approach achieves $99.4% pm 0.16%$ accuracy, and the resulting model can be used to classify new images without retraining.
arXiv Detail & Related papers (2020-07-16T14:36:04Z) - 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.