Realistic Model Selection for Weakly Supervised Object Localization
- URL: http://arxiv.org/abs/2404.10034v1
- Date: Mon, 15 Apr 2024 17:25:21 GMT
- Title: Realistic Model Selection for Weakly Supervised Object Localization
- Authors: Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli, Eric Granger,
- Abstract summary: We introduce a new Weakly Supervised Object localization protocol that provides a localization signal without the need for manual bbox annotations.
Our results show that our noisy boxes allow selecting models with performance close to those selected using ground truth boxes, and better than models selected using only image-class labels.
- Score: 13.412674368913747
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Weakly Supervised Object Localization (WSOL) allows for training deep learning models for classification and localization, using only global class-level labels. The lack of bounding box (bbox) supervision during training represents a considerable challenge for hyper-parameter search and model selection. Earlier WSOL works implicitly observed localization performance over a test set which leads to biased performance evaluation. More recently, a better WSOL protocol has been proposed, where a validation set with bbox annotations is held out for model selection. Although it does not rely on the test set, this protocol is unrealistic since bboxes are not available in real-world applications, and when available, it is better to use them directly to fit model weights. Our initial empirical analysis shows that the localization performance of a model declines significantly when using only image-class labels for model selection (compared to using bounding-box annotations). This suggests that adding bounding-box labels is preferable for selecting the best model for localization. In this paper, we introduce a new WSOL validation protocol that provides a localization signal without the need for manual bbox annotations. In particular, we leverage noisy pseudo boxes from an off-the-shelf ROI proposal generator such as Selective-Search, CLIP, and RPN pretrained models for model selection. Our experimental results with several WSOL methods on ILSVRC and CUB-200-2011 datasets show that our noisy boxes allow selecting models with performance close to those selected using ground truth boxes, and better than models selected using only image-class labels.
Related papers
- SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation [55.87169702896249]
Unsupervised Domain Adaptation (DA) consists of adapting a model trained on a labeled source domain to perform well on an unlabeled target domain with some data distribution shift.
We propose a framework to evaluate DA methods and present a fair evaluation of existing shallow algorithms, including reweighting, mapping, and subspace alignment.
Our benchmark highlights the importance of realistic validation and provides practical guidance for real-life applications.
arXiv Detail & Related papers (2024-07-16T12:52:29Z) - Semi-supervised 3D Object Detection with Proficient Teachers [114.54835359657707]
Dominated point cloud-based 3D object detectors in autonomous driving scenarios rely heavily on the huge amount of accurately labeled samples.
Pseudo-Labeling methodology is commonly used for SSL frameworks, however, the low-quality predictions from the teacher model have seriously limited its performance.
We propose a new Pseudo-Labeling framework for semi-supervised 3D object detection, by enhancing the teacher model to a proficient one with several necessary designs.
arXiv Detail & Related papers (2022-07-26T04:54:03Z) - Cost-Effective Online Contextual Model Selection [14.094350329970537]
We formulate this task as an online contextual active model selection problem, where at each round the learner receives an unlabeled data point along with a context.
The goal is to output the best model for any given context without obtaining an excessive amount of labels.
We propose a contextual active model selection algorithm (CAMS), which relies on a novel uncertainty sampling query criterion defined on a given policy class for adaptive model selection.
arXiv Detail & Related papers (2022-07-13T08:22:22Z) - Dynamic Label Assignment for Object Detection by Combining Predicted and
Anchor IoUs [20.41563386339572]
We introduce a simple and effective approach to perform label assignment dynamically based on the training status with predictions.
Our approach shows improvements in the performance of the detection models with the adaptive label assignment algorithm.
arXiv Detail & Related papers (2022-01-23T23:14:07Z) - A linearized framework and a new benchmark for model selection for
fine-tuning [112.20527122513668]
Fine-tuning from a collection of models pre-trained on different domains is emerging as a technique to improve test accuracy in the low-data regime.
We introduce two new baselines for model selection -- Label-Gradient and Label-Feature Correlation.
Our benchmark highlights accuracy gain with model zoo compared to fine-tuning Imagenet models.
arXiv Detail & Related papers (2021-01-29T21:57:15Z) - Evaluation for Weakly Supervised Object Localization: Protocol, Metrics,
and Datasets [65.73451960585571]
We argue that weakly-supervised object localization (WSOL) task is ill-posed with only image-level labels.
We propose a new evaluation protocol where full supervision is limited to only a small held-out set not overlapping with the test set.
arXiv Detail & Related papers (2020-07-08T15:09:16Z) - Multi-label learning for dynamic model type recommendation [13.304462985219237]
We propose a problem-independent dynamic base-classifier model recommendation for the online local pool (OLP) technique.
Our proposed framework builds a multi-label meta-classifier responsible for recommending a set of relevant model types.
Experimental results show that different data distributions favored different model types on a local scope.
arXiv Detail & Related papers (2020-04-01T16:42:12Z) - Pairwise Similarity Knowledge Transfer for Weakly Supervised Object
Localization [53.99850033746663]
We study the problem of learning localization model on target classes with weakly supervised image labels.
In this work, we argue that learning only an objectness function is a weak form of knowledge transfer.
Experiments on the COCO and ILSVRC 2013 detection datasets show that the performance of the localization model improves significantly with the inclusion of pairwise similarity function.
arXiv Detail & Related papers (2020-03-18T17:53:33Z) - Evaluating Weakly Supervised Object Localization Methods Right [65.73451960585571]
We argue that weakly-supervised object localization (WSOL) task is ill-posed with only image-level labels.
We propose a new evaluation protocol where full supervision is limited to only a small held-out set not overlapping with the test set.
arXiv Detail & Related papers (2020-01-21T10:50:06Z)
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.