Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks

• URL: http://arxiv.org/abs/2309.03874v1
• Date: Thu, 7 Sep 2023 17:36:02 GMT
• Title: Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks
• Authors: Eyal Gomel, Tal Shaharabany and Lior Wolf
• Abstract summary: We train the detectors on top of the network output instead of the image data and apply suitable loss backpropagation. Our findings reveal a significant improvement in phrase grounding for the what is where by looking'' task.
• Score: 57.70351255180495
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: It has been established that training a box-based detector network can enhance the localization performance of weakly supervised and unsupervised methods. Moreover, we extend this understanding by demonstrating that these detectors can be utilized to improve the original network, paving the way for further advancements. To accomplish this, we train the detectors on top of the network output instead of the image data and apply suitable loss backpropagation. Our findings reveal a significant improvement in phrase grounding for the ``what is where by looking'' task, as well as various methods of unsupervised object discovery. Our code is available at https://github.com/eyalgomel/box-based-refinement.

Related papers

• Mesh-SORT: Simple and effective of location-wise tracker [0.0]
  In most tracking scenarios, objects tend to move and be lost within specific locations. We propose different strategies for tracking and association that can identify and target these regions. We present a robust strategy for dealing with lost objects, as well as a location-wise method for tracking by detection.
  arXiv  Detail & Related papers  (2023-02-28T08:47:53Z)
• Label-Efficient Object Detection via Region Proposal Network Pre-Training [58.50615557874024]
  We propose a simple pretext task that provides an effective pre-training for the region proposal network (RPN) In comparison with multi-stage detectors without RPN pre-training, our approach is able to consistently improve downstream task performance.
  arXiv  Detail & Related papers  (2022-11-16T16:28:18Z)
• Evaluating the Label Efficiency of Contrastive Self-Supervised Learning for Multi-Resolution Satellite Imagery [0.0]
  Self-supervised learning has been applied in the remote sensing domain to exploit readily-available unlabeled data. In this paper, we study self-supervised visual representation learning through the lens of label efficiency.
  arXiv  Detail & Related papers  (2022-10-13T06:54:13Z)
• W2N:Switching From Weak Supervision to Noisy Supervision for Object Detection [64.10643170523414]
  We propose a novel WSOD framework with a new paradigm that switches from weak supervision to noisy supervision (W2N) In the localization adaptation module, we propose a regularization loss to reduce the proportion of discriminative parts in original pseudo ground-truths. Our W2N outperforms all existing pure WSOD methods and transfer learning methods.
  arXiv  Detail & Related papers  (2022-07-25T12:13:48Z)
• Decoupling Makes Weakly Supervised Local Feature Better [39.17900986173409]
  We propose a decoupled describe-then-detect pipeline tailored for weakly supervised local feature learning. Within our pipeline, the detection step is decoupled from the description step and postponed until discriminative and robust descriptors are learned. In addition, we introduce a line-to-window search strategy to explicitly use the camera pose information for better descriptor learning.
  arXiv  Detail & Related papers  (2022-01-08T16:51:02Z)
• Mixed-Privacy Forgetting in Deep Networks [114.3840147070712]
  We show that the influence of a subset of the training samples can be removed from the weights of a network trained on large-scale image classification tasks. Inspired by real-world applications of forgetting techniques, we introduce a novel notion of forgetting in mixed-privacy setting. We show that our method allows forgetting without having to trade off the model accuracy.
  arXiv  Detail & Related papers  (2020-12-24T19:34:56Z)
• Self-supervised Segmentation via Background Inpainting [96.10971980098196]
  We introduce a self-supervised detection and segmentation approach that can work with single images captured by a potentially moving camera. We exploit a self-supervised loss function that we exploit to train a proposal-based segmentation network. We apply our method to human detection and segmentation in images that visually depart from those of standard benchmarks and outperform existing self-supervised methods.
  arXiv  Detail & Related papers  (2020-11-11T08:34:40Z)
• Unsupervised Metric Relocalization Using Transform Consistency Loss [66.19479868638925]
  Training networks to perform metric relocalization traditionally requires accurate image correspondences. We propose a self-supervised solution, which exploits a key insight: localizing a query image within a map should yield the same absolute pose, regardless of the reference image used for registration. We evaluate our framework on synthetic and real-world data, showing our approach outperforms other supervised methods when a limited amount of ground-truth information is available.
  arXiv  Detail & Related papers  (2020-11-01T19:24:27Z)
• Modification method for single-stage object detectors that allows to exploit the temporal behaviour of a scene to improve detection accuracy [0.0]
  A modified neural network is more prone to detect hidden objects with more confidence than an unmodified one. A weakly supervised training method is proposed, which allows for training a modified network without requiring any additional annotated data.
  arXiv  Detail & Related papers  (2020-09-03T12:38:55Z)

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.