Learning to Discover and Detect Objects

• URL: http://arxiv.org/abs/2210.10774v1
• Date: Wed, 19 Oct 2022 17:59:55 GMT
• Title: Learning to Discover and Detect Objects
• Authors: Vladimir Fomenko, Ismail Elezi, Deva Ramanan, Laura Leal-Taix\'e, Aljo\v{s}a O\v{s}ep
• Abstract summary: We tackle the problem of novel class discovery, detection, and localization (NCDL) In this setting, we assume a source dataset with labels for objects of commonly observed classes. By training our detection network with this objective in an end-to-end manner, it learns to classify all region proposals for a large variety of classes.
• Score: 43.52208526783969
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We tackle the problem of novel class discovery, detection, and localization (NCDL). In this setting, we assume a source dataset with labels for objects of commonly observed classes. Instances of other classes need to be discovered, classified, and localized automatically based on visual similarity, without human supervision. To this end, we propose a two-stage object detection network Region-based NCDL (RNCDL), that uses a region proposal network to localize object candidates and is trained to classify each candidate, either as one of the known classes, seen in the source dataset, or one of the extended set of novel classes, with a long-tail distribution constraint on the class assignments, reflecting the natural frequency of classes in the real world. By training our detection network with this objective in an end-to-end manner, it learns to classify all region proposals for a large variety of classes, including those that are not part of the labeled object class vocabulary. Our experiments conducted using COCO and LVIS datasets reveal that our method is significantly more effective compared to multi-stage pipelines that rely on traditional clustering algorithms or use pre-extracted crops. Furthermore, we demonstrate the generality of our approach by applying our method to a large-scale Visual Genome dataset, where our network successfully learns to detect various semantic classes without explicit supervision.

Related papers

• Debiased Novel Category Discovering and Localization [40.02326438622898]
  We focus on the challenging problem of Novel Class Discovery and Localization (NCDL) We propose an Debiased Region Mining (DRM) approach that combines class-agnostic Region Proposal Network (RPN) and class-aware RPN. We conduct extensive experiments on the NCDL benchmark, and the results demonstrate that the proposed DRM approach significantly outperforms previous methods.
  arXiv  Detail & Related papers  (2024-02-29T03:09:16Z)
• Weakly Supervised Open-Vocabulary Object Detection [31.605276665964787]
  We propose a novel weakly supervised open-vocabulary object detection framework, namely WSOVOD, to extend traditional WSOD. To achieve this, we explore three vital strategies, including dataset-level feature adaptation, image-level salient object localization, and region-level vision-language alignment.
  arXiv  Detail & Related papers  (2023-12-19T18:59:53Z)
• ECEA: Extensible Co-Existing Attention for Few-Shot Object Detection [52.16237548064387]
  Few-shot object detection (FSOD) identifies objects from extremely few annotated samples. Most existing FSOD methods, recently, apply the two-stage learning paradigm, which transfers the knowledge learned from abundant base classes to assist the few-shot detectors by learning the global features. We propose an Extensible Co-Existing Attention (ECEA) module to enable the model to infer the global object according to the local parts.
  arXiv  Detail & Related papers  (2023-09-15T06:55:43Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• Clustering augmented Self-Supervised Learning: Anapplication to Land Cover Mapping [10.720852987343896]
  We introduce a new method for land cover mapping by using a clustering based pretext task for self-supervised learning. We demonstrate the effectiveness of the method on two societally relevant applications.
  arXiv  Detail & Related papers  (2021-08-16T19:35:43Z)
• Learning Open-World Object Proposals without Learning to Classify [110.30191531975804]
  We propose a classification-free Object Localization Network (OLN) which estimates the objectness of each region purely by how well the location and shape of a region overlaps with any ground-truth object. This simple strategy learns generalizable objectness and outperforms existing proposals on cross-category generalization.
  arXiv  Detail & Related papers  (2021-08-15T14:36:02Z)
• Distribution Alignment: A Unified Framework for Long-tail Visual Recognition [52.36728157779307]
  We propose a unified distribution alignment strategy for long-tail visual recognition. We then introduce a generalized re-weight method in the two-stage learning to balance the class prior. Our approach achieves the state-of-the-art results across all four recognition tasks with a simple and unified framework.
  arXiv  Detail & Related papers  (2021-03-30T14:09:53Z)
• Region Comparison Network for Interpretable Few-shot Image Classification [97.97902360117368]
  Few-shot image classification has been proposed to effectively use only a limited number of labeled examples to train models for new classes. We propose a metric learning based method named Region Comparison Network (RCN), which is able to reveal how few-shot learning works. We also present a new way to generalize the interpretability from the level of tasks to categories.
  arXiv  Detail & Related papers  (2020-09-08T07:29:05Z)

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.