Look Around and Learn: Self-Training Object Detection by Exploration

• URL: http://arxiv.org/abs/2302.03566v4
• Date: Tue, 30 Jul 2024 13:18:32 GMT
• Title: Look Around and Learn: Self-Training Object Detection by Exploration
• Authors: Gianluca Scarpellini, Stefano Rosa, Pietro Morerio, Lorenzo Natale, Alessio Del Bue,
• Abstract summary: An agent learns to explore the environment using a pre-trained off-the-shelf detector to locate objects and associate pseudo-labels. By assuming that pseudo-labels for the same object must be consistent across different views, we learn the exploration policy Look Around to mine hard samples. We implement a unified benchmark of the current state-of-the-art and compare our approach with pre-existing exploration policies and perception mechanisms.
• Score: 23.620820805804616
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When an object detector is deployed in a novel setting it often experiences a drop in performance. This paper studies how an embodied agent can automatically fine-tune a pre-existing object detector while exploring and acquiring images in a new environment without relying on human intervention, i.e., a fully self-supervised approach. In our setting, an agent initially learns to explore the environment using a pre-trained off-the-shelf detector to locate objects and associate pseudo-labels. By assuming that pseudo-labels for the same object must be consistent across different views, we learn the exploration policy Look Around to mine hard samples, and we devise a novel mechanism called Disagreement Reconciliation for producing refined pseudo-labels from the consensus among observations. We implement a unified benchmark of the current state-of-the-art and compare our approach with pre-existing exploration policies and perception mechanisms. Our method is shown to outperform existing approaches, improving the object detector by 6.2% in a simulated scenario, a 3.59% advancement over other state-of-the-art methods, and by 9.97% in the real robotic test without relying on ground-truth. Code for the proposed approach and baselines are available at https://iit-pavis.github.io/Look_Around_And_Learn/.

Related papers

• Open-World Object Detection with Instance Representation Learning [1.8749305679160366]
  We propose a method to train an object detector that can both detect novel objects and extract semantically rich features in open-world conditions. Our method learns a robust and generalizable feature space, outperforming other OWOD-based feature extraction methods.
  arXiv  Detail & Related papers  (2024-09-24T13:13:34Z)
• Towards Open-World Object-based Anomaly Detection via Self-Supervised Outlier Synthesis [15.748043194987075]
  This work aims to bridge the gap by leveraging an open-world object detector and an OoD detector via virtual outlier. Our approach empowers our overall object detector architecture to learn anomaly-aware feature representations without relying on class labels. Our method establishes state-of-the-art performance on object-level anomaly detection, achieving an average recall score improvement of over 5.4% for natural images.
  arXiv  Detail & Related papers  (2024-07-22T16:16:38Z)
• Bayesian Detector Combination for Object Detection with Crowdsourced Annotations [49.43709660948812]
  Acquiring fine-grained object detection annotations in unconstrained images is time-consuming, expensive, and prone to noise. We propose a novel Bayesian Detector Combination (BDC) framework to more effectively train object detectors with noisy crowdsourced annotations. BDC is model-agnostic, requires no prior knowledge of the annotators' skill level, and seamlessly integrates with existing object detection models.
  arXiv  Detail & Related papers  (2024-07-10T18:00:54Z)
• Self-improving object detection via disagreement reconciliation [30.971936386281275]
  This paper studies how to automatically fine-tune a pre-existing object detector while exploring and acquiring images in a new environment. By assuming that pseudo-labels for the same object must be consistent across different views, we devise a novel mechanism for producing refined predictions from the consensus among observations. Our approach improves the off-the-shelf object detector by 2.66% in terms of mAP and outperforms the current state of the art without relying on ground-truth annotations.
  arXiv  Detail & Related papers  (2023-02-21T12:20:46Z)
• Interactron: Embodied Adaptive Object Detection [18.644357684104662]
  We propose Interactron, a method for adaptive object detection in an interactive setting. Our idea is to continue training during inference and adapt the model at test time without any explicit supervision via interacting with the environment.
  arXiv  Detail & Related papers  (2022-02-01T18:56:14Z)
• Robust Region Feature Synthesizer for Zero-Shot Object Detection [87.79902339984142]
  We build a novel zero-shot object detection framework that contains an Intra-class Semantic Diverging component and an Inter-class Structure Preserving component. It is the first study to carry out zero-shot object detection in remote sensing imagery.
  arXiv  Detail & Related papers  (2022-01-01T03:09:15Z)
• Robust Object Detection via Instance-Level Temporal Cycle Confusion [89.1027433760578]
  We study the effectiveness of auxiliary self-supervised tasks to improve the out-of-distribution generalization of object detectors. Inspired by the principle of maximum entropy, we introduce a novel self-supervised task, instance-level temporal cycle confusion (CycConf) For each object, the task is to find the most different object proposals in the adjacent frame in a video and then cycle back to itself for self-supervision.
  arXiv  Detail & Related papers  (2021-04-16T21:35:08Z)
• 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)
• Slender Object Detection: Diagnoses and Improvements [74.40792217534]
  In this paper, we are concerned with the detection of a particular type of objects with extreme aspect ratios, namely textbfslender objects. For a classical object detection method, a drastic drop of $18.9%$ mAP on COCO is observed, if solely evaluated on slender objects.
  arXiv  Detail & Related papers  (2020-11-17T09:39:42Z)
• Synthesizing the Unseen for Zero-shot Object Detection [72.38031440014463]
  We propose to synthesize visual features for unseen classes, so that the model learns both seen and unseen objects in the visual domain. We use a novel generative model that uses class-semantics to not only generate the features but also to discriminatively separate them.
  arXiv  Detail & Related papers  (2020-10-19T12:36:11Z)
• Semantic Curiosity for Active Visual Learning [45.75355448193764]
  We study the task of embodied interactive learning for object detection. Our goal is to learn an object detector by having an agent select what data to obtain labels for.
  arXiv  Detail & Related papers  (2020-06-16T17:59:24Z)

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.