Multiple instance active learning for object detection

• URL: http://arxiv.org/abs/2104.02324v1
• Date: Tue, 6 Apr 2021 07:03:38 GMT
• Title: Multiple instance active learning for object detection
• Authors: Tianning Yuan (1), Fang Wan (1), Mengying Fu (1), Jianzhuang Liu (2), Songcen Xu (2), Xiangyang Ji (3), Qixiang Ye (1) ((1) University of Chinese Academy of Sciences, Beijing, China, (2) Noah's Ark Lab, Huawei Technologies, Shenzhen, China, (3) Tsinghua University, Beijing, China)
• Abstract summary: Multiple Instance Active Object Detection (MI-AOD) is an instance-level active learning method for object detection. MI-AOD treats unlabeled images as instance bags and feature anchors in images as instances. MI-AOD outperforms state-of-the-art methods with significant margins.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the substantial progress of active learning for image recognition, there still lacks an instance-level active learning method specified for object detection. In this paper, we propose Multiple Instance Active Object Detection (MI-AOD), to select the most informative images for detector training by observing instance-level uncertainty. MI-AOD defines an instance uncertainty learning module, which leverages the discrepancy of two adversarial instance classifiers trained on the labeled set to predict instance uncertainty of the unlabeled set. MI-AOD treats unlabeled images as instance bags and feature anchors in images as instances, and estimates the image uncertainty by re-weighting instances in a multiple instance learning (MIL) fashion. Iterative instance uncertainty learning and re-weighting facilitate suppressing noisy instances, toward bridging the gap between instance uncertainty and image-level uncertainty. Experiments validate that MI-AOD sets a solid baseline for instance-level active learning. On commonly used object detection datasets, MI-AOD outperforms state-of-the-art methods with significant margins, particularly when the labeled sets are small. Code is available at https://github.com/yuantn/MI-AOD.

Related papers

• Classification Committee for Active Deep Object Detection [24.74839931613233]
  We propose a classification committee for active deep object detection method. The committee selects the most informative images according to their uncertainty values. We show that our method outperforms the state-of-the-art active learning methods.
  arXiv  Detail & Related papers  (2023-08-16T16:31:36Z)
• Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection via Negative Deterministic Information [54.35679298764169]
  Weakly supervised object detection (WSOD) is a challenging task, in which image-level labels are used to train an object detector. This paper focuses on identifying and fully exploiting the deterministic information in WSOD. We propose a negative deterministic information (NDI) based method for improving WSOD, namely NDI-WSOD.
  arXiv  Detail & Related papers  (2022-04-21T12:55:27Z)
• SIOD: Single Instance Annotated Per Category Per Image for Object Detection [67.64774488115299]
  We propose the Single Instance annotated Object Detection (SIOD), requiring only one instance annotation for each existing category in an image. Degraded from inter-task (WSOD) or inter-image (SSOD) discrepancies to the intra-image discrepancy, SIOD provides more reliable and rich prior knowledge for mining the rest of unlabeled instances. Under the SIOD setting, we propose a simple yet effective framework, termed Dual-Mining (DMiner), which consists of a Similarity-based Pseudo Label Generating module (SPLG) and a Pixel-level Group Contrastive Learning module (PGCL)
  arXiv  Detail & Related papers  (2022-03-29T08:49:51Z)
• Learning to Detect Instance-level Salient Objects Using Complementary Image Labels [55.049347205603304]
  We present the first weakly-supervised approach to the salient instance detection problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids.
  arXiv  Detail & Related papers  (2021-11-19T10:15:22Z)
• Discovery-and-Selection: Towards Optimal Multiple Instance Learning for Weakly Supervised Object Detection [86.86602297364826]
  We propose a discoveryand-selection approach fused with multiple instance learning (DS-MIL) Our proposed DS-MIL approach can consistently improve the baselines, reporting state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-10-18T07:06:57Z)
• Reliable Shot Identification for Complex Event Detection via Visual-Semantic Embedding [72.9370352430965]
  We propose a visual-semantic guided loss method for event detection in videos. Motivated by curriculum learning, we introduce a negative elastic regularization term to start training the classifier with instances of high reliability. An alternative optimization algorithm is developed to solve the proposed challenging non-net regularization problem.
  arXiv  Detail & Related papers  (2021-10-12T11:46:56Z)
• Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos [82.02074241700728]
  In this paper, we present a prohibitive-level action recognition model that is trained with only video-frame labels. Our method per person detectors have been trained on large image datasets within Multiple Instance Learning framework. We show how we can apply our method in cases where the standard Multiple Instance Learning assumption, that each bag contains at least one instance with the specified label, is invalid.
  arXiv  Detail & Related papers  (2020-07-21T10:45:05Z)
• Object Instance Mining for Weakly Supervised Object Detection [24.021995037282394]
  This paper introduces an end-to-end object instance mining (OIM) framework for weakly supervised object detection. OIM attempts to detect all possible object instances existing in each image by introducing information propagation on the spatial and appearance graphs. During the iterative learning process, the less discriminative object instances from the same class can be gradually detected and utilized for training.
  arXiv  Detail & Related papers  (2020-02-04T02:11:39Z)

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.