Active Learning Strategies for Weakly-supervised Object Detection

• URL: http://arxiv.org/abs/2207.12112v1
• Date: Mon, 25 Jul 2022 12:22:01 GMT
• Title: Active Learning Strategies for Weakly-supervised Object Detection
• Authors: Huy V. Vo, Oriane Sim\'eoni, Spyros Gidaris, Andrei Bursuc, Patrick P\'erez and Jean Ponce
• Abstract summary: BiB is a novel active learning strategy designed specifically to address the well-documented failure modes of weakly-supervised detectors. BiB reaches 97% of the performance of fully-supervised Fast RCNN with only 10% of fully-annotated images on VOC07. On COCO, using on average 10 fully-annotated images per class, or equivalently 1% of the training set, BiB also reduces the performance gap between the weakly-supervised detector and the fully-supervised Fast RCNN by over 70%.
• Score: 34.25737761591651
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Object detectors trained with weak annotations are affordable alternatives to fully-supervised counterparts. However, there is still a significant performance gap between them. We propose to narrow this gap by fine-tuning a base pre-trained weakly-supervised detector with a few fully-annotated samples automatically selected from the training set using ``box-in-box'' (BiB), a novel active learning strategy designed specifically to address the well-documented failure modes of weakly-supervised detectors. Experiments on the VOC07 and COCO benchmarks show that BiB outperforms other active learning techniques and significantly improves the base weakly-supervised detector's performance with only a few fully-annotated images per class. BiB reaches 97% of the performance of fully-supervised Fast RCNN with only 10% of fully-annotated images on VOC07. On COCO, using on average 10 fully-annotated images per class, or equivalently 1% of the training set, BiB also reduces the performance gap (in AP) between the weakly-supervised detector and the fully-supervised Fast RCNN by over 70%, showing a good trade-off between performance and data efficiency. Our code is publicly available at https://github.com/huyvvo/BiB.

Related papers

• ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision [7.819942809508631]
  We propose ContraCluster, an unsupervised image classification method that combines clustering with the power of contrastive self-supervised learning. ContraCluster consists of three stages: (1) contrastive self-supervised pre-training (CPT), (2) contrastive prototype sampling (CPS), and (3) prototype-based semi-supervised fine-tuning (PB-SFT). We demonstrate empirically that ContraCluster achieves new state-of-the-art results for standard benchmark datasets including CIFAR-10, STL-10, and ImageNet-10.
  arXiv  Detail & Related papers  (2023-04-19T01:51:08Z)
• Box-Level Active Detection [47.41635810670186]
  We introduce a box-level active detection framework that controls a box-based budget per cycle. We propose Complementary Pseudo Active Strategy (ComPAS) to exploit both human annotations and the model intelligence. ComPAS consistently outperforms 10 competitors under 4 settings in a unified setting.
  arXiv  Detail & Related papers  (2023-03-23T08:06:10Z)
• Masked Unsupervised Self-training for Zero-shot Image Classification [98.23094305347709]
  Masked Unsupervised Self-Training (MUST) is a new approach which leverages two different and complimentary sources of supervision: pseudo-labels and raw images. MUST improves upon CLIP by a large margin and narrows the performance gap between unsupervised and supervised classification.
  arXiv  Detail & Related papers  (2022-06-07T02:03:06Z)
• Semi-Weakly Supervised Object Detection by Sampling Pseudo Ground-Truth Boxes [9.827002225566073]
  This paper introduces a weakly semi-supervised training method for object detection. It achieves state-of-the-art performance by leveraging only a small fraction of fully-labeled images with information in weakly-labeled images. In particular, our generic sampling-based learning strategy produces pseudo-ground-truth (GT) bounding box annotations in an online fashion.
  arXiv  Detail & Related papers  (2022-04-01T00:44:42Z)
• Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection [54.92703325989853]
  We propose a two-stage Activation-to-Saliency (A2S) framework that effectively generates high-quality saliency cues. No human annotations are involved in our framework during the whole training process. Our framework reports significant performance compared with existing USOD methods.
  arXiv  Detail & Related papers  (2021-12-07T11:54:06Z)
• To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection [95.21700830273221]
  Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. We propose a self-calibrated training strategy by explicitly establishing a mutual calibration loop between pseudo labels and network predictions. We prove that even a much smaller dataset with well-matched annotations can facilitate models to achieve better performance as well as generalizability.
  arXiv  Detail & Related papers  (2021-09-04T02:45:22Z)
• Towards Reducing Labeling Cost in Deep Object Detection [61.010693873330446]
  We propose a unified framework for active learning, that considers both the uncertainty and the robustness of the detector. Our method is able to pseudo-label the very confident predictions, suppressing a potential distribution drift.
  arXiv  Detail & Related papers  (2021-06-22T16:53:09Z)
• Unsupervised Class-Incremental Learning Through Confusion [0.4604003661048266]
  We introduce a novelty detection method that leverages network confusion caused by training incoming data as a new class. We found that incorporating a class-imbalance during this detection method substantially enhances performance.
  arXiv  Detail & Related papers  (2021-04-09T15:58:43Z)
• Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection [27.354492072251492]
  Online annotation module (OAM) learns to generate a many-shot set of emphreliable annotations from a larger volume of weakly labelled images. Our OAM can be jointly trained with any fully supervised two-stage object detection method, providing additional training annotations on the fly. The integration of the OAM with Fast(er) R-CNN improves their performance by $17%$ mAP, $9%$ AP50 on PASCAL VOC 2007 and MS-COCO benchmarks, and significantly outperforms competing methods using mixed supervision.
  arXiv  Detail & Related papers  (2020-08-21T22:06:43Z)

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.