• Corpus ID: 227255144

Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection

  title={Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection},
  author={Tiancai Wang and Tong Yang and Jiale Cao and X. Zhang},
Object detectors usually achieve promising results with the supervision of complete instance annotations. However, their performance is far from satisfactory with sparse instance annotations. Most existing methods for sparsely annotated object detection either re-weight the loss of hard negative samples or convert the unlabeled instances into ignored regions to reduce the interference of false negatives. We argue that these strategies are insufficient since they can at most alleviate the… 

Figures and Tables from this paper

Sparsely Annotated Object Detection: A Region-based Semi-supervised Approach
This work revisits the formulation of sparsely annotated object detection and proposes a region-based semi-supervised algorithm, that automatically identifies regions containing unlabeled foreground objects and achieves competitive performance on standard semi- supervised setups demonstrating the strength and broad applicability of the approach.
Deep Semi-supervised Metric Learning with Dual Alignment for Cervical Cancer Cell Detection
A novel semisupervised deep metric learning method to effectively leverage both labeled and unlabeled data with application to cervical cancer cell detection, demonstrating efficacy of deep semi-supervised metric learning with dual alignment on improving cervical cancercell detection performance.
Bootstrap Your Object Detector via Mixed Training
  • Mengde Xu, Zheng Zhang, +5 authors Xiang Bai
  • Computer Science
  • 2021
The introduction of MixTraining, a new training paradigm for object detection that can improve the performance of existing detectors for free and addresses localization noise and missing labels in human annotations by incorporating pseudo boxes that can compensate for these errors.
Scaling up instance annotation via label propagation
This paper proposes a highly efficient annotation scheme for building large datasets with object segmentation masks by using hierarchical clustering on mask predictions made by a segmentation model and efficiently searches through the hierarchy of clusters and selects which clusters to annotate.
Correcting Imprecise Object Locations for Training Object Detectors in Remote Sensing Applications
Object detection on aerial and satellite imagery is an important tool for image analysis in remote sensing and has many areas of application. As modern object detectors require accurate annotations
Semi-supervised Cell Detection in Time-lapse Images Using Temporal Consistency
A semi-supervised cell-detection method that effectively uses a time-lapse sequence with one labeled image and the other images unlabeled to select high-confidence positions by tracking the detected cells from the the labeled frame to those far from it.


Towards Human-Machine Cooperation: Self-Supervised Sample Mining for Object Detection
This paper presents a principled Self-supervised Sample Mining (SSM) process accounting for the real challenges in object detection, and proposes a new AL framework for gradually incorporating unlabeled or partially labeled data into the model learning while minimizing the annotating effort of users.
NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection
A novel NOise Tolerant Ensemble RCNN (NOTE-RCNN) object detector is proposed, in which a few seed box level annotations and a large scale of image level annotations are used to train the detector.
Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation
This paper addresses the value of cross-image semantic relations for comprehensive object pattern mining and provides a unified framework that handles well different WSSS settings, i.e., learning WSSD with (1) precise image-level supervision only, (2) extra simple single-label data, and (3) extra noisy web data.
Sampling Techniques for Large-Scale Object Detection From Sparsely Annotated Objects
This study proposes part-aware sampling, a method that uses human intuition for the hierarchical relation between objects that won the first and second place on the public and private test sets of the Google AI Open Images Competition 2018.
Consistency-based Semi-supervised Learning for Object detection
A Consistency-based Semi-supervised learning method for object Detection (CSD), which is a way of using consistency constraints as a tool for enhancing detection performance by making full use of available unlabeled data.
Soft Sampling for Robust Object Detection
The robustness of object detection under the presence of missing annotations is studied, and it is observed that after dropping 30% of the annotations, the performance of CNN-based object detectors like Faster-RCNN only drops by 5% on the PASCAL VOC dataset.
Proposal Learning for Semi-Supervised Object Detection
This paper presents a proposal learning approach to learn proposal features and predictions from both labeled and unlabeled data and builds a general and high-performance semi-supervised object detection framework, which can be easily adapted to proposal-based object detectors with different backbone architectures.
Focal Loss for Dense Object Detection
This paper proposes to address the extreme foreground-background class imbalance encountered during training of dense detectors by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples, and develops a novel Focal Loss, which focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.
Objects365: A Large-Scale, High-Quality Dataset for Object Detection
  • Shuai Shao, Zeming Li, +5 authors Jian Sun
  • Computer Science
    2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
Object365 can serve as a better feature learning dataset for localization-sensitive tasks like object detection and semantic segmentation and better generalization ability of Object365 has been verified on CityPersons, VOC segmentation, and ADE tasks.
Enriched Feature Guided Refinement Network for Object Detection
A single-stage detection framework that jointly tackles the problem of multi-scale object detection and class imbalance is proposed and a cascaded refinement scheme which first instills multi- Scale contextual features into the prediction layers of the single- stage detector in order to enrich their discriminative power for multi- scale detection.