Towards Accurate Localization by Instance Search
Not on the map. Why?
Abstract (arXiv)
Visual object localization is the key step in a series of object detection tasks. In the literature, high localization accuracy is achieved with the mainstream strongly supervised frameworks. However, such methods require object-level annotations and are unable to detect objects of unknown categories. Weakly supervised methods face similar difficulties. In this paper, a self-paced learning framework is proposed to achieve accurate object localization on the rank list returned by instance search. The proposed framework mines the target instance gradually from the queries and their corresponding top-ranked search results. Since a common instance is shared between the query and the images in the rank list, the target visual instance can be accurately localized even without knowing what the object category is. In addition to performing localization on instance search, the issue of few-shot object detection is also addressed under the same framework. Superior performance over state-of-the-art methods is observed on both tasks.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 33 of its 55 references that are in the map. First posted on arXiv 11 Jul 2021.
Builds on
33 of 55 references.
References · 33
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
- 2017Squeeze-and-Excitation Networkscited by 4,763
- 2017Non-local Neural Networkscited by 2,290
- 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
- 2018GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wildcited by 471
- 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 445
- 2018LaSOT: A High-quality Benchmark for Large-scale Single Object Trackingcited by 424
- 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
21 more
- 2018Few-shot Object Detection via Feature Reweightingcited by 265
- 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
- 2018Distractor-aware Siamese Networks for Visual Object Trackingcited by 187
- 2015Weakly Supervised Deep Detection Networkscited by 183
- 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
- 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
- 2015Particular object retrieval with integral max-pooling of CNN activationscited by 160
- 2020Multi-Scale Positive Sample Refinement for Few-Shot Object Detectioncited by 116
- 2017YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Videocited by 109
- 2018PCL: Proposal Cluster Learning for Weakly Supervised Object Detectioncited by 97
- 2021Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detectioncited by 79
- 2019One-Shot Object Detection with Co-Attention and Co-Excitationcited by 67
- 2016Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representationscited by 49
- 2015Cross-dimensional Weighting for Aggregated Deep Convolutional Featurescited by 41
- 2015Weakly Supervised Object Localization with Multi-fold Multiple Instance Learningcited by 39
- 2016Self Paced Deep Learning for Weakly Supervised Object Detectioncited by 25
- 2016Faster R-CNN Features for Instance Searchcited by 14
- 2017Class-Weighted Convolutional Features for Visual Instance Searchcited by 8
- 2017Saliency Weighted Convolutional Features for Instance Searchcited by 6
- 2020Deeply Activated Salient Region for Instance Searchcited by 4
- 2018Instance Search via Instance Level Segmentation and Feature Representationcited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.