Scaling Object Detection by Transferring Classification Weights

@article{Kuen2019ScalingOD,
  title={Scaling Object Detection by Transferring Classification Weights},
  author={Jason Kuen and Federico Perazzi and Zhe L. Lin and Jianming Zhang and Yap-Peng Tan},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={6043-6052}
}
Large scale object detection datasets are constantly increasing their size in terms of the number of classes and annotations count. Yet, the number of object-level categories annotated in detection datasets is an order of magnitude smaller than image-level classification labels. State-of-the art object detection models are trained in a supervised fashion and this limits the number of object classes they can detect. In this paper, we propose a novel weight transfer network (WTN) to effectively… Expand
Class-agnostic Object Detection
TLDR
This work proposes class-agnostic object detection as a new problem that focuses on detecting objects irrespective of their object-classes, and proposes a new adversarial learning framework that forces the model to exclude class-specific information from features used for predictions. Expand
Cross-Supervised Object Detection
TLDR
This work proposes a unified framework that combines a detection head trained from instance- level annotations and a recognition head learned from image-level annotations, together with a spatial correlation module that bridges the gap between detection and recognition. Expand
Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer
TLDR
An effective knowledge transfer framework to boost the weakly supervised object detection accuracy with the help of an external fully-annotated source dataset, whose categories may not overlap with the target domain, is proposed. Expand
CaT: Weakly Supervised Object Detection with Category Transfer
TLDR
A novel category transfer framework for weakly supervised object detection that achieves 63.5% mAP and 80.3% CorLoc with 5 overlapping categories between two datasets, which outperforms the state-of-the-art methods. Expand
Weak Novel Categories without Tears: A Survey on Weak-Shot Learning
  • Li Niu
  • Computer Science
  • 2021
TLDR
This paper discusses the existing weakshot learning methodologies in different tasks and summarizes the codes at https://github.com/bcmi/Awesome-Weak-Shot-Learning and treats it as weakly supervised learning with auxiliary fully supervised categories. Expand
Learning to Localize Actions from Moments
TLDR
This paper introduces a new design of transfer learning type to learn action localization for a large set of action categories, but only on action moments from the categories of interest and temporal annotations of untrimmed videos from a small set of Action Herald Networks (AherNet). Expand
A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection
TLDR
The approach turns an object-centric image into a useful training example for object detection in scene-centric images by mitigating the domain gap between the two image sources in both the input and label space and employs a multi-stage procedure to train the object detector. Expand

References

SHOWING 1-10 OF 55 REFERENCES
LSDA: Large Scale Detection through Adaptation
TLDR
This paper proposes Large Scale Detection through Adaptation (LSDA), an algorithm which learns the difference between the two tasks and transfers this knowledge to classifiers for categories without bounding box annotated data, turning them into detectors. Expand
Large Scale Semi-Supervised Object Detection Using Visual and Semantic Knowledge Transfer
TLDR
Strong evidence is found that visual similarity and semantic relatedness are complementary for the task, and when combined notably improve detection, achieving state-of-the-art detection performance in a semi-supervised setting. Expand
Visual and Semantic Knowledge Transfer for Large Scale Semi-Supervised Object Detection
TLDR
Strong evidence is found that visual similarity and semantic relatedness are complementary for the task, and when combined notably improve detection, achieving state-of-the-art detection performance in a semi-supervised setting. Expand
R-FCN-3000 at 30fps: Decoupling Detection and Classification
TLDR
It is shown that the objectness learned by R-FCN-3000 generalizes to novel classes and the performance increases with the number of training object classes - supporting the hypothesis that it is possible to learn a universal objectness detector. Expand
Few-Shot Object Detection via Feature Reweighting
TLDR
This work develops a few-shot object detector that can learn to detect novel objects from only a few annotated examples, using a meta feature learner and a reweighting module within a one-stage detection architecture. Expand
Zero-Shot Object Detection
TLDR
The problem of zero-shot object detection (ZSD), which aims to detect object classes which are not observed during training, is introduced and the problems associated with selecting a background class are discussed and motivate two background-aware approaches for learning robust detectors. Expand
Revisiting Knowledge Transfer for Training Object Class Detectors
TLDR
A unified knowledge transfer framework based on training a single neural network multi-class object detector over all source classes, organized in a semantic hierarchy is presented, establishing its general applicability. Expand
Zero-Annotation Object Detection with Web Knowledge Transfer
TLDR
This work proposes an object detection method that does not require any form of human annotation on target tasks, by exploiting freely available web images, and introduces a multi-instance multi-label domain adaption learning framework with two key innovations. Expand
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Expand
You Only Look Once: Unified, Real-Time Object Detection
TLDR
Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork. Expand
...
1
2
3
4
5
...