Interactive Multi-Class Tiny-Object Detection

@article{Lee2022InteractiveMT,
  title={Interactive Multi-Class Tiny-Object Detection},
  author={Chun Jen Lee and Seonwook Park and Heon Song and Jeongun Ryu and Sanghoon Kim and Haejoon Kim and S{\'e}rgio Pereira and Donggeun Yoo},
  journal={2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2022},
  pages={14116-14125}
}
  • C. LeeSeonwook Park Donggeun Yoo
  • Published 29 March 2022
  • Computer Science
  • 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Annotating tens or hundreds of tiny objects in a given image is laborious yet crucial for a multitude of Computer Vision tasks. Such imagery typically contains objects from various categories, yet the multi-class interactive annotation setting for the detection task has thus far been unex-plored. To address these needs, we propose a novel interactive annotation method for multiple instances of tiny objects from multiple classes, based on a few point-based user in-puts. Our approach, C3Det… 

A Novel Multi-Scale Transformer for Object Detection in Aerial Scenes

DFCformer is mainly composed of three parts: the backbone network DMViT, which introduces deformation patch embedding and multi-scale adaptive self-attention to capture sufficient features of the objects, and FRGC guides feature interaction layer by layer to break the barriers between feature layers and improve the information discrimination and processing ability of multi- scale critical features.

Multi-Stage Transformer 3D Object Detection Method

A multi-task transformer 3D object detection method that includes a fast transformer based 3D encoder and a multi-stage transformer decoder and can supress current other 3Dobject detection methods with a clear margin.

Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems

This paper shows that the existing cross entropy loss minimization problem essentially learns the label conditional entropy of the underlying data distribution of the dataset, and proposes a mutual information learning framework where deep neural network classifiers are trained via learning the mutual information between the label and the in- put.

References

SHOWING 1-10 OF 37 REFERENCES

Deep Interactive Object Selection

This paper presents a novel deep-learning-based algorithm which has much better understanding of objectness and can reduce user interactions to just a few clicks and is superior to all existing interactive object selection approaches.

Points as Queries: Weakly Semi-supervised Object Detection by Points

A new detector is introduced, Point DETR, which extends DETR by adding a point encoder, which achieves a promising performance when using 20% fully labeled data from COCO, and the point annotations bring over 10 points in various AR metrics.

Interactive object detection

An interactive object annotation method that incrementally trains an object detector while the user provides annotations that gives live feedback to the user by detecting objects on the fly and predicts the potential annotation costs of unseen images.

Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++

This work follows the idea of Polygon-RNN to produce polygonal annotations of objects interactively using humans-in-the-loop and achieves a high reduction in annotation time for new datasets, moving a step closer towards an interactive annotation tool to be used in practice.

Interactive Full Image Segmentation by Considering All Regions Jointly

This work proposes an interactive, scribble-based annotation framework which operates on the whole image to produce segmentations for all regions, and adapt Mask-RCNN into a fast interactive segmentation framework and introduces an instance-aware loss measured at the pixel-level in the full image canvas, which lets predictions for nearby regions properly compete for space.

Learning To Count Everything

This paper presents a novel method that takes a query image together with a few exemplar objects from the query image and predicts a density map for the presence of all objects of interest in the query photo, and introduces a dataset of 147 object categories containing over 6000 images suitable for the few-shot counting task.

Deep GrabCut for Object Selection

A novel segmentation approach that uses a rectangle as a soft constraint by transforming it into an Euclidean distance map that gets accurate segmentation results given sloppy rectangles while being general for both interactive segmentation and instance segmentation.

Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges

  • Jian DingNan Xue L. Zhang
  • Computer Science, Environmental Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2022
The expanded large-scale DOTA dataset, the extensive baselines, the code library and the challenges can facilitate the designs of robust algorithms and reproducible research on the problem of object detection in aerial images.

Few-Shot Segmentation Propagation with Guided Networks

This work addresses the problem of few-shot segmentation: given few image and few pixel supervision, segment any images accordingly, and proposes guided networks, which extract a latent task representation from any amount of supervision, and optimize the architecture end-to-end for fast, accurate few- shot segmentation.

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.