ComplETR: Reducing the cost of annotations for object detection in dense scenes with vision transformers

09/13/2022
by   Achin Jain, et al.
12

Annotating bounding boxes for object detection is expensive, time-consuming, and error-prone. In this work, we propose a DETR based framework called ComplETR that is designed to explicitly complete missing annotations in partially annotated dense scene datasets. This reduces the need to annotate every object instance in the scene thereby reducing annotation cost. ComplETR augments object queries in DETR decoder with patch information of objects in the image. Combined with a matching loss, it can effectively find objects that are similar to the input patch and complete the missing annotations. We show that our framework outperforms the state-of-the-art methods such as Soft Sampling and Unbiased Teacher by itself, while at the same time can be used in conjunction with these methods to further improve their performance. Our framework is also agnostic to the choice of the downstream object detectors; we show performance improvement for several popular detectors such as Faster R-CNN, Cascade R-CNN, CenterNet2, and Deformable DETR on multiple dense scene datasets.

READ FULL TEXT

page 2

page 9

research
06/26/2020

Cross-Ssupervised Object Detection

After learning a new object category from image-level annotations (with ...
research
06/26/2020

Cross-Supervised Object Detection

After learning a new object category from image-level annotations (with ...
research
09/12/2023

SCP: Scene Completion Pre-training for 3D Object Detection

3D object detection using LiDAR point clouds is a fundamental task in th...
research
06/04/2021

Hallucination In Object Detection – A Study In Visual Part Verification

We show that object detectors can hallucinate and detect missing objects...
research
09/30/2020

Learning Object Detection from Captions via Textual Scene Attributes

Object detection is a fundamental task in computer vision, requiring lar...
research
06/18/2018

Soft Sampling for Robust Object Detection

We study the robustness of object detection under the presence of missin...
research
12/24/2019

Dense RepPoints: Representing Visual Objects with Dense Point Sets

We present an object representation, called Dense RepPoints, for flexibl...

Please sign up or login with your details

Forgot password? Click here to reset