Ground-truth or DAER: Selective Re-query of Secondary Information
- URL: http://arxiv.org/abs/2009.07414v3
- Date: Fri, 3 Sep 2021 00:56:24 GMT
- Title: Ground-truth or DAER: Selective Re-query of Secondary Information
- Authors: Stephan J. Lemmer and Jason J. Corso
- Abstract summary: Many vision tasks use secondary information at inference time -- a seed -- to assist a computer vision model in solving a problem.
We propose the problem of seed rejection, determining whether to reject a seed based on the expected performance degradation.
We show our method can reduce the number of seeds that need to be reviewed for a target performance by over 23% compared to strong baselines.
- Score: 37.21776636843253
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Many vision tasks use secondary information at inference time -- a seed -- to
assist a computer vision model in solving a problem. For example, an initial
bounding box is needed to initialize visual object tracking. To date, all such
work makes the assumption that the seed is a good one. However, in practice,
from crowdsourcing to noisy automated seeds, this is often not the case. We
hence propose the problem of seed rejection -- determining whether to reject a
seed based on the expected performance degradation when it is provided in place
of a gold-standard seed. We provide a formal definition to this problem, and
focus on two meaningful subgoals: understanding causes of error and
understanding the model's response to noisy seeds conditioned on the primary
input. With these goals in mind, we propose a novel training method and
evaluation metrics for the seed rejection problem. We then use seeded versions
of the viewpoint estimation and fine-grained classification tasks to evaluate
these contributions. In these experiments, we show our method can reduce the
number of seeds that need to be reviewed for a target performance by over 23%
compared to strong baselines.
Related papers
- Double-Bounded Optimal Transport for Advanced Clustering and
Classification [58.237576976486544]
We propose Doubly Bounded Optimal Transport (DB-OT), which assumes that the target distribution is restricted within two boundaries instead of a fixed one.
We show that our method can achieve good results with our improved inference scheme in the testing stage.
arXiv Detail & Related papers (2024-01-21T07:43:01Z) - Unsupervised Pre-Training for 3D Leaf Instance Segmentation [34.122575664767915]
This paper addresses the problem of reducing the labeling effort required to perform leaf instance segmentation on 3D point clouds.
We propose a novel self-supervised task-specific pre-training approach to initialize the backbone of a network for leaf instance segmentation.
We also introduce a novel automatic postprocessing that considers the difficulty of correctly segmenting the points close to the stem.
arXiv Detail & Related papers (2024-01-16T08:11:08Z) - Automatic counting of mounds on UAV images: combining instance
segmentation and patch-level correction [15.912811733537668]
We present a novel framework exploiting advances in Unmanned Aerial Vehicle (UAV) imaging and computer vision.
We exploit a visual recognition method based on a deep learning algorithm for multiple object detection by pixel-based segmentation.
We employ a machine learning estimation function that predicts the final number of mounds based on the local block properties extracted.
arXiv Detail & Related papers (2022-09-06T16:02:38Z) - Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit
Neural Representation [79.60988242843437]
We propose a novel approach that achieves self-supervised and magnification-flexible point clouds upsampling simultaneously.
Experimental results demonstrate that our self-supervised learning based scheme achieves competitive or even better performance than supervised learning based state-of-the-art methods.
arXiv Detail & Related papers (2022-04-18T07:18:25Z) - Automated Seed Quality Testing System using GAN & Active Learning [2.8978926857710263]
We build a novel seed image acquisition setup, which captures both the top and bottom views.
We are able to get accuracies of up to 91.6% for testing the physical purity of seed samples.
arXiv Detail & Related papers (2021-10-02T10:28:25Z) - An Efficient Method for the Classification of Croplands in Scarce-Label
Regions [0.0]
Two of the main challenges for cropland classification by satellite time-series images are insufficient ground-truth data and inaccessibility of high-quality hyperspectral images for under-developed areas.
Unlabeled medium-resolution satellite images are abundant, but how to benefit from them is an open question.
We will show how to leverage their potential for cropland classification using self-supervised tasks.
arXiv Detail & Related papers (2021-03-17T12:10:11Z) - Seed Phenotyping on Neural Networks using Domain Randomization and
Transfer Learning [0.0]
Seed phenotyping is the idea of analyzing the morphometric characteristics of a seed to predict its behavior in terms of development, tolerance and yield.
The focus of the work is the application and feasibility analysis of the state-of-the-art object detection and localization networks.
arXiv Detail & Related papers (2020-12-24T14:04:28Z) - Completely Self-Supervised Crowd Counting via Distribution Matching [92.09218454377395]
We propose a complete self-supervision approach to training models for dense crowd counting.
The only input required to train, apart from a large set of unlabeled crowd images, is the approximate upper limit of the crowd count.
Our method dwells on the idea that natural crowds follow a power law distribution, which could be leveraged to yield error signals for backpropagation.
arXiv Detail & Related papers (2020-09-14T13:20:12Z) - Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks [50.78037828213118]
This paper tackles the semi-supervised crowd counting problem from the perspective of feature learning.
We propose a novel semi-supervised crowd counting method which is built upon two innovative components.
arXiv Detail & Related papers (2020-07-07T05:30:53Z) - CASE: Context-Aware Semantic Expansion [68.30244980290742]
This paper defines and studies a new task called Context-Aware Semantic Expansion (CASE)
Given a seed term in a sentential context, we aim to suggest other terms that well fit the context as the seed.
We show that annotations for this task can be harvested at scale from existing corpora, in a fully automatic manner.
arXiv Detail & Related papers (2019-12-31T06:38:57Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.