Object Detection with a Unified Label Space from Multiple Datasets
- URL: http://arxiv.org/abs/2008.06614v1
- Date: Sat, 15 Aug 2020 00:51:27 GMT
- Title: Object Detection with a Unified Label Space from Multiple Datasets
- Authors: Xiangyun Zhao, Samuel Schulter, Gaurav Sharma, Yi-Hsuan Tsai, Manmohan
Chandraker, Ying Wu
- Abstract summary: Given multiple datasets with different label spaces, the goal of this work is to train a single object detector predicting over the union of all the label spaces.
Consider an object category like faces that is annotated in one dataset, but is not annotated in another dataset.
Some categories, like face here, would thus be considered foreground in one dataset, but background in another.
We propose loss functions that carefully integrate partial but correct annotations with complementary but noisy pseudo labels.
- Score: 94.33205773893151
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Given multiple datasets with different label spaces, the goal of this work is
to train a single object detector predicting over the union of all the label
spaces. The practical benefits of such an object detector are obvious and
significant application-relevant categories can be picked and merged form
arbitrary existing datasets. However, naive merging of datasets is not possible
in this case, due to inconsistent object annotations. Consider an object
category like faces that is annotated in one dataset, but is not annotated in
another dataset, although the object itself appears in the latter images. Some
categories, like face here, would thus be considered foreground in one dataset,
but background in another. To address this challenge, we design a framework
which works with such partial annotations, and we exploit a pseudo labeling
approach that we adapt for our specific case. We propose loss functions that
carefully integrate partial but correct annotations with complementary but
noisy pseudo labels. Evaluation in the proposed novel setting requires full
annotation on the test set. We collect the required annotations and define a
new challenging experimental setup for this task based one existing public
datasets. We show improved performances compared to competitive baselines and
appropriate adaptations of existing work.
Related papers
- Object-Centric Multiple Object Tracking [124.30650395969126]
This paper proposes a video object-centric model for multiple-object tracking pipelines.
It consists of an index-merge module that adapts the object-centric slots into detection outputs and an object memory module.
Benefited from object-centric learning, we only require sparse detection labels for object localization and feature binding.
arXiv Detail & Related papers (2023-09-01T03:34:12Z) - AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute
Decomposition-Aggregation [33.25304533086283]
Open-vocabulary semantic segmentation is a challenging task that requires segmenting novel object categories at inference time.
Recent studies have explored vision-language pre-training to handle this task, but suffer from unrealistic assumptions in practical scenarios.
This work proposes a novel attribute decomposition-aggregation framework, AttrSeg, inspired by human cognition in understanding new concepts.
arXiv Detail & Related papers (2023-08-31T19:34:09Z) - Detection Hub: Unifying Object Detection Datasets via Query Adaptation
on Language Embedding [137.3719377780593]
A new design (named Detection Hub) is dataset-aware and category-aligned.
It mitigates the dataset inconsistency and provides coherent guidance for the detector to learn across multiple datasets.
The categories across datasets are semantically aligned into a unified space by replacing one-hot category representations with word embedding.
arXiv Detail & Related papers (2022-06-07T17:59:44Z) - Iterative Learning for Instance Segmentation [0.0]
State-of-the-art deep neural network models require large amounts of labeled data in order to perform well in this task.
We propose for the first time, an iterative learning and annotation method that is able to detect, segment and annotate instances in datasets composed of multiple similar objects.
Experiments on two different datasets show the validity of the approach in different applications related to visual inspection.
arXiv Detail & Related papers (2022-02-18T10:25:02Z) - Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks [17.033055327465238]
We propose two contrasting paradigms for data annotation.
The descriptive paradigm encourages annotator subjectivity, whereas the prescriptive paradigm discourages it.
We argue that dataset creators should explicitly aim for one or the other to facilitate the intended use of their dataset.
arXiv Detail & Related papers (2021-12-14T15:38:22Z) - Simple multi-dataset detection [83.9604523643406]
We present a simple method for training a unified detector on multiple large-scale datasets.
We show how to automatically integrate dataset-specific outputs into a common semantic taxonomy.
Our approach does not require manual taxonomy reconciliation.
arXiv Detail & Related papers (2021-02-25T18:55:58Z) - Self-supervised Robust Object Detectors from Partially Labelled Datasets [3.1669406516464007]
merging datasets allows us to train one integrated object detector, instead of training several ones.
We propose a training framework to overcome missing-label challenge of the merged datasets.
We evaluate our proposed framework for training Yolo on a simulated merged dataset with missing rate $approx!48%$ using VOC2012 and VOC2007.
arXiv Detail & Related papers (2020-05-23T15:18:20Z) - Weakly-Supervised Salient Object Detection via Scribble Annotations [54.40518383782725]
We propose a weakly-supervised salient object detection model to learn saliency from scribble labels.
We present a new metric, termed saliency structure measure, to measure the structure alignment of the predicted saliency maps.
Our method not only outperforms existing weakly-supervised/unsupervised methods, but also is on par with several fully-supervised state-of-the-art models.
arXiv Detail & Related papers (2020-03-17T12:59:50Z) - Cross-dataset Training for Class Increasing Object Detection [52.34737978720484]
We present a conceptually simple, flexible and general framework for cross-dataset training in object detection.
By cross-dataset training, existing datasets can be utilized to detect the merged object classes with a single model.
While using cross-dataset training, we only need to label the new classes on the new dataset.
arXiv Detail & Related papers (2020-01-14T04:40:47Z)
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.