MetaBox+: A New Region based Active Learning Method for Semantic Segmentation using Priority Maps

Colling, Pascal; Roese-Koerner, Lutz; Gottschalk, Hanno; Rottmann, Matthias

doi:10.5220/0010227500510062

Cited by 18 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such classes could be initially incorporated into an existing model using the presented methodology in this work. Afterwards, the initial performance could be further improved with active learning approaches, such as presented in [Col+21], still requiring only a small amount of human labeling effort. It is also an open question, to which extent the proposed method can be used iteratively to improve the performance on a new class.…”

Section: Discussionmentioning

confidence: 99%

Detecting and Learning the Unknown in Semantic Segmentation

Chan¹,

Svenja²,

Rottmann³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Semantic segmentation is a crucial component for perception in automated driving. Deep neural networks (DNNs) are commonly used for this task and they are usually trained on a closed set of object classes appearing in a closed operational domain. However, this is in contrast to the open world assumption in automated driving that DNNs are deployed to. Therefore, DNNs necessarily face data that they have never encountered previously, also known as anomalies, which are extremely safety-critical to properly cope with.In this work, we first give an overview about anomalies from an information-theoretic perspective. Next, we review research in detecting semantically unknown objects in semantic segmentation. We demonstrate that training for high entropy responses on anomalous objects outperforms other recent methods, which is in line with our theoretical findings. Moreover, we examine a method to assess the occurrence frequency of anomalies in order to select anomaly types to include into a model's set of semantic categories. We demonstrate that these anomalies can then be learned in an unsupervised fashion, which is particularly suitable in online applications based on deep learning.

show abstract

Section: Discussionmentioning

confidence: 99%

Detecting and Learning the Unknown in Semantic Segmentation

Chan¹,

Svenja²,

Rottmann³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Different from annotators whose budget may be measured in time or money, previous work proposed to use the number of labeled points as a substitute of the real annotation cost [3]. At present, with the development of regionbased approaches [8], some approaches [3,6,19] advocate the click number instead of the number of labeled points as a more realistic measurement of annotation cost. In our work, we consider one-click operation can assign the class of one region based on the traditional dominant labeling strategy [3].…”

Section: Labeling For the Candidate Superpointsmentioning

confidence: 99%

Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning

Shao¹,

Luo²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

The expensive annotation cost is notoriously known as a main constraint for the development of the point cloud semantic segmentation technique. In this paper, we propose a novel active learning-based method to tackle this problem. Dubbed SSDR-AL, our method groups the original point clouds into superpoints and selects the most informative and representative ones for label acquisition. We achieve the selection mechanism via a graph reasoning network that considers both the spatial and structural diversity of the superpoints. To deploy SSDR-AL in a more practical scenario, we design a noise aware iterative labeling scheme to confront the "noisy annotation" problem introduced by previous dominant labeling methods in superpoints. Extensive experiments on two point cloud benchmarks demonstrate the effectiveness of SSDR-AL in the semantic segmentation task. Particularly, SSDR-AL significantly outperforms the baseline method when the labeled sets are small, where SSDR-AL requires only 5.7% and 1.9% annotation costs to achieve the performance of 90% fully supervised learning on S3DIS and Semantic3D datasets, respectively.

show abstract

“…equation (8). As the removal of FP OoD predictions should not come at cost of a significant loss in original performance, see figure 6, we additionally consider the miss rate of road pixels: (10) with pixel locations predicted to be in-distribution in Ẑin and annotated as in-distribution in Z in . The road miss rate measures the proportion of actual road pixels in the whole dataset which are incorrectly identified.…”

Section: Segment-wise Evaluationmentioning

confidence: 99%

“…Defining additional classes requires a large amount of annotated data (cf. [10,47]) and may even lead to performance drops [13]. One natural approach is to introduce a none-of-the-known output for objects not belonging to any of the predefined classes [45].…”

Section: Introductionmentioning

confidence: 99%

“…Detection errors for LostAndFound OoD objects at different entropy thresholds t. We consider the road miss rate ε, see equation(10), as further measure of loss in original performance (for Cityscapes mIoU, see figure5). Below the horizontal line, i.e., t ≥ 0.3, we consider the loss in original performance to be acceptable, see section 6.3 for further details.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation

Chan¹,

Rottmann²,

Gottschalk³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Deep neural networks (DNNs) for the semantic segmentation of images are usually trained to operate on a predefined closed set of object classes. This is in contrast to the "open world" setting where DNNs are envisioned to be deployed to. From a functional safety point of view, the ability to detect so-called "out-of-distribution" (OoD) samples, i.e., objects outside of a DNN's semantic space, is crucial for many applications such as automated driving. A natural baseline approach to OoD detection is to threshold on the pixel-wise softmax entropy. We present a two-step procedure that significantly improves that approach. Firstly, we utilize samples from the COCO dataset as OoD proxy and introduce a second training objective to maximize the softmax entropy on these samples. Starting from pretrained semantic segmentation networks we re-train a number of DNNs on different in-distribution datasets and consistently observe improved OoD detection performance when evaluating on completely disjoint OoD datasets. Secondly, we perform a transparent post-processing step to discard false positive OoD samples by so-called "meta classification". To this end, we apply linear models to a set of hand-crafted metrics derived from the DNN's softmax probabilities. In our experiments we consistently observe a clear additional gain in OoD detection performance, cutting down the number of detection errors by 52% when comparing the best baseline with our results. We achieve this improvement sacrificing only marginally in original segmentation performance. Therefore, our method contributes to safer DNNs with more reliable overall system performance.

show abstract

MetaBox+: A New Region based Active Learning Method for Semantic Segmentation using Priority Maps

Cited by 18 publications

References 0 publications

Detecting and Learning the Unknown in Semantic Segmentation

Detecting and Learning the Unknown in Semantic Segmentation

Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning

Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation

Contact Info

Product

Resources

About