Corpus ID: 235593296

MEAL: Manifold Embedding-based Active Learning

  title={MEAL: Manifold Embedding-based Active Learning},
  author={Deepthi Sreenivasaiah and Thomas Wollmann},
Image segmentation is a common and challenging task in autonomous driving. Availability of sufficient pixel-level annotations for the training data is a hurdle. Active learning helps learning from small amounts of data by suggesting the most promising samples for labeling. In this work, we propose a new pool-based method for active learning, which proposes promising patches extracted from full image, in each acquisition step. The problem is framed in an exploration-exploitation framework by… Expand

Figures and Tables from this paper


Ask-n-Learn: Active Learning via Reliable Gradient Representations for Image Classification
Ask-n-Learn, an active learning approach based on gradient embeddings obtained using the pesudo-labels estimated in each iteration of the algorithm, is proposed and significant improvements over state-of-the-art baselines, including the recently proposed BADGE algorithm are demonstrated. Expand
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
This work designs a new algorithm for batch active learning with deep neural network models that samples groups of points that are disparate and high-magnitude when represented in a hallucinated gradient space, and shows that while other approaches sometimes succeed for particular batch sizes or architectures, BADGE consistently performs as well or better, making it a versatile option for practical active learning problems. Expand
Importance of Self-Consistency in Active Learning for Semantic Segmentation
We address the task of active learning in the context of semantic segmentation and show that self-consistency can be a powerful source of self-supervision to greatly improve the performance of aExpand
On Deep Unsupervised Active Learning
A novel Deep neural network framework for Unsupervised Active Learning, called DUAL, which can explicitly learn a nonlinear embedding to map each input into a latent space through an encoder-decoder architecture, and introduce a selection block to select representative samples in the the learnt latent space. Expand
Real-Time Driving Scene Semantic Segmentation
Object Weighted Focal Loss (OWFL) is proposed to deal with the serious class imbalance issue in pixel-wise segmentation task and could effectively improve the overall mean IoU of minor and hard objects by increasing loss contribution from them. Expand
Reinforced active learning for image segmentation
This paper proposes a new modification of the deep Q-network (DQN) formulation for active learning, adapting it to the large-scale nature of semantic segmentation problems, and finds that its method asks for more labels of under-represented categories compared to the baselines, improving their performance and helping to mitigate class imbalance. Expand
ViewAL: Active Learning With Viewpoint Entropy for Semantic Segmentation
This work introduces a new viewpoint entropy formulation, which is the basis of a novel active learning strategy for semantic segmentation that exploits viewpoint consistency in multi-view datasets and proposes uncertainty computations on a superpixel level, which exploits inherently localized signal in the segmentation task, directly lowering the annotation costs. Expand
PyTorch: An Imperative Style, High-Performance Deep Learning Library
This paper details the principles that drove the implementation of PyTorch and how they are reflected in its architecture, and explains how the careful and pragmatic implementation of the key components of its runtime enables them to work together to achieve compelling performance. Expand
Active Learning for Convolutional Neural Networks: A Core-Set Approach
This work defines the problem of active learning as core-set selection as choosing set of points such that a model learned over the selected subset is competitive for the remaining data points, and presents a theoretical result characterizing the performance of any selected subset using the geometry of the datapoints. Expand
CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation
This work proposes an active learning-based strategy, called CEREALS, in which a human only has to hand-label a few, automatically selected, regions within an unlabeled image corpus, which minimizes human annotation effort while maximizing the performance of a semantic image segmentation method. Expand