Unsupervised learning of features and object boundaries from local
prediction
- URL: http://arxiv.org/abs/2205.14195v1
- Date: Fri, 27 May 2022 18:54:10 GMT
- Title: Unsupervised learning of features and object boundaries from local
prediction
- Authors: Heiko H. Sch\"utt and Wei Ji Ma
- Abstract summary: We introduce a layer of feature maps with a pairwise Markov random field model in which each factor is paired with an additional binary variable, which switches the factor on or off.
We can learn both the features and the parameters of the Markov random field factors from images without further supervision signals.
We show that computing predictions across space aids both segmentation and feature learning, and models trained to optimize these predictions show similarities to the human visual system.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: A visual system has to learn both which features to extract from images and
how to group locations into (proto-)objects. Those two aspects are usually
dealt with separately, although predictability is discussed as a cue for both.
To incorporate features and boundaries into the same model, we model a layer of
feature maps with a pairwise Markov random field model in which each factor is
paired with an additional binary variable, which switches the factor on or off.
Using one of two contrastive learning objectives, we can learn both the
features and the parameters of the Markov random field factors from images
without further supervision signals. The features learned by shallow neural
networks based on this loss are local averages, opponent colors, and Gabor-like
stripe patterns. Furthermore, we can infer connectivity between locations by
inferring the switch variables. Contours inferred from this connectivity
perform quite well on the Berkeley segmentation database (BSDS500) without any
training on contours. Thus, computing predictions across space aids both
segmentation and feature learning, and models trained to optimize these
predictions show similarities to the human visual system. We speculate that
retinotopic visual cortex might implement such predictions over space through
lateral connections.
Related papers
- SIGMA:Sinkhorn-Guided Masked Video Modeling [69.31715194419091]
Sinkhorn-guided Masked Video Modelling ( SIGMA) is a novel video pretraining method.
We distribute features of space-time tubes evenly across a limited number of learnable clusters.
Experimental results on ten datasets validate the effectiveness of SIGMA in learning more performant, temporally-aware, and robust video representations.
arXiv Detail & Related papers (2024-07-22T08:04:09Z) - Dual Feature Augmentation Network for Generalized Zero-shot Learning [14.410978100610489]
Zero-shot learning (ZSL) aims to infer novel classes without training samples by transferring knowledge from seen classes.
Existing embedding-based approaches for ZSL typically employ attention mechanisms to locate attributes on an image.
We propose a novel Dual Feature Augmentation Network (DFAN), which comprises two feature augmentation modules.
arXiv Detail & Related papers (2023-09-25T02:37:52Z) - Domain Adaptive Synapse Detection with Weak Point Annotations [63.97144211520869]
We present AdaSyn, a framework for domain adaptive synapse detection with weak point annotations.
In the WASPSYN challenge at I SBI 2023, our method ranks the 1st place.
arXiv Detail & Related papers (2023-08-31T05:05:53Z) - Structured Latent Variable Models for Articulated Object Interaction [24.97457132614502]
We investigate a scenario in which a robot learns a low-dimensional representation of a door given a video of the door opening or closing.
This representation can be used to infer door-related parameters and predict the outcomes of interacting with the door.
arXiv Detail & Related papers (2023-05-26T01:22:35Z) - Extracting Semantic Knowledge from GANs with Unsupervised Learning [65.32631025780631]
Generative Adversarial Networks (GANs) encode semantics in feature maps in a linearly separable form.
We propose a novel clustering algorithm, named KLiSH, which leverages the linear separability to cluster GAN's features.
KLiSH succeeds in extracting fine-grained semantics of GANs trained on datasets of various objects.
arXiv Detail & Related papers (2022-11-30T03:18:16Z) - Do Neural Networks Trained with Topological Features Learn Different
Internal Representations? [1.418465438044804]
We investigate whether a model trained with topological features learns internal representations of data that are fundamentally different than those learned by a model trained with the original raw data.
We find that structurally, the hidden representations of models trained and evaluated on topological features differ substantially compared to those trained and evaluated on the corresponding raw data.
We conjecture that this means that neural networks trained on raw data may extract some limited topological features in the process of making predictions.
arXiv Detail & Related papers (2022-11-14T19:19:04Z) - Learning sparse features can lead to overfitting in neural networks [9.2104922520782]
We show that feature learning can perform worse than lazy training.
Although sparsity is known to be essential for learning anisotropic data, it is detrimental when the target function is constant or smooth.
arXiv Detail & Related papers (2022-06-24T14:26:33Z) - Probabilistic Tracking with Deep Factors [8.030212474745879]
We show how to use a deep feature encoding in conjunction with generative densities over the features in a factor-graph based, probabilistic tracking framework.
We present a likelihood model that combines a learned feature encoder with generative densities over them, both trained in a supervised manner.
arXiv Detail & Related papers (2021-12-02T21:31:51Z) - Intersection Regularization for Extracting Semantic Attributes [72.53481390411173]
We consider the problem of supervised classification, such that the features that the network extracts match an unseen set of semantic attributes.
For example, when learning to classify images of birds into species, we would like to observe the emergence of features that zoologists use to classify birds.
We propose training a neural network with discrete top-level activations, which is followed by a multi-layered perceptron (MLP) and a parallel decision tree.
arXiv Detail & Related papers (2021-03-22T14:32:44Z) - Learning What Makes a Difference from Counterfactual Examples and
Gradient Supervision [57.14468881854616]
We propose an auxiliary training objective that improves the generalization capabilities of neural networks.
We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task.
Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
arXiv Detail & Related papers (2020-04-20T02:47:49Z) - Articulation-aware Canonical Surface Mapping [54.0990446915042]
We tackle the tasks of predicting a Canonical Surface Mapping (CSM) that indicates the mapping from 2D pixels to corresponding points on a canonical template shape, and inferring the articulation and pose of the template corresponding to the input image.
Our key insight is that these tasks are geometrically related, and we can obtain supervisory signal via enforcing consistency among the predictions.
We empirically show that allowing articulation helps learn more accurate CSM prediction, and that enforcing the consistency with predicted CSM is similarly critical for learning meaningful articulation.
arXiv Detail & Related papers (2020-04-01T17:56:45Z)
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.