Robust Representation Learning via Perceptual Similarity Metrics
- URL: http://arxiv.org/abs/2106.06620v1
- Date: Fri, 11 Jun 2021 21:45:44 GMT
- Title: Robust Representation Learning via Perceptual Similarity Metrics
- Authors: Saeid Asgari Taghanaki, Kristy Choi, Amir Khasahmadi, Anirudh Goyal
- Abstract summary: Contrastive Input Morphing (CIM) is a representation learning framework that learns input-space transformations of the data.
We show that CIM is complementary to other mutual information-based representation learning techniques.
- Score: 18.842322467828502
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: A fundamental challenge in artificial intelligence is learning useful
representations of data that yield good performance on a downstream task,
without overfitting to spurious input features. Extracting such task-relevant
predictive information is particularly difficult for real-world datasets. In
this work, we propose Contrastive Input Morphing (CIM), a representation
learning framework that learns input-space transformations of the data to
mitigate the effect of irrelevant input features on downstream performance. Our
method leverages a perceptual similarity metric via a triplet loss to ensure
that the transformation preserves task-relevant information.Empirically, we
demonstrate the efficacy of our approach on tasks which typically suffer from
the presence of spurious correlations: classification with nuisance
information, out-of-distribution generalization, and preservation of subgroup
accuracies. We additionally show that CIM is complementary to other mutual
information-based representation learning techniques, and demonstrate that it
improves the performance of variational information bottleneck (VIB) when used
together.
Related papers
- Leveraging Superfluous Information in Contrastive Representation Learning [0.0]
We show that superfluous information does exist during the conventional contrastive learning framework.
We design a new objective, namely SuperInfo, to learn robust representations by a linear combination of both predictive and superfluous information.
We demonstrate that learning with our loss can often outperform the traditional contrastive learning approaches on image classification, object detection and instance segmentation tasks.
arXiv Detail & Related papers (2024-08-19T16:21:08Z) - Tackling Distribution Shifts in Task-Oriented Communication with Information Bottleneck [28.661084093544684]
We propose a novel approach based on the information bottleneck (IB) principle and invariant risk minimization (IRM) framework.
The proposed method aims to extract compact and informative features that possess high capability for effective domain-shift generalization.
We show that the proposed scheme outperforms state-of-the-art approaches and achieves a better rate-distortion tradeoff.
arXiv Detail & Related papers (2024-05-15T17:07:55Z) - ALP: Action-Aware Embodied Learning for Perception [60.64801970249279]
We introduce Action-Aware Embodied Learning for Perception (ALP)
ALP incorporates action information into representation learning through a combination of optimizing a reinforcement learning policy and an inverse dynamics prediction objective.
We show that ALP outperforms existing baselines in several downstream perception tasks.
arXiv Detail & Related papers (2023-06-16T21:51:04Z) - FUNCK: Information Funnels and Bottlenecks for Invariant Representation
Learning [7.804994311050265]
We investigate a set of related information funnels and bottleneck problems that claim to learn invariant representations from the data.
We propose a new element to this family of information-theoretic objectives: The Conditional Privacy Funnel with Side Information.
Given the generally intractable objectives, we derive tractable approximations using amortized variational inference parameterized by neural networks.
arXiv Detail & Related papers (2022-11-02T19:37:55Z) - Cluster-level pseudo-labelling for source-free cross-domain facial
expression recognition [94.56304526014875]
We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER)
Our method exploits self-supervised pretraining to learn good feature representations from the target data.
We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
arXiv Detail & Related papers (2022-10-11T08:24:50Z) - Automatic Data Augmentation via Invariance-Constrained Learning [94.27081585149836]
Underlying data structures are often exploited to improve the solution of learning tasks.
Data augmentation induces these symmetries during training by applying multiple transformations to the input data.
This work tackles these issues by automatically adapting the data augmentation while solving the learning task.
arXiv Detail & Related papers (2022-09-29T18:11:01Z) - Learning Bias-Invariant Representation by Cross-Sample Mutual
Information Minimization [77.8735802150511]
We propose a cross-sample adversarial debiasing (CSAD) method to remove the bias information misused by the target task.
The correlation measurement plays a critical role in adversarial debiasing and is conducted by a cross-sample neural mutual information estimator.
We conduct thorough experiments on publicly available datasets to validate the advantages of the proposed method over state-of-the-art approaches.
arXiv Detail & Related papers (2021-08-11T21:17:02Z) - Heterogeneous Contrastive Learning: Encoding Spatial Information for
Compact Visual Representations [183.03278932562438]
This paper presents an effective approach that adds spatial information to the encoding stage to alleviate the learning inconsistency between the contrastive objective and strong data augmentation operations.
We show that our approach achieves higher efficiency in visual representations and thus delivers a key message to inspire the future research of self-supervised visual representation learning.
arXiv Detail & Related papers (2020-11-19T16:26:25Z) - Self-Supervised Domain Adaptation with Consistency Training [0.2462953128215087]
We consider the problem of unsupervised domain adaptation for image classification.
We create a self-supervised pretext task by augmenting the unlabeled data with a certain type of transformation.
We force the representation of the augmented data to be consistent with that of the original data.
arXiv Detail & Related papers (2020-10-15T06:03:47Z) - Mining Implicit Entity Preference from User-Item Interaction Data for
Knowledge Graph Completion via Adversarial Learning [82.46332224556257]
We propose a novel adversarial learning approach by leveraging user interaction data for the Knowledge Graph Completion task.
Our generator is isolated from user interaction data, and serves to improve the performance of the discriminator.
To discover implicit entity preference of users, we design an elaborate collaborative learning algorithms based on graph neural networks.
arXiv Detail & Related papers (2020-03-28T05:47:33Z)
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.