Encouraging Disentangled and Convex Representation with Controllable
Interpolation Regularization
- URL: http://arxiv.org/abs/2112.03163v1
- Date: Mon, 6 Dec 2021 16:52:07 GMT
- Title: Encouraging Disentangled and Convex Representation with Controllable
Interpolation Regularization
- Authors: Yunhao Ge, Zhi Xu, Yao Xiao, Gan Xin, Yunkui Pang, and Laurent Itti
- Abstract summary: We focus on controllable disentangled representation learning (C-Dis-RL)
We propose a simple yet efficient method: Controllable Interpolation Regularization (CIR)
- Score: 15.725515910594725
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We focus on controllable disentangled representation learning (C-Dis-RL),
where users can control the partition of the disentangled latent space to
factorize dataset attributes (concepts) for downstream tasks. Two general
problems remain under-explored in current methods: (1) They lack comprehensive
disentanglement constraints, especially missing the minimization of mutual
information between different attributes across latent and observation domains.
(2) They lack convexity constraints in disentangled latent space, which is
important for meaningfully manipulating specific attributes for downstream
tasks. To encourage both comprehensive C-Dis-RL and convexity simultaneously,
we propose a simple yet efficient method: Controllable Interpolation
Regularization (CIR), which creates a positive loop where the disentanglement
and convexity can help each other. Specifically, we conduct controlled
interpolation in latent space during training and 'reuse' the encoder to help
form a 'perfect disentanglement' regularization. In that case, (a)
disentanglement loss implicitly enlarges the potential 'understandable'
distribution to encourage convexity; (b) convexity can in turn improve robust
and precise disentanglement. CIR is a general module and we merge CIR with
three different algorithms: ELEGANT, I2I-Dis, and GZS-Net to show the
compatibility and effectiveness. Qualitative and quantitative experiments show
improvement in C-Dis-RL and latent convexity by CIR. This further improves
downstream tasks: controllable image synthesis, cross-modality image
translation and zero-shot synthesis. More experiments demonstrate CIR can also
improve other downstream tasks, such as new attribute value mining, data
augmentation, and eliminating bias for fairness.
Related papers
- Double-Shot 3D Shape Measurement with a Dual-Branch Network [14.749887303860717]
We propose a dual-branch Convolutional Neural Network (CNN)-Transformer network (PDCNet) to process different structured light (SL) modalities.
Within PDCNet, a Transformer branch is used to capture global perception in the fringe images, while a CNN branch is designed to collect local details in the speckle images.
We show that our method can reduce fringe order ambiguity while producing high-accuracy results on a self-made dataset.
arXiv Detail & Related papers (2024-07-19T10:49:26Z) - Accelerating Distributed Optimization: A Primal-Dual Perspective on Local Steps [4.471962177124311]
In distributed machine learning, current algorithms that achieve optimal communication typically require strongly convex objectives.
We show (Accelerated) GAMS-Accelerated for communication rounds despite the Lagrangian being only in general.
arXiv Detail & Related papers (2024-07-02T22:14:54Z) - Closed-Loop Unsupervised Representation Disentanglement with $\beta$-VAE
Distillation and Diffusion Probabilistic Feedback [45.68054456449699]
Representation disentanglement may help AI fundamentally understand the real world and thus benefit both discrimination and generation tasks.
We propose a textbfCL-Disentanglement approach dubbed textbfCL-Dis.
Experiments demonstrate the superiority of CL-Dis on applications like real image manipulation and visual analysis.
arXiv Detail & Related papers (2024-02-04T05:03:22Z) - Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training.
We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
arXiv Detail & Related papers (2023-10-20T12:45:12Z) - Interpolation-based Correlation Reduction Network for Semi-Supervised
Graph Learning [49.94816548023729]
We propose a novel graph contrastive learning method, termed Interpolation-based Correlation Reduction Network (ICRN)
In our method, we improve the discriminative capability of the latent feature by enlarging the margin of decision boundaries.
By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discnative representation learning.
arXiv Detail & Related papers (2022-06-06T14:26:34Z) - Gleo-Det: Deep Convolution Feature-Guided Detector with Local Entropy
Optimization for Salient Points [5.955667705173262]
We propose to achieve fine constraint based on the requirement of repeatability while coarse constraint with guidance of deep convolution features.
With the guidance of convolution features, we define the cost function from both positive and negative sides.
arXiv Detail & Related papers (2022-04-27T12:40:21Z) - Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image
Translation [56.44946660061753]
This paper proposes a universal regularization technique called maximum spatial perturbation consistency (MSPC)
MSPC enforces a spatial perturbation function (T ) and the translation operator (G) to be commutative (i.e., TG = GT )
Our method outperforms the state-of-the-art methods on most I2I benchmarks.
arXiv Detail & Related papers (2022-03-23T19:59:04Z) - Contrastive Conditional Neural Processes [45.70735205041254]
Conditional Neural Processes(CNPs) bridge neural networks with probabilistic inference to approximate functions of Processes under meta-learning settings.
Two auxiliary contrastive branches are set up hierarchically, namely in-instantiation temporal contrastive learning(tt TCL) and cross-instantiation function contrastive learning(tt FCL)
We empirically show that tt TCL captures high-level abstraction of observations, whereas tt FCL helps identify underlying functions, which in turn provides more efficient representations.
arXiv Detail & Related papers (2022-03-08T10:08:45Z) - Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains.
We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
arXiv Detail & Related papers (2021-12-12T06:11:16Z) - Unpaired Adversarial Learning for Single Image Deraining with Rain-Space
Contrastive Constraints [61.40893559933964]
We develop an effective unpaired SID method which explores mutual properties of the unpaired exemplars by a contrastive learning manner in a GAN framework, named as CDR-GAN.
Our method performs favorably against existing unpaired deraining approaches on both synthetic and real-world datasets, even outperforms several fully-supervised or semi-supervised models.
arXiv Detail & Related papers (2021-09-07T10:00:45Z) - An Information Bottleneck Approach for Controlling Conciseness in
Rationale Extraction [84.49035467829819]
We show that it is possible to better manage this trade-off by optimizing a bound on the Information Bottleneck (IB) objective.
Our fully unsupervised approach jointly learns an explainer that predicts sparse binary masks over sentences, and an end-task predictor that considers only the extracted rationale.
arXiv Detail & Related papers (2020-05-01T23:26:41Z)
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.