Transformers as Meta-Learners for Implicit Neural Representations

• URL: http://arxiv.org/abs/2208.02801v2
• Date: Fri, 5 Aug 2022 06:49:41 GMT
• Title: Transformers as Meta-Learners for Implicit Neural Representations
• Authors: Yinbo Chen, Xiaolong Wang
• Abstract summary: Implicit Neural Representations (INRs) have emerged and shown their benefits over discrete representations in recent years. We propose a formulation that uses Transformers as hypernetworks for INRs, where it can directly build the whole set of INR weights. We demonstrate the effectiveness of our method for building INRs in different tasks and domains, including 2D image regression and view synthesis for 3D objects.
• Score: 10.673855995948736
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Implicit Neural Representations (INRs) have emerged and shown their benefits over discrete representations in recent years. However, fitting an INR to the given observations usually requires optimization with gradient descent from scratch, which is inefficient and does not generalize well with sparse observations. To address this problem, most of the prior works train a hypernetwork that generates a single vector to modulate the INR weights, where the single vector becomes an information bottleneck that limits the reconstruction precision of the output INR. Recent work shows that the whole set of weights in INR can be precisely inferred without the single-vector bottleneck by gradient-based meta-learning. Motivated by a generalized formulation of gradient-based meta-learning, we propose a formulation that uses Transformers as hypernetworks for INRs, where it can directly build the whole set of INR weights with Transformers specialized as set-to-set mapping. We demonstrate the effectiveness of our method for building INRs in different tasks and domains, including 2D image regression and view synthesis for 3D objects. Our work draws connections between the Transformer hypernetworks and gradient-based meta-learning algorithms and we provide further analysis for understanding the generated INRs.

Related papers

• Single-Layer Learnable Activation for Implicit Neural Representation (SL$^{2}$A-INR) [6.572456394600755]
  Implicit Representation (INR) leveraging a neural network to transform coordinate input into corresponding attributes has driven significant advances in vision-related domains. We propose SL$2$A-INR with a single-layer learnable activation function, prompting the effectiveness of traditional ReLU-baseds. Our method performs superior across diverse tasks, including image representation, 3D shape reconstruction, single image super-resolution, CT reconstruction, and novel view.
  arXiv  Detail & Related papers  (2024-09-17T02:02:15Z)
• Attention Beats Linear for Fast Implicit Neural Representation Generation [13.203243059083533]
  We propose Attention-based Localized INR (ANR) composed of a localized attention layer (LAL) and a global representation vector. With instance-specific representation and instance-agnostic ANR parameters, the target signals are well reconstructed as a continuous function.
  arXiv  Detail & Related papers  (2024-07-22T03:52:18Z)
• Transformers meet Neural Algorithmic Reasoners [16.5785372289558]
  We propose a novel approach that combines the Transformer's language understanding with the robustness of graph neural network (GNN)-based neural algorithmic reasoners (NARs) We evaluate our resulting TransNAR model on CLRS-Text, the text-based version of the CLRS-30 benchmark, and demonstrate significant gains over Transformer-only models for algorithmic reasoning.
  arXiv  Detail & Related papers  (2024-06-13T16:42:06Z)
• Locality-Aware Generalizable Implicit Neural Representation [54.93702310461174]
  Generalizable implicit neural representation (INR) enables a single continuous function to represent multiple data instances. We propose a novel framework for generalizable INR that combines a transformer encoder with a locality-aware INR decoder. Our framework significantly outperforms previous generalizable INRs and validates the usefulness of the locality-aware latents for downstream tasks.
  arXiv  Detail & Related papers  (2023-10-09T11:26:58Z)
• B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers [97.75725574963197]
  We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training. We show that a sequence of such transformations induces a single linear transformation that faithfully summarises the full model computations. We show that the resulting explanations are of high visual quality and perform well under quantitative interpretability metrics.
  arXiv  Detail & Related papers  (2023-06-19T12:54:28Z)
• Regularize implicit neural representation by itself [48.194276790352006]
  This paper proposes a regularizer called Implicit Neural Representation Regularizer (INRR) to improve the generalization ability of the Implicit Neural Representation (INR) The proposed INRR is based on learned Dirichlet Energy (DE) that measures similarities between rows/columns of the matrix. The paper also reveals a series of properties derived from INRR, including momentum methods like convergence trajectory and multi-scale similarity.
  arXiv  Detail & Related papers  (2023-03-27T04:11:08Z)
• Signal Processing for Implicit Neural Representations [80.38097216996164]
  Implicit Neural Representations (INRs) encode continuous multi-media data via multi-layer perceptrons. Existing works manipulate such continuous representations via processing on their discretized instance. We propose an implicit neural signal processing network, dubbed INSP-Net, via differential operators on INR.
  arXiv  Detail & Related papers  (2022-10-17T06:29:07Z)
• B-cos Networks: Alignment is All We Need for Interpretability [136.27303006772294]
  We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training. A B-cos transform induces a single linear transform that faithfully summarises the full model computations. We show that it can easily be integrated into common models such as VGGs, ResNets, InceptionNets, and DenseNets.
  arXiv  Detail & Related papers  (2022-05-20T16:03:29Z)
• Improving the Sample-Complexity of Deep Classification Networks with Invariant Integration [77.99182201815763]
  Leveraging prior knowledge on intraclass variance due to transformations is a powerful method to improve the sample complexity of deep neural networks. We propose a novel monomial selection algorithm based on pruning methods to allow an application to more complex problems. We demonstrate the improved sample complexity on the Rotated-MNIST, SVHN and CIFAR-10 datasets.
  arXiv  Detail & Related papers  (2022-02-08T16:16:11Z)

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.