Masked Completion via Structured Diffusion with White-Box Transformers

• URL: http://arxiv.org/abs/2404.02446v1
• Date: Wed, 3 Apr 2024 04:23:01 GMT
• Title: Masked Completion via Structured Diffusion with White-Box Transformers
• Authors: Druv Pai, Ziyang Wu, Sam Buchanan, Yaodong Yu, Yi Ma,
• Abstract summary: We provide the first instantiation of the white-box design paradigm that can be applied to large-scale unsupervised representation learning. We do this by exploiting a fundamental connection between diffusion, compression, and (masked) completion, deriving a deep transformer-like masked autoencoder architecture. CRATE-MAE demonstrates highly promising performance on large-scale imagery datasets.
• Score: 23.07048591213815
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern learning frameworks often train deep neural networks with massive amounts of unlabeled data to learn representations by solving simple pretext tasks, then use the representations as foundations for downstream tasks. These networks are empirically designed; as such, they are usually not interpretable, their representations are not structured, and their designs are potentially redundant. White-box deep networks, in which each layer explicitly identifies and transforms structures in the data, present a promising alternative. However, existing white-box architectures have only been shown to work at scale in supervised settings with labeled data, such as classification. In this work, we provide the first instantiation of the white-box design paradigm that can be applied to large-scale unsupervised representation learning. We do this by exploiting a fundamental connection between diffusion, compression, and (masked) completion, deriving a deep transformer-like masked autoencoder architecture, called CRATE-MAE, in which the role of each layer is mathematically fully interpretable: they transform the data distribution to and from a structured representation. Extensive empirical evaluations confirm our analytical insights. CRATE-MAE demonstrates highly promising performance on large-scale imagery datasets while using only ~30% of the parameters compared to the standard masked autoencoder with the same model configuration. The representations learned by CRATE-MAE have explicit structure and also contain semantic meaning. Code is available at https://github.com/Ma-Lab-Berkeley/CRATE .

Related papers

• (PASS) Visual Prompt Locates Good Structure Sparsity through a Recurrent HyperNetwork [60.889175951038496]
  Large-scale neural networks have demonstrated remarkable performance in different domains like vision and language processing. One of the key questions of structural pruning is how to estimate the channel significance. We propose a novel algorithmic framework, namely textttPASS. It is a tailored hyper-network to take both visual prompts and network weight statistics as input, and output layer-wise channel sparsity in a recurrent manner.
  arXiv  Detail & Related papers  (2024-07-24T16:47:45Z)
• How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model [4.215221129670858]
  We show that by introducing sparsity to generative hierarchical models of data, the task acquires insensitivity to spatial transformations that are discrete versions of smooth transformations. We quantify how the sample complexity of CNNs learning the SRHM depends on both the sparsity and hierarchical structure of the task.
  arXiv  Detail & Related papers  (2024-04-16T17:01:27Z)
• White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is? [27.58916930770997]
  We show a family of white-box transformer-like deep network architectures, named CRATE, which are mathematically fully interpretable. Experiments show that these networks, despite their simplicity, indeed learn to compress and sparsify representations of large-scale real-world image and text datasets.
  arXiv  Detail & Related papers  (2023-11-22T02:23:32Z)
• Emergence of Segmentation with Minimalistic White-Box Transformers [22.688777622988795]
  Previous works have shown that segmentation properties emerge in vision transformers (ViTs) trained using self-supervised methods such as DINO, but not in those trained on supervised classification tasks. In this study, we probe whether segmentation emerges in transformer-based models solely as a result of intricate self-supervised learning mechanisms. Our results suggest a path to design white-box foundation models that are simultaneously highly performant and mathematically fully interpretable.
  arXiv  Detail & Related papers  (2023-08-30T19:02:17Z)
• With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning [47.96387857237473]
  We devise a network which can perform attention over activations obtained while processing other training samples. Our memory models the distribution of past keys and values through the definition of prototype vectors. We demonstrate that our proposal can increase the performance of an encoder-decoder Transformer by 3.7 CIDEr points both when training in cross-entropy only and when fine-tuning with self-critical sequence training.
  arXiv  Detail & Related papers  (2023-08-23T18:53:00Z)
• Complex-Valued Autoencoders for Object Discovery [62.26260974933819]
  We propose a distributed approach to object-centric representations: the Complex AutoEncoder. We show that this simple and efficient approach achieves better reconstruction performance than an equivalent real-valued autoencoder on simple multi-object datasets. We also show that it achieves competitive unsupervised object discovery performance to a SlotAttention model on two datasets, and manages to disentangle objects in a third dataset where SlotAttention fails - all while being 7-70 times faster to train.
  arXiv  Detail & Related papers  (2022-04-05T09:25:28Z)
• SeqTR: A Simple yet Universal Network for Visual Grounding [88.03253818868204]
  We propose a simple yet universal network termed SeqTR for visual grounding tasks. We cast visual grounding as a point prediction problem conditioned on image and text inputs. Under this paradigm, visual grounding tasks are unified in our SeqTR network without task-specific branches or heads.
  arXiv  Detail & Related papers  (2022-03-30T12:52:46Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• Mapping the Internet: Modelling Entity Interactions in Complex Heterogeneous Networks [0.0]
  We propose a versatile, unified framework called HMill' for sample representation, model definition and training. We show an extension of the universal approximation theorem to the set of all functions realized by models implemented in the framework. We solve three different problems from the cybersecurity domain using the framework.
  arXiv  Detail & Related papers  (2021-04-19T21:32:44Z)
• Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior [80.5637175255349]
  We propose a new enriched prior based Dual-constrained Deep Semi-Supervised Coupled Factorization Network, called DS2CF-Net. To ex-tract hidden deep features, DS2CF-Net is modeled as a deep-structure and geometrical structure-constrained neural network. Our network can obtain state-of-the-art performance for representation learning and clustering.
  arXiv  Detail & Related papers  (2020-09-08T13:10:21Z)
• End-to-End Object Detection with Transformers [88.06357745922716]
  We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components. The main ingredients of the new framework, called DEtection TRansformer or DETR, are a set-based global loss.
  arXiv  Detail & Related papers  (2020-05-26T17:06:38Z)

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.