Search Results for author:
Found 32 papers, 22 papers with code
Learning Symmetrization for Equivariance with Orbit Distance Minimization
We present a general framework for symmetrizing an arbitrary neural-network architecture and making it equivariant with respect to a given group.
3D Denoisers are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation
Pretraining molecular representations from large unlabeled data is essential for molecular property prediction due to the high cost of obtaining ground-truth labels.
MetaWeather: Few-Shot Weather-Degraded Image Restoration
Real-world weather conditions are intricate and often occur concurrently.
Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance
In contrary to equivariant architectures, we use an arbitrary base model such as an MLP or a transformer and symmetrize it to be equivariant to the given group by employing a small equivariant network that parameterizes the probabilistic distribution underlying the symmetrization.
Ranked #1 on
Link Prediction
on PCQM-Contact
(using extra training data)
Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
We propose Visual Token Matching (VTM), a universal few-shot learner for arbitrary dense prediction tasks.
Towards End-to-End Generative Modeling of Long Videos with Memory-Efficient Bidirectional Transformers
However, the transformers are prohibited from directly learning the long-term dependency in videos due to the quadratic complexity of self-attention, and inherently suffering from slow inference time and error propagation due to the autoregressive process.
Ranked #24 on
Video Generation
on UCF-101
Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost
The forward and backward cost are thus linear to the number of edges, which each attention head can also choose flexibly based on the input.
Equivariant Hypergraph Neural Networks
Many problems in computer vision and machine learning can be cast as learning on hypergraphs that represent higher-order relations.
Diverse Generative Perturbations on Attention Space for Transferable Adversarial Attacks
Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attention due to their practicality.
Pure Transformers are Powerful Graph Learners
We show that standard Transformers without graph-specific modifications can lead to promising results in graph learning both in theory and practice.
Ranked #15 on
Graph Regression
on PCQM4Mv2-LSC
Part-based Pseudo Label Refinement for Unsupervised Person Re-identification
In this paper, we propose a novel Part-based Pseudo Label Refinement (PPLR) framework that reduces the label noise by employing the complementary relationship between global and part features.
Ranked #3 on
Unsupervised Vehicle Re-Identification
on VeRi-776
Learning to Generate Novel Classes for Deep Metric Learning
Motivated by this, we introduce a new data augmentation approach that synthesizes novel classes and their embedding vectors.
Multi-View Representation Learning via Total Correlation Objective
Multi-View Representation Learning (MVRL) aims to discover a shared representation of observations from different views with the complex underlying correlation.
Learning Continuous Representation of Audio for Arbitrary Scale Super Resolution
To obtain a continuous representation of audio and enable super resolution for arbitrary scale factor, we propose a method of implicit neural representation, coined Local Implicit representation for Super resolution of Arbitrary scale (LISA).
Multi-Task Neural Processes
To this end, we propose Multi-Task Neural Processes (MTNPs), an extension of NPs designed to jointly infer tasks realized from multiple stochastic processes.
Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs
We present a generalization of Transformers to any-order permutation invariant data (sets, graphs, and hypergraphs).
Ranked #5 on
Graph Regression
on PCQM4M-LSC
(Validation MAE metric)
Multi-Task Processes
Neural Processes (NPs) consider a task as a function realized from a stochastic process and flexibly adapt to unseen tasks through inference on functions.
Transformers Generalize DeepSets and Can be Extended to Graphs & Hypergraphs
We present a generalization of Transformers to any-order permutation invariant data (sets, graphs, and hypergraphs).
Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction
Despite the recent advances in the literature, existing approaches are limited to moderately short-term prediction (less than a few seconds), while extrapolating it to a longer future quickly leads to destruction in structure and content.
SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data
Generative modeling of set-structured data, such as point clouds, requires reasoning over local and global structures at various scales.
Ranked #3 on
Point Cloud Generation
on ShapeNet Car
Improving Unsupervised Image Clustering With Robust Learning
Unsupervised image clustering methods often introduce alternative objectives to indirectly train the model and are subject to faulty predictions and overconfident results.
Ranked #1 on
Image Clustering
on CIFAR-100
(Train Set metric, using extra
training data)
Variational Interaction Information Maximization for Cross-domain Disentanglement
Grounded in information theory, we cast the simultaneous learning of domain-invariant and domain-specific representations as a joint objective of multiple information constraints, which does not require adversarial training or gradient reversal layers.
High-Fidelity Synthesis with Disentangled Representation
Despite the simplicity, we show that the proposed method is highly effective, achieving comparable image generation quality to the state-of-the-art methods using the disentangled representation.
Diversity-Sensitive Conditional Generative Adversarial Networks
We propose a simple yet highly effective method that addresses the mode-collapse problem in the Conditional Generative Adversarial Network (cGAN).
Learning Hierarchical Semantic Image Manipulation through Structured Representations
In this work, we present a novel hierarchical framework for semantic image manipulation.
Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis
We propose a novel hierarchical approach for text-to-image synthesis by inferring semantic layout.
Decomposing Motion and Content for Natural Video Sequence Prediction
To the best of our knowledge, this is the first end-to-end trainable network architecture with motion and content separation to model the spatiotemporal dynamics for pixel-level future prediction in natural videos.
Ranked #1 on
Video Prediction
on KTH
(Cond metric)
Weakly Supervised Semantic Segmentation using Web-Crawled Videos
Our goal is to overcome this limitation with no additional human intervention by retrieving videos relevant to target class labels from web repository, and generating segmentation labels from the retrieved videos to simulate strong supervision for semantic segmentation.
Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network
We propose a novel weakly-supervised semantic segmentation algorithm based on Deep Convolutional Neural Network (DCNN).
Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation
We propose a novel deep neural network architecture for semi-supervised semantic segmentation using heterogeneous annotations.
Learning Deconvolution Network for Semantic Segmentation
We propose a novel semantic segmentation algorithm by learning a deconvolution network.
Ranked #3 on
Curved Text Detection
on SCUT-CTW1500
Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
We propose an online visual tracking algorithm by learning discriminative saliency map using Convolutional Neural Network (CNN).
