Search Results for author:
Found 31 papers, 24 papers with code
A Hybrid Generative and Discriminative PointNet on Unordered Point Sets
This paper proposes GDPNet, the first hybrid Generative and Discriminative PointNet that extends JEM for point cloud classification and generation.
MatchXML: An Efficient Text-label Matching Framework for Extreme Multi-label Text Classification
We then extract the dense text representations from the fine-tuned Transformer.
Multi Label Text Classification
Multi-Label Text Classification
+3
M-EBM: Towards Understanding the Manifolds of Energy-Based Models
Despite its simplicity, M-EBM significantly improves unconditional EBMs in training stability and speed on a host of benchmark datasets, such as CIFAR10, CIFAR100, CelebA-HQ, and ImageNet 32x32.
Accounting for Temporal Variability in Functional Magnetic Resonance Imaging Improves Prediction of Intelligence
We compare the prediction performance for different intelligence measures based on static FC, dynamic FC, and region level time series acquired from the Adolescent Brain Cognitive Development (ABCD) study involving close to 7000 individuals.
APSNet: Attention Based Point Cloud Sampling
Traditional task-agnostic sampling methods, such as farthest point sampling (FPS), do not consider downstream tasks when sampling point clouds, and thus non-informative points to the tasks are often sampled.
Towards Bridging the Performance Gaps of Joint Energy-based Models
This question has recently been answered in the affirmative, introducing the field of Joint Energy-based Model (JEM), which achieves high classification accuracy and image generation quality simultaneously.
Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model
Diffusion Denoising Probability Models (DDPM) and Vision Transformer (ViT) have demonstrated significant progress in generative tasks and discriminative tasks, respectively, and thus far these models have largely been developed in their own domains.
Semantic Structure based Query Graph Prediction for Question Answering over Knowledge Graph
Therefore, this paper focuses on query graph generation from natural language questions.
ChiTransformer:Towards Reliable Stereo from Cues
Current stereo matching techniques are challenged by restricted searching space, occluded regions and sheer size.
Chitransformer: Towards Reliable Stereo From Cues
Current stereo matching techniques are challenged by restricted searching space, occluded regions and sheer size.
Ranked #2 on
Stereo Depth Estimation
on KITTI2015
(D1-all All metric)
Generative Dynamic Patch Attack
Extensive experiments on VGGFace, Traffic Sign and ImageNet show that GDPA achieves higher attack success rates than state-of-the-art patch attacks, while adversarially trained model with GDPA demonstrates superior robustness to adversarial patch attacks than competing methods.
JEM++: Improved Techniques for Training JEM
1) We propose a proximal SGLD to generate samples in the proximity of samples from the previous step, which improves the stability.
Improving Text-to-Image Synthesis Using Contrastive Learning
To address this issue, we propose a contrastive learning approach to improve the quality and enhance the semantic consistency of synthetic images.
Ranked #9 on
Text-to-Image Generation
on CUB
Dep-$L_0$: Improving $L_0$-based Network Sparsification via Dependency Modeling
We term our algorithm Dep-$L_0$ as it prunes networks via a dependency-enabled $L_0$ regularization.
Reducing Risk and Uncertainty of Deep Neural Networks on Diagnosing COVID-19 Infection
In this work, we introduce uncertainty estimation to detect confusing cases for expert referral to address the unreliability of state-of-the-art (SOTA) DNNs on COVID-19 detection.
Generative Max-Mahalanobis Classifiers for Image Classification, Generation and More
We show that our Generative MMC (GMMC) can be trained discriminatively, generatively, or jointly for image classification and generation.
A Unified Plug-and-Play Framework for Effective Data Denoising and Robust Abstention
The success of Deep Neural Networks (DNNs) highly depends on data quality.
Adversarial Privacy Preserving Graph Embedding against Inference Attack
In this paper, we propose Adversarial Privacy Graph Embedding (APGE), a graph adversarial training framework that integrates the disentangling and purging mechanisms to remove users' private information from learned node representations.
Learning with Multiplicative Perturbations
In this paper, we propose xAT and xVAT, new adversarial training algorithms, that generate \textbf{multiplicative} perturbations to input examples for robust training of DNNs.
Sparse Graph Attention Networks
Among the variants of GNNs, Graph Attention Networks (GATs) learn to assign dense attention coefficients over all neighbors of a node for feature aggregation, and improve the performance of many graph learning tasks.
Toward Filament Segmentation Using Deep Neural Networks
Despite the known challenges in the identification and characterization of filaments by the existing module, which in turn are inherited into any other module that intends to learn from such outputs, Mask R-CNN shows promising results.
Neural Plasticity Networks
To the best of our knowledge, this is the first learning framework that unifies network sparsification and network expansion in an end-to-end training pipeline.
Neural Image Compression and Explanation
Explaining the prediction of deep neural networks (DNNs) and semantic image compression are two active research areas of deep learning with a numerous of applications in decision-critical systems, such as surveillance cameras, drones and self-driving cars, where interpretable decision is critical and storage/network bandwidth is limited.
$L_0$-ARM: Network Sparsification via Stochastic Binary Optimization
Thanks to the flexibility of ARM, many smooth or non-smooth parametric functions, such as scaled sigmoid or hard sigmoid, can be used to parameterize this binary optimization problem and the unbiasness of the ARM estimator is retained, while the hard concrete estimator has to rely on the hard sigmoid function to achieve conditional computation and thus accelerated training.
Defense-VAE: A Fast and Accurate Defense against Adversarial Attacks
The proposed method is generic and can defend white-box and black-box attacks without the need of retraining the original CNN classifiers, and can further strengthen the defense by retraining CNN or end-to-end finetuning the whole pipeline.
Towards Robust Human Activity Recognition from RGB Video Stream with Limited Labeled Data
Due to lack of depth information, RGB video based activity recognition performs poorly compared to RGB-D video based solutions.
Parallelizing Word2Vec in Multi-Core and Many-Core Architectures
Word2vec is a widely used algorithm for extracting low-dimensional vector representations of words.
Extreme Stochastic Variational Inference: Distributed and Asynchronous
Moreover, it requires the parameters to fit in the memory of a single processor; this is problematic when the number of parameters is in billions.
Parallelizing Word2Vec in Shared and Distributed Memory
In combination, these techniques allow us to scale up the computation near linearly across cores and nodes, and process hundreds of millions of words per second, which is the fastest word2vec implementation to the best of our knowledge.
BlackOut: Speeding up Recurrent Neural Network Language Models With Very Large Vocabularies
One way to understand BlackOut is to view it as an extension of the DropOut strategy to the output layer, wherein we use a discriminative training loss and a weighted sampling scheme.
WordRank: Learning Word Embeddings via Robust Ranking
Then, based on this insight, we propose a novel framework WordRank that efficiently estimates word representations via robust ranking, in which the attention mechanism and robustness to noise are readily achieved via the DCG-like ranking losses.
