Search Results for author:
Found 32 papers, 15 papers with code
MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction
MVDiffusion++ achieves superior flexibility and scalability with two surprisingly simple ideas: 1) A ``pose-free architecture'' where standard self-attention among 2D latent features learns 3D consistency across an arbitrary number of conditional and generation views without explicitly using camera pose information; and 2) A ``view dropout strategy'' that discards a substantial number of output views during training, which reduces the training-time memory footprint and enables dense and high-resolution view synthesis at test time.
Taming Mode Collapse in Score Distillation for Text-to-3D Generation
In this paper, we reveal that the existing score distillation-based text-to-3D generation frameworks degenerate to maximal likelihood seeking on each view independently and thus suffer from the mode collapse problem, manifesting as the Janus artifact in practice.
SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity
In this paper, we reveal that the gradient estimation in score distillation is inherent to high variance.
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
On segment anything task such as zero-shot instance segmentation, our EfficientSAMs with SAMI-pretrained lightweight image encoders perform favorably with a significant gain (e. g., ~4 AP on COCO/LVIS) over other fast SAM models.
Ranked #3 on
Zero-Shot Instance Segmentation
on LVIS v1.0 val
Pose-Free Generalizable Rendering Transformer
To address this challenge, we introduce PF-GRT, a new Pose-Free framework for Generalizable Rendering Transformer, eliminating the need for pre-computed camera poses and instead leveraging feature-matching learned directly from data.
TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
Results demonstrate that our TODM Supernet either matches or surpasses the performance of manually tuned models by up to a relative of 3% better in word error rate (WER), while efficiently keeping the cost of training many models at a small constant.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
In addition, the proposed method achieves the SOTA performance in NAS for building fast machine translation models, yielding better latency-BLEU tradeoff compared to HAT, state-of-the-art NAS for MT.
PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion
Fusing 3D LiDAR features with 2D camera features is a promising technique for enhancing the accuracy of 3D detection, thanks to their complementary physical properties.
Fast Point Cloud Generation with Straight Flows
We perform evaluations on multiple 3D tasks and find that our PSF performs comparably to the standard diffusion model, outperforming other efficient 3D point cloud generation methods.
Temporally Consistent Online Depth Estimation in Dynamic Scenes
We present a framework named Consistent Online Dynamic Depth (CODD) to produce temporally consistent depth estimates in dynamic scenes in an online setting.
Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation
Therefore, we propose HRViT, which enhances ViTs to learn semantically-rich and spatially-precise multi-scale representations by integrating high-resolution multi-branch architectures with ViTs.
Ranked #24 on
Semantic Segmentation
on Cityscapes val
Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet
From wearables to powerful smart devices, modern automatic speech recognition (ASR) models run on a variety of edge devices with different computational budgets.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution
This paper improves the streaming transformer transducer for speech recognition by using non-causal convolution.
NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training
In this work, we observe that the poor performance is due to a gradient conflict issue: the gradients of different sub-networks conflict with that of the supernet more severely in ViTs than CNNs, which leads to early saturation in training and inferior convergence.
Ranked #7 on
Neural Architecture Search
on ImageNet
Noisy Training Improves E2E ASR for the Edge
We apply noisy training to improve both dense and sparse state-of-the-art Emformer models and observe consistent WER reduction.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Vision Transformers with Patch Diversification
To alleviate this problem, in this work, we introduce novel loss functions in vision transformer training to explicitly encourage diversity across patch representations for more discriminative feature extraction.
Ranked #19 on
Semantic Segmentation
on Cityscapes val
AlphaNet: Improved Training of Supernets with Alpha-Divergence
Weight-sharing NAS builds a supernet that assembles all the architectures as its sub-networks and jointly trains the supernet with the sub-networks.
Ranked #12 on
Neural Architecture Search
on ImageNet
KeepAugment: A Simple Information-Preserving Data Augmentation Approach
Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems.
AlphaMatch: Improving Consistency for Semi-supervised Learning with Alpha-divergence
Semi-supervised learning (SSL) is a key approach toward more data-efficient machine learning by jointly leverage both labeled and unlabeled data.
AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling
Our discovered model family, AttentiveNAS models, achieves top-1 accuracy from 77. 3% to 80. 7% on ImageNet, and outperforms SOTA models, including BigNAS and Once-for-All networks.
Ranked #21 on
Neural Architecture Search
on ImageNet
Stein Variational Gradient Descent With Matrix-Valued Kernels
Stein variational gradient descent (SVGD) is a particle-based inference algorithm that leverages gradient information for efficient approximate inference.
Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent
Designing energy-efficient networks is of critical importance for enabling state-of-the-art deep learning in mobile and edge settings where the computation and energy budgets are highly limited.
Splitting Steepest Descent for Growing Neural Architectures
We develop a progressive training approach for neural networks which adaptively grows the network structure by splitting existing neurons to multiple off-springs.
Improving Neural Language Modeling via Adversarial Training
Theoretically, we show that our adversarial mechanism effectively encourages the diversity of the embedding vectors, helping to increase the robustness of models.
Ranked #5 on
Language Modelling
on Penn Treebank (Word Level)
Variational Inference with Tail-adaptive f-Divergence
Variational inference with {\alpha}-divergences has been widely used in modern probabilistic machine learning.
Stein Variational Gradient Descent as Moment Matching
Stein variational gradient descent (SVGD) is a non-parametric inference algorithm that evolves a set of particles to fit a given distribution of interest.
Stein Variational Message Passing for Continuous Graphical Models
We propose a novel distributed inference algorithm for continuous graphical models, by extending Stein variational gradient descent (SVGD) to leverage the Markov dependency structure of the distribution of interest.
Learning to Draw Samples with Amortized Stein Variational Gradient Descent
We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference.
Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE
We propose a number of new algorithms for learning deep energy models and demonstrate their properties.
Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning
We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference.
Ranked #19 on
Conditional Image Generation
on CIFAR-10
(Inception score metric)
Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm
We propose a general purpose variational inference algorithm that forms a natural counterpart of gradient descent for optimization.
