Search Results for author:
Found 28 papers, 10 papers with code
Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-time Mobile Telepresence
Real-time and robust photorealistic avatars for telepresence in AR/VR have been highly desired for enabling immersive photorealistic telepresence.
Trainable Projected Gradient Method for Robust Fine-tuning
To solve this problem, we propose Trainable Projected Gradient Method (TPGM) to automatically learn the constraint imposed for each layer for a fine-grained fine-tuning regularization.
Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priors
Current popular backbones in computer vision, such as Vision Transformers (ViT) and ResNets are trained to perceive the world from 2D images.
Pruning Compact ConvNets for Efficient Inference
The resulting family of pruned models can consistently obtain better performance than existing FBNetV3 models at the same level of computation, and thus provide state-of-the-art results when trading off between computational complexity and generalization performance on the ImageNet benchmark.
Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
Vision Transformers (ViTs) have shown impressive performance but still require a high computation cost as compared to convolutional neural networks (CNNs), one reason is that ViTs' attention measures global similarities and thus has a quadratic complexity with the number of input tokens.
3D-Aware Encoding for Style-based Neural Radiance Fields
In the first stage, we introduce a base encoder that converts the input image to a latent code.
Token Merging: Your ViT But Faster
Off-the-shelf, ToMe can 2x the throughput of state-of-the-art ViT-L @ 512 and ViT-H @ 518 models on images and 2. 2x the throughput of ViT-L on video with only a 0. 2-0. 3% accuracy drop in each case.
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP
To address this, we propose to finetune CLIP on a collection of masked image regions and their corresponding text descriptions.
Hydra Attention: Efficient Attention with Many Heads
While transformers have begun to dominate many tasks in vision, applying them to large images is still computationally difficult.
Open-Set Semi-Supervised Object Detection
To address this problem, we consider online and offline OOD detection modules, which are integrated with SSOD methods.
NASRec: Weight Sharing Neural Architecture Search for Recommender Systems
To overcome the data multi-modality and architecture heterogeneity challenges in the recommendation domain, NASRec establishes a large supernet (i. e., search space) to search the full architectures.
Cross-Domain Adaptive Teacher for Object Detection
To mitigate this problem, we propose a teacher-student framework named Adaptive Teacher (AT) which leverages domain adversarial learning and weak-strong data augmentation to address the domain gap.
FBNetV5: Neural Architecture Search for Multiple Tasks in One Run
To tackle these challenges, we propose FBNetV5, a NAS framework that can search for neural architectures for a variety of vision tasks with much reduced computational cost and human effort.
Ranked #7 on
Neural Architecture Search
on ImageNet
An Investigation on Hardware-Aware Vision Transformer Scaling
In particular, when transferred to PiT, our scaling strategies lead to a boosted ImageNet top-1 accuracy of from $74. 6\%$ to $76. 7\%$ ($\uparrow2. 1\%$) under the same 0. 7G FLOPs; and when transferred to the COCO object detection task, the average precision is boosted by $\uparrow0. 7\%$ under a similar throughput on a V100 GPU.
Adaptive Unbiased Teacher for Cross-Domain Object Detection
This enables the student model to capture domain-invariant features.
Visual Transformers: Where Do Transformers Really Belong in Vision Models?
A recent trend in computer vision is to replace convolutions with transformers.
FP-NAS: Fast Probabilistic Neural Architecture Search
Furthermore, to search fast in the multi-variate space, we propose a coarse-to-fine strategy by using a factorized distribution at the beginning which can reduce the number of architecture parameters by over an order of magnitude.
Fully Dynamic Inference with Deep Neural Networks
Modern deep neural networks are powerful and widely applicable models that extract task-relevant information through multi-level abstraction.
Visual Transformers: Token-based Image Representation and Processing for Computer Vision
In this work, we challenge this paradigm by (a) representing images as semantic visual tokens and (b) running transformers to densely model token relationships.
FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining
To address this, we present Neural Architecture-Recipe Search (NARS) to search both (a) architectures and (b) their corresponding training recipes, simultaneously.
Ranked #5 on
Neural Architecture Search
on ImageNet
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
We propose a masking mechanism for feature map reuse, so that memory and computational costs stay nearly constant as the search space expands.
Ranked #68 on
Neural Architecture Search
on ImageNet
STEERAGE: Synthesis of Neural Networks Using Architecture Search and Grow-and-Prune Methods
On MNIST dataset, our CNN architecture achieves an error rate of 0. 66%, with 8. 6x fewer parameters compared to the LeNet-5 baseline.
DiabDeep: Pervasive Diabetes Diagnosis based on Wearable Medical Sensors and Efficient Neural Networks
For server (edge) side inference, we achieve a 96. 3% (95. 3%) accuracy in classifying diabetics against healthy individuals, and a 95. 7% (94. 6%) accuracy in distinguishing among type-1/type-2 diabetic, and healthy individuals.
Incremental Learning Using a Grow-and-Prune Paradigm with Efficient Neural Networks
Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications.
ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation
We formulate platform-aware NN architecture search in an optimization framework and propose a novel algorithm to search for optimal architectures aided by efficient accuracy and resource (latency and/or energy) predictors.
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
Due to this, previous neural architecture search (NAS) methods are computationally expensive.
Ranked #838 on
Image Classification
on ImageNet
Grow and Prune Compact, Fast, and Accurate LSTMs
To address these problems, we propose a hidden-layer LSTM (H-LSTM) that adds hidden layers to LSTM's original one level non-linear control gates.
NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm
To address these problems, we introduce a network growth algorithm that complements network pruning to learn both weights and compact DNN architectures during training.
