Search Results for author:
Found 42 papers, 19 papers with code
LEF: Late-to-Early Temporal Fusion for LiDAR 3D Object Detection
We propose a late-to-early recurrent feature fusion scheme for 3D object detection using temporal LiDAR point clouds.
WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting
To study the effect of these modular approaches, design new paradigms that mitigate these limitations, and accelerate the development of end-to-end motion forecasting models, we augment the Waymo Open Motion Dataset (WOMD) with large-scale, high-quality, diverse LiDAR data for the motion forecasting task.
PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds
To alleviate the cost of hyperparameter tuning and iterative pseudo labeling, we develop a population-based data augmentation framework for 3D detection, named AutoPseudoAugment.
LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations
Data augmentations are important in training high-performance 3D object detectors for point clouds.
SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds
3D object detection in point clouds is a core component for modern robotics and autonomous driving systems.
LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds
Developing neural models that accurately understand objects in 3D point clouds is essential for the success of robotics and autonomous driving.
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
Cross-entropy loss and focal loss are the most common choices when training deep neural networks for classification problems.
Ranked #99 on
Image Classification
on ImageNet
(using extra training data)
Revisiting Multi-Scale Feature Fusion for Semantic Segmentation
It is commonly believed that high internal resolution combined with expensive operations (e. g. atrous convolutions) are necessary for accurate semantic segmentation, resulting in slow speed and large memory usage.
DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection
In this paper, we propose two novel techniques: InverseAug that inverses geometric-related augmentations, e. g., rotation, to enable accurate geometric alignment between lidar points and image pixels, and LearnableAlign that leverages cross-attention to dynamically capture the correlations between image and lidar features during fusion.
Occupancy Flow Fields for Motion Forecasting in Autonomous Driving
We propose Occupancy Flow Fields, a new representation for motion forecasting of multiple agents, an important task in autonomous driving.
Combined Scaling for Zero-shot Transfer Learning
Second, while increasing the dataset size and the model size has been the defacto method to improve the performance of deep learning models like BASIC, the effect of a large contrastive batch size on such contrastive-trained image-text models is not well-understood.
CoAtNet: Marrying Convolution and Attention for All Data Sizes
Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks.
Ranked #1 on
Image Classification
on GasHisSDB
EfficientNetV2: Smaller Models and Faster Training
By pretraining on the same ImageNet21k, our EfficientNetV2 achieves 87. 3% top-1 accuracy on ImageNet ILSVRC2012, outperforming the recent ViT by 2. 0% accuracy while training 5x-11x faster using the same computing resources.
Ranked #3 on
Image Classification
on Stanford Cars
Robust and Accurate Object Detection via Adversarial Learning
Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection.
Ranked #17 on
Object Detection
on COCO-O
MoViNets: Mobile Video Networks for Efficient Video Recognition
We present Mobile Video Networks (MoViNets), a family of computation and memory efficient video networks that can operate on streaming video for online inference.
Ranked #3 on
Action Classification
on Charades
Rethinking Co-design of Neural Architectures and Hardware Accelerators
In our work, we target the optimization of hardware and software configurations on an industry-standard edge accelerator.
Searching for Fast Model Families on Datacenter Accelerators
On top of our DC accelerator optimized neural architecture search space, we further propose a latency-aware compound scaling (LACS), the first multi-objective compound scaling method optimizing both accuracy and latency.
Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention
The scalability of Nystr\"{o}mformer enables application to longer sequences with thousands of tokens.
Ranked #13 on
Semantic Textual Similarity
on MRPC
(F1 metric)
PyGlove: Symbolic Programming for Automated Machine Learning
As a result, AutoML can be reformulated as an automated process of symbolic manipulation.
NAHAS: Neural Architecture and Hardware Accelerator Search
In this paper, we study the importance of co-designing neural architectures and hardware accelerators.
Training EfficientNets at Supercomputer Scale: 83% ImageNet Top-1 Accuracy in One Hour
EfficientNets are a family of state-of-the-art image classification models based on efficiently scaled convolutional neural networks.
Efficient Scale-Permuted Backbone with Learned Resource Distribution
Furthermore, SpineNet is built with a uniform resource distribution over operations.
Shape-Texture Debiased Neural Network Training
To prevent models from exclusively attending on a single cue in representation learning, we augment training data with images with conflicting shape and texture information (eg, an image of chimpanzee shape but with lemon texture) and, most importantly, provide the corresponding supervisions from shape and texture simultaneously.
Ranked #598 on
Image Classification
on ImageNet
Go Wide, Then Narrow: Efficient Training of Deep Thin Networks
This is achieved by layerwise imitation, that is, forcing the thin network to mimic the intermediate outputs of the wide network from layer to layer.
Smooth Adversarial Training
SAT also works well with larger networks: it helps EfficientNet-L1 to achieve 82. 2% accuracy and 58. 6% robustness on ImageNet, outperforming the previous state-of-the-art defense by 9. 5% for accuracy and 11. 6% for robustness.
AutoHAS: Efficient Hyperparameter and Architecture Search
Efficient hyperparameter or architecture search methods have shown remarkable results, but each of them is only applicable to searching for either hyperparameters (HPs) or architectures.
When Ensembling Smaller Models is More Efficient than Single Large Models
Ensembling is a simple and popular technique for boosting evaluation performance by training multiple models (e. g., with different initializations) and aggregating their predictions.
MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
By incorporating regular convolutions in the search space and directly optimizing the network architectures for object detection, we obtain a family of object detection models, MobileDets, that achieve state-of-the-art results across mobile accelerators.
BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models
Without extra retraining or post-processing steps, we are able to train a single set of shared weights on ImageNet and use these weights to obtain child models whose sizes range from 200 to 1000 MFLOPs.
Ranked #30 on
Neural Architecture Search
on ImageNet
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
We propose SpineNet, a backbone with scale-permuted intermediate features and cross-scale connections that is learned on an object detection task by Neural Architecture Search.
Ranked #9 on
Image Classification
on iNaturalist
Adversarial Examples Improve Image Recognition
We show that AdvProp improves a wide range of models on various image recognition tasks and performs better when the models are bigger.
Ranked #4 on
Domain Generalization
on VizWiz-Classification
EfficientDet: Scalable and Efficient Object Detection
Model efficiency has become increasingly important in computer vision.
Ranked #6 on
Object Detection
on COCO minival
(APS metric)
Search to Distill: Pearls are Everywhere but not the Eyes
Standard Knowledge Distillation (KD) approaches distill the knowledge of a cumbersome teacher model into the parameters of a student model with a pre-defined architecture.
Scaling Up Neural Architecture Search with Big Single-Stage Models
In this work, we propose BigNAS, an approach that simplifies this workflow and scales up neural architecture search to target a wide range of model sizes simultaneously.
Evo-NAS: Evolutionary-Neural Hybrid Agent for Architecture Search
We show that the Evo-NAS agent outperforms both neural and evolutionary agents when applied to architecture search for a suite of text and image classification benchmarks.
MixConv: Mixed Depthwise Convolutional Kernels
In this paper, we systematically study the impact of different kernel sizes, and observe that combining the benefits of multiple kernel sizes can lead to better accuracy and efficiency.
Ranked #733 on
Image Classification
on ImageNet
AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures
Learning to represent videos is a very challenging task both algorithmically and computationally.
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available.
Ranked #1 on
Medical Image Classification
on NCT-CRC-HE-100K
Searching for MobileNetV3
We achieve new state of the art results for mobile classification, detection and segmentation.
Ranked #8 on
Dichotomous Image Segmentation
on DIS-TE1
Neural Architecture Search Over a Graph Search Space
However, the success of NAS depends on the definition of the search space.
Evolutionary-Neural Hybrid Agents for Architecture Search
We show that the Evo-NAS agent outperforms both neural and evolutionary agents when applied to architecture search for a suite of text and image classification benchmarks.
MnasNet: Platform-Aware Neural Architecture Search for Mobile
In this paper, we propose an automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency.
Ranked #829 on
Image Classification
on ImageNet
(using extra training data)
