Search Results for author:
Found 17 papers, 14 papers with code
TResNet: High Performance GPU-Dedicated Architecture
In this work, we introduce a series of architecture modifications that aim to boost neural networks' accuracy, while retaining their GPU training and inference efficiency.
Ranked #7 on
Fine-Grained Image Classification
on Oxford 102 Flowers
(using extra training data)
ImageNet-21K Pretraining for the Masses
ImageNet-1K serves as the primary dataset for pretraining deep learning models for computer vision tasks.
Ranked #2 on
Image Classification
on Stanford Cars
Asymmetric Loss For Multi-Label Classification
In this paper, we introduce a novel asymmetric loss ("ASL"), which operates differently on positive and negative samples.
Ranked #4 on
Multi-Label Classification
on NUS-WIDE
Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results
The scheme, named USI (Unified Scheme for ImageNet), is based on knowledge distillation and modern tricks.
ML-Decoder: Scalable and Versatile Classification Head
In this paper, we introduce ML-Decoder, a new attention-based classification head.
Ranked #2 on
Fine-Grained Image Classification
on Stanford Cars
(using extra training data)
An Image is Worth 16x16 Words, What is a Video Worth?
Methods that reach State of the Art (SotA) accuracy, usually make use of 3D convolution layers as a way to abstract the temporal information from video frames.
Ranked #23 on
Action Recognition
on UCF101
(using extra training data)
Multi-label Classification with Partial Annotations using Class-aware Selective Loss
We propose to estimate the class distribution using a dedicated temporary model, and we show its improved efficiency over a naive estimation computed using the dataset's partial annotations.
Ranked #1 on
Multi-Label Classification
on OpenImages-v6
End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network
While efficient architectures and a plethora of augmentations for end-to-end image classification tasks have been suggested and heavily investigated, state-of-the-art techniques for audio classifications still rely on numerous representations of the audio signal together with large architectures, fine-tuned from large datasets.
Ranked #2 on
Environmental Sound Classification
on UrbanSound8K
(using extra training data)
XNAS: Neural Architecture Search with Expert Advice
This paper introduces a novel optimization method for differential neural architecture search, based on the theory of prediction with expert advice.
HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search
Realistic use of neural networks often requires adhering to multiple constraints on latency, energy and memory among others.
Ranked #21 on
Neural Architecture Search
on ImageNet
Knapsack Pruning with Inner Distillation
Through this we produce compact architectures with the same FLOPs as EfficientNet-B0 and MobileNetV3 but with higher accuracy, by $1\%$ and $0. 3\%$ respectively on ImageNet, and faster runtime on GPU.
Ranked #3 on
Network Pruning
on ImageNet
ASAP: Architecture Search, Anneal and Prune
In this paper, we propose a differentiable search space that allows the annealing of architecture weights, while gradually pruning inferior operations.
PETA: Photo Albums Event Recognition using Transformers Attention
We address this gap with a tailor-made solution, combining the power of CNNs for image representation and transformers for album representation to perform global reasoning on image collection, offering a practical and efficient solution for photo albums event recognition.
BINAS: Bilinear Interpretable Neural Architecture Search
Practical use of neural networks often involves requirements on latency, energy and memory among others.
WeMix: How to Better Utilize Data Augmentation
To this end, we develop two novel algorithms, termed "AugDrop" and "MixLoss", to correct the data bias in the data augmentation.
A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks
We show that convergence to a global minimum is guaranteed for networks with widths quadratic in the sample size and linear in their depth at a time logarithmic in both.
Diverse Imagenet Models Transfer Better
Encouraged by the recent transferability results of self-supervised models, we propose a method that combines self-supervised and supervised pretraining to generate models with both high diversity and high accuracy, and as a result high transferability.
