Search Results for author:
Found 17 papers, 14 papers with code
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 #4 on
Keyword Spotting
on Google Speech Commands
(Google Speech Commands V2 35 metric)
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.
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
Multi-Label Classification
on OpenImages-v6
BINAS: Bilinear Interpretable Neural Architecture Search
Practical use of neural networks often involves requirements on latency, energy and memory among others.
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
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.
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
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 #25 on
Action Recognition
on UCF101
(using extra training data)
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
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.
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.
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
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 #6 on
Fine-Grained Image Classification
on Oxford 102 Flowers
(using extra training data)
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
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.
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.
