Few-shot classification aims at leveraging knowledge learned in a deep learning model, in order to obtain good classification performance on new problems, where only a few labeled samples per class are available. Recent years have seen a fair number of works in the field, each one introducing their own methodology. A frequent problem, though, is the use of suboptimally trained models as a first building block, leading to doubts about whether proposed approaches bring gains if applied to more sophisticated pretrained models. In this work, we propose a simple way to train such models, with the aim of reaching top performance on multiple standardized benchmarks in the field. This methodology offers a new baseline on which to propose (and fairly compare) new techniques or adapt existing ones.

https://www.mdpi.com/2313-433X/8/7/179/pdf?version=1656087073

Easy—Ensemble Augmented-Shot-Y-Shaped Learning: State-of-the-Art Few-Shot Classification with Simple Components

Filter pruning is effective to reduce the computational costs of neural networks. Existing methods show that updating the previous pruned filter would enable large model capacity and achieve better performance. However, during the iterative pruning process, even if the network weights are updated to new values, the pruning criterion remains the same. In addition, when evaluating the filter importance, only the magnitude information of the filters is considered. However, in neural networks, filters do not work individually, but they would affect other filters. As a result, the magnitude information of each filter, which merely reflects the information of an individual filter itself, is not enough to judge the filter importance. To solve the above problems, we propose meta-attribute-based filter pruning (MFP). First, to expand the existing magnitude information-based pruning criteria, we introduce a new set of criteria to consider the geometric distance of filters. Additionally, to explicitly assess the current state of the network, we adaptively select the most suitable criteria for pruning via a meta-attribute, a property of the neural network at the current state. Experiments on two image classification benchmarks validate our method. For ResNet-50 on ILSVRC-2012, we could reduce more than 50% FLOPs with only 0.44% top-5 accuracy loss. 

/pdf/filter-pruning-by-switching-to-neighboring-cnns-with-good-3csn2925.pdf

Filter Pruning by Switching to Neighboring CNNs With Good Attributes

Though network pruning receives popularity in reducing the complexity of convolutional neural networks (CNNs), it remains an open issue to concurrently maintain model accuracy as well as achieve significant speedups on general CPUs. In this paper, we propose a novel 1xN pruning pattern to break this limitation. In particular, consecutive N output kernels with the same input channel index are grouped into one block, which serves as a basic pruning granularity of our pruning pattern. Our 1xN pattern prunes these blocks considered unimportant. We also provide a workflow of filter rearrangement that first rearranges the weight matrix in the output channel dimension to derive more influential blocks for accuracy improvements and then applies similar rearrangement to the next-layer weights in the input channel dimension to ensure correct convolutional operations. Moreover, the output computation after our 1xN pruning can be realized via a parallelized block-wise vectorized operation, leading to significant speedups on general CPUs. The efficacy of our pruning pattern is proved with experiments on ILSVRC-2012. For example, Given the pruning rate of 50% and N=4, our pattern obtains about 3.0% improvements over filter pruning in the top-1 accuracy of MobileNet-V2. Meanwhile, it obtains 56.04ms inference savings on Cortex-A7 CPU over weight pruning. Our project is made available at https://github.com/lmbxmu/1xN.

1xN Pattern for Pruning Convolutional Neural Networks.

There is an inherent need for machines to have a notion of how entities within their environment behave and to anticipate changes in the near future. In this work, we focus on anticipating future appearance, given the current frame of a video. Typical methods are used either to predict the next frame of a video or to predict future optical flow or trajectories based on a single video frame. This work presents an experiment on stretching the ability of CNNs to anticipate appearance at an arbitrarily given near future time, by conditioning our predicted video frames on a continuous time variable. We show that CNNs can learn an intrinsic representation of typical appearance changes over time and successfully generate realistic predictions in one step-at a deliberate time difference in the near future. The method is evaluated on the KTH human actions dataset and compared to a baseline consisting of an analogous CNN architecture that is not time-aware.

https://hal.inria.fr/hal-01467064/document

One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network

Few-shot learning aims at leveraging knowledge learned by one or more deep learning models, in order to obtain good classification performance on new problems, where only a few labeled samples per class are available. Recent years have seen a fair number of works in the field, introducing methods with numerous ingredients. A frequent problem, though, is the use of suboptimally trained models to extract knowledge, leading to interrogations on whether proposed approaches bring gains compared to using better initial models without the introduced ingredients. In this work, we propose a simple methodology, that reaches or even beats state of the art performance on multiple standardized benchmarks of the field, while adding almost no hyperparameters or parameters to those used for training the initial deep learning models on the generic dataset. This methodology offers a new baseline on which to propose (and fairly compare) new techniques or adapt existing ones.

EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients

Since the rate at which new content is uploaded to the Internet has reached unprecedented marks, knowing the popularity of online content, especially video, is of importance for network management, recommendation schemes, service design, advertising planning, and so on. Despite the fact that various models have been developed, few of them address the short-term popularity prediction. Toward this goal, we exploit the self-attention mechanism of the Transformer, a state-of-the-art model in neural machine translation, to forecast the values of multiple time series in the near future. Specifically, we propose an attention-based non-recursive neural network, a novel model that entirely dispenses with recurrence and convolutions, for time series prediction. Since our model is the combination of the input attention mechanism in the dual-stage attention-based recurrent neural network (DA-RNN) and the self-attention of Transformer, it is able to adaptively select the most relevant input sequences as well as capture the long-term dependencies across previous time steps to make the prediction. The experiments show the root mean square errors (RMSEs) achieved by our model are only 6.06 and 3.60 when testing on the NASDAQ 100 dataset and the views count of the top most popular videos on Youtube respectively, while the RMSEs of DA-RNN are 8.52 and 12.31. Hence, our model outperforms the baseline not only in time series prediction but also in contents popularity prediction aspect.

Attention-Based Neural Network: A Novel Approach for Predicting the Popularity of Online Content

Network pruning is an effective method to reduce the computational expense of over-parameterized neural networks for deployment on low-resource systems. Recent state-of-the-art techniques for retraining pruned networks such as weight rewinding and learning rate rewinding have been shown to outperform the traditional fine-tuning technique in recovering the lost accuracy (Renda et al., 2020), but so far it is unclear what accounts for such performance. In this work, we conduct extensive experiments to verify and analyze the uncanny effectiveness of learning rate rewinding. We find that the reason behind the success of learning rate rewinding is the usage of a large learning rate. Similar phenomenon can be observed in other learning rate schedules that involve large learning rates, e.g., the 1-cycle learning rate schedule (Smith et al., 2019). By leveraging the right learning rate schedule in retraining, we demonstrate a counter-intuitive phenomenon in that randomly pruned networks could even achieve better performance than methodically pruned networks (fine-tuned with the conventional approach). Our results emphasize the cruciality of the learning rate schedule in pruned network retraining - a detail often overlooked by practitioners during the implementation of network pruning.

/pdf/network-pruning-that-matters-a-case-study-on-retraining-20y5xlhsbz.pdf

Network Pruning That Matters: A Case Study on Retraining Variants

Network pruning is one of the most dominant methods for reducing the heavy inference cost of deep neural networks. Existing methods often iteratively prune networks to attain high compression ratio without incurring significant loss in performance. However, we argue that conventional methods for retraining pruned networks (i.e., using small, fixed learning rate) are inadequate as they completely ignore the benefits from snapshots of iterative pruning. In this work, we show that strong ensembles can be constructed from snapshots of iterative pruning, which achieve competitive performance and vary in network structure. Furthermore, we present simple, general and effective pipeline that generates strong ensembles of networks during pruning with large learning rate restarting, and utilizes knowledge distillation with those ensembles to improve the predictive power of compact models. In standard image classification benchmarks such as CIFAR and Tiny-Imagenet, we advance state-of-the-art pruning ratio of structured pruning by integrating simple l1-norm filters pruning into our pipeline. Specifically, we reduce 75-80% of total parameters and 65-70% MACs of numerous variants of ResNet architectures while having comparable or better performance than that of original networks. Code associate with this paper is made publicly available at this https URL.

pdf/paying-more-attention-to-snapshots-of-iterative-pruning-4tddjtegy9.pdf

Paying more attention to snapshots of Iterative Pruning: Improving Model Compression via Ensemble Distillation

Network pruning is one of the most dominant methods for reducing the heavy inference cost of deep neural networks Existing methods often iteratively prune networks to attain high compression ratio without incurring significant loss in performance However, we argue that conventional methods for retraining pruned networks (ie, using small, fixed learning rate) are inadequate as they completely ignore the benefits from snapshots of iterative pruning In this work, we show that strong ensembles can be constructed from snapshots of iterative pruning, which achieve competitive performance and vary in network structure Furthermore, we present simple, general and effective pipeline that generates strong ensembles of networks during pruning with large learning rate restarting, and utilizes knowledge distillation with those ensembles to improve the predictive power of compact models In standard image classification benchmarks such as CIFAR and Tiny-Imagenet, we advance state-of-the-art pruning ratio of structured pruning by integrating simple l1-norm filters pruning into our pipeline Specifically, we reduce 75-80% of total parameters and 65-70% MACs of numerous variants of ResNet architectures while having comparable or better performance than that of original networks Code associate with this paper is made publicly available at this https URL

/pdf/paying-more-attention-to-snapshots-of-iterative-pruning-2hdvmctyay.pdf

Paying more Attention to Snapshots of Iterative Pruning: Improving Model Compression via Ensemble Distillation.

Network pruning is an effective method to reduce the computational expense of over-parameterized neural networks for deployment on low-resource systems. Recent state-of-the-art techniques for retraining pruned networks such as weight rewinding and learning rate rewinding have been shown to outperform the traditional fine-tuning technique in recovering the lost accuracy (Renda et al., 2020), but so far it is unclear what accounts for such performance. In this work, we conduct extensive experiments to verify and analyze the uncanny effectiveness of learning rate rewinding. We find that the reason behind the success of learning rate rewinding is the usage of a large learning rate. Similar phenomenon can be observed in other learning rate schedules that involve large learning rates, e.g., the 1-cycle learning rate schedule (Smith et al., 2019). By leveraging the right learning rate schedule in retraining, we demonstrate a counter-intuitive phenomenon in that randomly pruned networks could even achieve better performance than methodically pruned networks (fine-tuned with the conventional approach). Our results emphasize the cruciality of the learning rate schedule in pruned network retraining - a detail often overlooked by practitioners during the implementation of network pruning. One-sentence Summary: We study the effective of different retraining mechanisms while doing pruning

Popular Tasks used by Researchers

How can I help with your research?

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

We encountered an error while loading the panel. Please try refreshing the page.

Something went wrong

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

Anyone with the link can view this chat. You can switch it back to private anytime.

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Duong H. Le

Author Tools

Chat about Author

Papers

Attention-Based Neural Network: A Novel Approach for Predicting the Popularity of Online Content

Network Pruning That Matters: A Case Study on Retraining Variants

Paying more attention to snapshots of Iterative Pruning: Improving Model Compression via Ensemble Distillation

Paying more Attention to Snapshots of Iterative Pruning: Improving Model Compression via Ensemble Distillation.

Network Pruning That Matters: A Case Study on Retraining Variants