paper-with-me

홈 › Papers

ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks

2024-01-01 · CVPR 2024 1 · Kai Han, Yunhe Wang, Jianyuan Guo, Enhua Wu

The large-scale visual pretraining has significantly improve the performance of large vision models. However we observe the low FLOPs pitfall that the existing low-FLOPs models cannot benefit from large-scale pretraining. In this paper we introduce a novel design principle termed ParameterNet aimed at augmenting the number of parameters in large-scale visual pretraining models while minimizing the increase in FLOPs. We leverage dynamic convolutions to incorporate additional parameters into the networks with only a marginal rise in FLOPs. The ParameterNet approach allows low-FLOPs networks to take advantage of large-scale visual pretraining. Furthermore we extend the ParameterNet concept to the language domain to enhance inference results while preserving inference speed. Experiments on the large-scale ImageNet-22K have shown the superiority of our ParameterNet scheme. For example ParameterNet-600M can achieve higher accuracy than the widely-used Swin Transformer (81.6% vs. 80.9%) and has much lower FLOPs (0.6G vs. 4.5G). The code will be released at https://parameternet.github.io/.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

All

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Stochastic Depth Stochastic Depth aims to shrink the depth of a network during training, while keeping it unchanged during testing. This is achieved by randomly dropping entire…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음

Similar Papers 제목 키워드 기반

ParameterNet: Parameters Are All You Need

2023-06-26 · Kai Han, Yunhe Wang, Jianyuan Guo, Enhua Wu

The large-scale visual pretraining has significantly improve the performance of large vision models. However, we observe the \emph{low FLOPs pitfall} that the existing low-FLOPs models cannot benefit from large-scale pre…

All

Neural Implicit Flow: a mesh-agnostic dimensionality reduction paradigm of spatio-temporal data

2022-04-07 · Shaowu Pan, Steven L. Brunton, J. Nathan Kutz

High-dimensional spatio-temporal dynamics can often be encoded in a low-dimensional subspace. Engineering applications for modeling, characterization, design, and control of such large-scale systems often rely on dimensi…

Dimensionality Reduction

Building a Large-scale Multimodal Knowledge Base System for Answering Visual Queries

2015-07-20 · Yuke Zhu, Ce Zhang, Christopher Ré, Li Fei-Fei

The complexity of the visual world creates significant challenges for comprehensive visual understanding. In spite of recent successes in visual recognition, today's vision systems would still struggle to deal with visua…

Knowledge Base ConstructionRetrieval

Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models

2023-12-22 · Guihong Li, Hsiang Hsu, Chun-Fu Chen, Radu Marculescu

The rapid growth of machine learning has spurred legislative initiatives such as ``the Right to be Forgotten,'' allowing users to request data removal. In response, ``machine unlearning'' proposes the selective removal o…

Machine Unlearningparameter-efficient fine-tuning

Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers

2024-01-03 · Aleksandar Stanić, Sergi Caelles, Michael Tschannen

Visual reasoning is dominated by end-to-end neural networks scaled to billions of model parameters and training examples. However, even the largest models struggle with compositional reasoning, generalization, fine-grain…

Question AnsweringVisual GroundingVisual Question AnsweringVisual Reasoning