Efficient Transferability Assessment for Selection of Pre-trained Detectors
- URL: http://arxiv.org/abs/2403.09432v1
- Date: Thu, 14 Mar 2024 14:23:23 GMT
- Title: Efficient Transferability Assessment for Selection of Pre-trained Detectors
- Authors: Zhao Wang, Aoxue Li, Zhenguo Li, Qi Dou,
- Abstract summary: This paper studies the efficient transferability assessment of pre-trained object detectors.
We build up a detector transferability benchmark which contains a large and diverse zoo of pre-trained detectors.
Experimental results demonstrate that our method outperforms other state-of-the-art approaches in assessing transferability.
- Score: 63.21514888618542
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Large-scale pre-training followed by downstream fine-tuning is an effective solution for transferring deep-learning-based models. Since finetuning all possible pre-trained models is computational costly, we aim to predict the transferability performance of these pre-trained models in a computational efficient manner. Different from previous work that seek out suitable models for downstream classification and segmentation tasks, this paper studies the efficient transferability assessment of pre-trained object detectors. To this end, we build up a detector transferability benchmark which contains a large and diverse zoo of pre-trained detectors with various architectures, source datasets and training schemes. Given this zoo, we adopt 7 target datasets from 5 diverse domains as the downstream target tasks for evaluation. Further, we propose to assess classification and regression sub-tasks simultaneously in a unified framework. Additionally, we design a complementary metric for evaluating tasks with varying objects. Experimental results demonstrate that our method outperforms other state-of-the-art approaches in assessing transferability under different target domains while efficiently reducing wall-clock time 32$\times$ and requires a mere 5.2\% memory footprint compared to brute-force fine-tuning of all pre-trained detectors.
Related papers
- KITE: A Kernel-based Improved Transferability Estimation Method [7.859384515308456]
We introduce Kite, as a Kernel-based Improved Transferability Estimation method.
Kite is based on the key observations that the separability of the pre-trained features and the similarity of the pre-trained features to random features are two important factors for estimating transferability.
We evaluate the performance of Kite on a recently introduced large-scale model selection benchmark.
arXiv Detail & Related papers (2024-05-01T21:58:04Z) - ETran: Energy-Based Transferability Estimation [8.15331116331861]
We argue that quantifying whether the target dataset is in-distribution (IND) or out-of-distribution (OOD) for the pre-trained model is an important factor in the transferability estimation.
We use energy-based models to determine whether the target dataset is OOD or IND for the pre-trained model.
This is the first work that proposes transferability estimation for object detection task.
arXiv Detail & Related papers (2023-08-03T20:41:08Z) - On the Trade-off of Intra-/Inter-class Diversity for Supervised
Pre-training [72.8087629914444]
We study the impact of the trade-off between the intra-class diversity (the number of samples per class) and the inter-class diversity (the number of classes) of a supervised pre-training dataset.
With the size of the pre-training dataset fixed, the best downstream performance comes with a balance on the intra-/inter-class diversity.
arXiv Detail & Related papers (2023-05-20T16:23:50Z) - Label-Efficient Object Detection via Region Proposal Network
Pre-Training [58.50615557874024]
We propose a simple pretext task that provides an effective pre-training for the region proposal network (RPN)
In comparison with multi-stage detectors without RPN pre-training, our approach is able to consistently improve downstream task performance.
arXiv Detail & Related papers (2022-11-16T16:28:18Z) - Self-Distillation for Further Pre-training of Transformers [83.84227016847096]
We propose self-distillation as a regularization for a further pre-training stage.
We empirically validate the efficacy of self-distillation on a variety of benchmark datasets for image and text classification tasks.
arXiv Detail & Related papers (2022-09-30T02:25:12Z) - Few-Shot Adaptation of Pre-Trained Networks for Domain Shift [17.123505029637055]
Deep networks are prone to performance degradation when there is a domain shift between the source (training) data and target (test) data.
Recent test-time adaptation methods update batch normalization layers of pre-trained source models deployed in new target environments with streaming data to mitigate such performance degradation.
We propose a framework for few-shot domain adaptation to address the practical challenges of data-efficient adaptation.
arXiv Detail & Related papers (2022-05-30T16:49:59Z) - Improved Fine-tuning by Leveraging Pre-training Data: Theory and
Practice [52.11183787786718]
Fine-tuning a pre-trained model on the target data is widely used in many deep learning applications.
Recent studies have empirically shown that training from scratch has the final performance that is no worse than this pre-training strategy.
We propose a novel selection strategy to select a subset from pre-training data to help improve the generalization on the target task.
arXiv Detail & Related papers (2021-11-24T06:18:32Z) - Deep Ensembles for Low-Data Transfer Learning [21.578470914935938]
We study different ways of creating ensembles from pre-trained models.
We show that the nature of pre-training itself is a performant source of diversity.
We propose a practical algorithm that efficiently identifies a subset of pre-trained models for any downstream dataset.
arXiv Detail & Related papers (2020-10-14T07:59:00Z) - Parameter-Efficient Transfer from Sequential Behaviors for User Modeling
and Recommendation [111.44445634272235]
In this paper, we develop a parameter efficient transfer learning architecture, termed as PeterRec.
PeterRec allows the pre-trained parameters to remain unaltered during fine-tuning by injecting a series of re-learned neural networks.
We perform extensive experimental ablation to show the effectiveness of the learned user representation in five downstream tasks.
arXiv Detail & Related papers (2020-01-13T14:09:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.