REST: Performance Improvement of a Black Box Model via RL-based Spatial
Transformation
- URL: http://arxiv.org/abs/2002.06610v1
- Date: Sun, 16 Feb 2020 16:15:59 GMT
- Title: REST: Performance Improvement of a Black Box Model via RL-based Spatial
Transformation
- Authors: Jae Myung Kim, Hyungjin Kim, Chanwoo Park, and Jungwoo Lee
- Abstract summary: We study robustness to geometric transformations in a specific condition where the black-box image classifier is given.
We propose an additional learner, emphREinforcement Spatial Transform (REST), that transforms the warped input data into samples regarded as in-distribution by the black-box models.
- Score: 15.691668909002892
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In recent years, deep neural networks (DNN) have become a highly active area
of research, and shown remarkable achievements on a variety of computer vision
tasks. DNNs, however, are known to often make overconfident yet incorrect
predictions on out-of-distribution samples, which can be a major obstacle to
real-world deployments because the training dataset is always limited compared
to diverse real-world samples. Thus, it is fundamental to provide guarantees of
robustness to the distribution shift between training and test time when we
construct DNN models in practice. Moreover, in many cases, the deep learning
models are deployed as black boxes and the performance has been already
optimized for a training dataset, thus changing the black box itself can lead
to performance degradation. We here study the robustness to the geometric
transformations in a specific condition where the black-box image classifier is
given. We propose an additional learner, \emph{REinforcement Spatial Transform
learner (REST)}, that transforms the warped input data into samples regarded as
in-distribution by the black-box models. Our work aims to improve the
robustness by adding a REST module in front of any black boxes and training
only the REST module without retraining the original black box model in an
end-to-end manner, i.e. we try to convert the real-world data into training
distribution which the performance of the black-box model is best suited for.
We use a confidence score that is obtained from the black-box model to
determine whether the transformed input is drawn from in-distribution. We
empirically show that our method has an advantage in generalization to
geometric transformations and sample efficiency.
Related papers
- B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable [53.848005910548565]
'B-cosification' is a novel approach to transform existing pre-trained models to become inherently interpretable.
We find that B-cosification can yield models that are on par with B-cos models trained from scratch in terms of interpretability.
arXiv Detail & Related papers (2024-11-01T16:28:11Z) - Transferable Post-training via Inverse Value Learning [83.75002867411263]
We propose modeling changes at the logits level during post-training using a separate neural network (i.e., the value network)
After training this network on a small base model using demonstrations, this network can be seamlessly integrated with other pre-trained models during inference.
We demonstrate that the resulting value network has broad transferability across pre-trained models of different parameter sizes.
arXiv Detail & Related papers (2024-10-28T13:48:43Z) - Cross-Domain Transfer Learning with CoRTe: Consistent and Reliable
Transfer from Black-Box to Lightweight Segmentation Model [25.3403116022412]
CoRTe is a pseudo-labelling function that extracts reliable knowledge from a black-box source model.
We benchmark CoRTe on two synthetic-to-real settings, demonstrating remarkable results when using black-box models to transfer knowledge on lightweight models for a target data distribution.
arXiv Detail & Related papers (2024-02-20T16:35:14Z) - Mafin: Enhancing Black-Box Embeddings with Model Augmented Fine-Tuning [13.211063836237468]
We introduce Model augmented fine-tuning (Mafin) -- a novel approach for fine-tuning a black-box embedding model by augmenting it with a trainable embedding model.
Our results demonstrate that Mafin significantly enhances the performance of the black-box embeddings by only requiring the training of a small augmented model.
arXiv Detail & Related papers (2024-02-19T14:33:24Z) - SHAPNN: Shapley Value Regularized Tabular Neural Network [4.587122314291091]
We present SHAPNN, a novel deep data modeling architecture designed for supervised learning.
Our neural network is trained using standard backward propagation optimization methods, and is regularized with realtime estimated Shapley values.
We evaluate our method on various publicly available datasets and compare it with state-of-the-art deep neural network models.
arXiv Detail & Related papers (2023-09-15T22:45:05Z) - DREAM: Domain-free Reverse Engineering Attributes of Black-box Model [51.37041886352823]
We propose a new problem of Domain-agnostic Reverse Engineering the Attributes of a black-box target model.
We learn a domain-agnostic model to infer the attributes of a target black-box model with unknown training data.
arXiv Detail & Related papers (2023-07-20T16:25:58Z) - How to Robustify Black-Box ML Models? A Zeroth-Order Optimization
Perspective [74.47093382436823]
We address the problem of black-box defense: How to robustify a black-box model using just input queries and output feedback?
We propose a general notion of defensive operation that can be applied to black-box models, and design it through the lens of denoised smoothing (DS)
We empirically show that ZO-AE-DS can achieve improved accuracy, certified robustness, and query complexity over existing baselines.
arXiv Detail & Related papers (2022-03-27T03:23:32Z) - MEMO: Test Time Robustness via Adaptation and Augmentation [131.28104376280197]
We study the problem of test time robustification, i.e., using the test input to improve model robustness.
Recent prior works have proposed methods for test time adaptation, however, they each introduce additional assumptions.
We propose a simple approach that can be used in any test setting where the model is probabilistic and adaptable.
arXiv Detail & Related papers (2021-10-18T17:55:11Z) - A Novel DNN Training Framework via Data Sampling and Multi-Task
Optimization [7.001799696806368]
We propose a novel framework to train DNN models.
It generates multiple pairs of training and validation sets from the gross training set via random splitting.
It outputs the best, among all trained models, which has the overall best performance across the validation sets from all pairs.
arXiv Detail & Related papers (2020-07-02T10:58:57Z) - Diversity inducing Information Bottleneck in Model Ensembles [73.80615604822435]
In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction.
We explicitly optimize a diversity inducing adversarial loss for learning latent variables and thereby obtain diversity in the output predictions necessary for modeling multi-modal data.
Compared to the most competitive baselines, we show significant improvements in classification accuracy, under a shift in the data distribution.
arXiv Detail & Related papers (2020-03-10T03:10:41Z)
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.