Multi-layer Representation Learning for Robust OOD Image Classification

Aristotelis Ballas, Christos Diou
7/27/2022
cs.CVcs.LG

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Convolutional Neural Networks have become the norm in image classification. Nevertheless, their difficulty to maintain high accuracy across datasets has become apparent in the past few years. In order to utilize such models in real-world scenarios and applications, they must be able to provide trustworthy predictions on unseen data. In this paper, we argue that extracting features from a CNN's intermediate layers can assist in the model's final prediction. Specifically, we adapt the Hypercolumns method to a ResNet-18 and find a significant increase in the model's accuracy, when evaluating on the NICO dataset.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Generalizing GradCAM for Embedding Networks

84% match2024

Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network

84% match2025

KANICE: Kolmogorov-Arnold Networks with Interactive Convolutional Elements

84% match2 repos32024

An Architecture Combining Convolutional Neural Network (CNN) and Support Vector Machine (SVM) for Image Classification

83% match1 repo4012017

Minimal Sufficient Views: A DNN model making predictions with more evidence has higher accuracy

83% match2024

DL-CapsNet: A Deep and Light Capsule Network

83% match2025

Cite this paper

@article{ballas2022multilayer,
  title  = {Multi-layer Representation Learning for Robust OOD Image Classification},
  author = {Aristotelis Ballas and Christos Diou},
  year   = {2022},
  eprint = {2207.13678},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.13678v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.13678.svg)](https://codeofpaper.com/paper/2207.13678)

Discussion