paper-with-me

Papers

Reproducibility study of "LICO: Explainable Models with Language-Image Consistency"

2024-10-17 · Luan Fletcher, Robert van der Klis, Martin Sedláček, Stefan Vasilev, Christos Athanasiadis

The growing reproducibility crisis in machine learning has brought forward a need for careful examination of research findings. This paper investigates the claims made by Lei et al. (2023) regarding their proposed method, LICO, for enhancing post-hoc interpretability techniques and improving image classification performance. LICO leverages natural language supervision from a vision-language model to enrich feature representations and guide the learning process. We conduct a comprehensive reproducibility study, employing (Wide) ResNets and established interpretability methods like Grad-CAM and RISE. We were mostly unable to reproduce the authors' results. In particular, we did not find that LICO consistently led to improved classification performance or improvements in quantitative and qualitative measures of interpretability. Thus, our findings highlight the importance of rigorous evaluation and transparent reporting in interpretability research.

📄 PDF Abstract BibTeX arXiv:2410.13989

Code (1)

robertdvdk/lico-fact 공식 구현 pytorch

Tasks

Explainable Modelsimage-classificationImage ClassificationLanguage ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

LICO: Explainable Models with Language-Image COnsistency

2023-09-21 · NeurIPS 2023 11

Interpreting the decisions of deep learning models has been actively studied since the explosion of deep neural networks. One of the most convincing interpretation approaches is salience-based visual interpretation, such…

SiMiC: Context-Aware Silicon Microstructure Characterization Using Attention-Based Convolutional Neural Networks for Field-Emission Tip Analysis

2026-01-21 · Jing Jie Tan, Rupert Schreiner, Matthias Hausladen, Ali Asgharzade 외 arxiv

Accurate characterization of silicon microstructures is essential for advancing microscale fabrication, quality control, and device performance. Traditional analysis using Scanning Electron Microscopy (SEM) often require…

Reproducibility Study of "XRec: Large Language Models for Explainable Recommendation"

2025-10-06 · Ranjan Mishra, Julian I. Bibo, Quinten van Engelen, Henk Schaapman arxiv

In this study, we reproduced the work done in the paper "XRec: Large Language Models for Explainable Recommendation" by Ma et al. (2024). The original authors introduced XRec, a model-agnostic collaborative instruction-t…

Deep Learning Reproducibility and Explainable AI (XAI)

2022-02-23 · A. -M. Leventi-Peetz, T. Östreich

The nondeterminism of Deep Learning (DL) training algorithms and its influence on the explainability of neural network (NN) models are investigated in this work with the help of image classification examples. To discuss …

Deep LearningExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)image-classification+1

Can LLMs faithfully generate their layperson-understandable 'self'?: A Case Study in High-Stakes Domains

2024-11-25 · Arion Das, Asutosh Mishra, Amitesh Patel, Soumilya De 외

Large Language Models (LLMs) have significantly impacted nearly every domain of human knowledge. However, the explainability of these models esp. to laypersons, which are crucial for instilling trust, have been examined …