paper-with-me

Papers

A Comparative Study of Label-free Representation Quality Metrics in Deep Learning

2026-08-24 · Daniel Richards Arputharaj, Daniel Jönsson, Gabriel Eilertsen arxiv

We present a comparative study of label-free metrics for assessing the quality of representations in deep neural networks to understand their reliability under a wide variety of configurations. We group existing label-free metrics into three families based on their construction and analytically establish connections between metrics within the same family. We then characterise the sensitivity of spectral metrics through controlled synthetic experiments. Finally, all label-free metrics are evaluated against downstream task accuracy across a diverse set of 260 vision models on six datasets spanning generic object classification, fine-grained object classification, scene recognition and geospatial task, stratifying results by architecture class and training objective. We find that intrinsic dimensionality (ID) is the most reliable predictor among the metrics considered. However, the reliability of all metrics, including ID, is moderated by architecture class and training objective. Our results provide a clearer understanding of what label-free representation quality metrics measure, when they are reliable, and how to interpret them in practice.

📄 PDF Abstract BibTeX arXiv:2608.23182

Code (0)

등록된 구현이 없습니다.

Tasks

Scene Recognition

Similar Papers 제목 키워드 기반

A Comparative Study on Annotation Quality of Crowdsourcing and LLM via Label Aggregation

2024-01-18 · Jiyi Li

Whether Large Language Models (LLMs) can outperform crowdsourcing on the data annotation task is attracting interest recently. Some works verified this issue with the average performance of individual crowd workers and L…

LEViL: Label-Efficient Video Learning via Zero-Shot Distillation over VLM-Generated Pseudo-Label Spaces

2026-06-19 · Aslı Çelik arxiv

Supervised video pretraining is a common transfer learning practice for improving downstream action recognition performance. However, it requires large-scale labeled source datasets, and the effectiveness of the learned …

Action RecognitionTransfer Learning

Comparative Evaluation of Embedding Representations for Financial News Sentiment Analysis

2025-12-15 · Joyjit Roy, Samaresh Kumar Singh arxiv

Financial sentiment analysis enhances market understanding. However, standard Natural Language Processing (NLP) approaches encounter significant challenges when applied to small datasets. This study presents a comparativ…

Sentiment AnalysisFew-Shot LearningData Augmentation

Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods

2026-03-26 · Xuanru Zhou, Yiwen Shao, Wei-Cheng Tseng, Dong Yu arxiv

Current audio pre-training seeks to learn unified representations for broad audio understanding tasks, but it remains fragmented and is fundamentally bottlenecked by its reliance on weak, noisy, and scale-limited labels.…

Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models

2022-12-01 · Zhuowan Li, Cihang Xie, Benjamin Van Durme, Alan Yuille

Despite the impressive advancements achieved through vision-and-language pretraining, it remains unclear whether this joint learning paradigm can help understand each individual modality. In this work, we conduct a compa…

AttributePredictionRepresentation Learning