Enhancing Deep Neural Network Reliability with Refinement and Calibration
A new paper proposes methods to enhance the reliability of deep neural networks (DNNs) by focusing on calibration and refinement. The authors introduce a novel loss function and a unified training framework called RefCal, which jointly optimizes calibration, refinement, and accuracy. Their approach significantly outperforms existing methods in terms of accuracy and refinement metrics.
- ▪Deep neural networks often provide unreliable confidence estimates, which can undermine user trust.
- ▪The proposed RefCal framework improves DNN reliability by optimizing calibration, refinement, and accuracy simultaneously.
- ▪On the CIFAR-100-LT dataset, RefCal achieved superior performance compared to the widely used Correctness Ranking Loss.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.23249 |
| Publication time | Mon, 25 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-25T04:07:35.648Z |
| Last seen | 2026-05-25T04:07:35.648Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | JW6hR15djrG9 |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Machine Learning arXiv:2605.23249 (cs) [Submitted on 22 May 2026] Title:Enhancing Deep Neural Network Reliability with Refinement and Calibration Authors:Ramya Hebbalaguppe, Ajay Shastry, Soumya Suvra Ghosal, Chetan Arora View a PDF of the paper titled Enhancing Deep Neural Network Reliability with Refinement and Calibration, by Ramya Hebbalaguppe and Ajay Shastry and Soumya Suvra Ghosal and Chetan Arora View PDF HTML (experimental) Abstract:Although deep neural networks (DNNs) achieve high predictive accuracy, their confidence estimates are often unreliable, potentially compromising user trust in their decisions.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
