Jose Oramas

4 papers · 2019–2025 · 2 conferences · across top CS/AI conferences

Achievements

🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (2) 🏃 Academic Marathon (6) 🐝 Cross-Pollinator (13) 🧭 Keyword Pioneer

Conferences

ICLR (3) WACV (1)

Top co-authors

Thomas Dooms (1) Tinne Tuytelaars (1) Benjamin Vandersmissen (1) Hamed Behzadi-Khormouji (1) Alice Rigg (1) Michael T Pearce (1) Lee Sharkey (1) Lucas Deckers (1) Kaili Wang (1)

Keywords

visual explanation (2) convolutional neural network (1) interpretability (1) semantic annotation (1) model interpretation (1) explanation heatmap (1) deep neural network (1)

Papers

Improving Neural Network Accuracy by Concurrently Training with a Twin Network ICLR 2025

Bilinear MLPs enable weight-based mechanistic interpretability ICLR 2025

A Protocol for Evaluating Model Interpretation Methods From Visual Explanations WACV 2023

Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks ICLR 2019