Jose Oramas

5 papers · 2019–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10) 🐣 Hot Topic Early Bird

Venues

ICLR (3) CVPR (1) WACV (1)

Top co-authors

Thomas Dooms (1) Arian Sabaghi (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)

Research topics

Artificial Intelligence (3) Deep Learning (3) Machine Learning (3) Core Methods (3) Computer Vision (2) Analysis (2) Architectures (2) Core AI (2) Application Areas (1) Learning Paradigms (1) Learning Types (1) Optimization & Theory (1)

Keywords

convolutional neural network (2) visual explanation (2) interpretability (1) self-supervised learning (1) knowledge distillation (1) mean squared error (1) spiking neural network (1) deep neural network (1) semantic annotation (1) model interpretation (1) weakly supervised object localization (1) neural network (1) parameter-efficient training (1) machine learning optimization (1) explanation heatmap (1) tri-region disentanglement (1) twin network augmentation (1) representation learning (1) bilinear layer (1) vision transformer (1)

Papers

TriLite: Efficient Weakly Supervised Object Localization with Universal Visual Features and Tri-Region Disentanglement CVPR 2026 Bilinear MLPs enable weight-based mechanistic interpretability ICLR 2025 Improving Neural Network Accuracy by Concurrently Training with a Twin Network 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