7 citations · 9 across the 11 of their papers we have counts for
16 papers
High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization
Masih Aminbeidokhti, Heitor Rapela Medeiros, Srikanth Muralidharan +2
Ensembling fine-tuned models initialized from powerful pre-trained weights is a common strategy to improve robustness under distribution shifts, but it comes with substantial compu…
Robust and Efficient Finetuning of Vision Foundation Models via Implicit Ensembling
Masih Aminbeidokhti, Heitor Rapela Medeiros, Eric Granger +1
Robust finetuning of foundation models seeks to improve out-of-distribution (OOD) generalization during in-distribution (ID) adaptation. We revisit Mixout, a stochastic regularizer…
VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors
Atif Belal, Heitor R. Medeiros, Marco Pedersoli +1
Vision-language object detectors (VLODs) such as YOLO-World and Grounding DINO exhibit strong zero-shot generalization, but their performance degrades under distribution shift. Tes…
Infrared Object Detection with Ultra Small ConvNets: Is ImageNet Pretraining Still Useful?
Srikanth Muralidharan, Heitor R. Medeiros, Masih Aminbeidokhti +2
Many real-world applications require recognition models that are robust to different operational conditions and modalities, but at the same time run on small embedded devices, with…
WiSE-OD: Benchmarking Robustness in Infrared Object Detection
Heitor R. Medeiros, Atif Belal, Masih Aminbeidokhti +2
Object detection (OD) in infrared (IR) imagery is critical for low-light and nighttime applications. However, the scarcity of large-scale IR datasets forces models to rely on weigh…
Accurate Parameter-Efficient Test-Time Adaptation for Time Series Forecasting
Heitor R. Medeiros, Hossein Sharifi-Noghabi, Gabriel L. Oliveira +1
Real-world time series often exhibit a non-stationary nature, degrading the performance of pre-trained forecasting models. Test-Time Adaptation (TTA) addresses this by adjusting mo…
Visual Modality Prompt for Adapting Vision-Language Object Detectors
Heitor R. Medeiros, Atif Belal, Srikanth Muralidharan +2
The zero-shot performance of object detectors degrades when tested on different modalities, such as infrared and depth. While recent work has explored image translation techniques…
MiPa: Mixed Patch Infrared-Visible Modality Agnostic Object Detection
Heitor R. Medeiros, David Latortue, Eric Granger +1
In real-world scenarios, using multiple modalities like visible (RGB) and infrared (IR) can greatly improve the performance of a predictive task such as object detection (OD). Mult…
Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledge
Heitor Rapela Medeiros, Masih Aminbeidokhti, Fidel Guerrero Pena +3
A common practice in deep learning involves training large neural networks on massive datasets to achieve high accuracy across various domains and tasks. While this approach works…
Domain Generalization by Rejecting Extreme Augmentations
Masih Aminbeidokhti, Fidel A. Guerrero Peña, Heitor Rapela Medeiros +3
Data augmentation is one of the most effective techniques for regularizing deep learning models and improving their recognition performance in a variety of tasks and domains. Howev…
HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information
Heitor Rapela Medeiros, Fidel A. Guerrero Pena, Masih Aminbeidokhti +3
A powerful way to adapt a visual recognition model to a new domain is through image translation. However, common image translation approaches only focus on generating data from the…
Re-basin via implicit Sinkhorn differentiation
Fidel A. Guerrero Peña, Heitor Rapela Medeiros, Thomas Dubail +3
The recent emergence of new algorithms for permuting models into functionally equivalent regions of the solution space has shed some light on the complexity of error surfaces, and…
Privacy-Preserving Person Detection Using Low-Resolution Infrared Cameras
Thomas Dubail, Fidel Alejandro Guerrero Peña, Heitor Rapela Medeiros +3
In intelligent building management, knowing the number of people and their location in a room are important for better control of its illumination, ventilation, and heating with re…
A Framework for Studying Reinforcement Learning and Sim-to-Real in Robot Soccer
Hansenclever F. Bassani, Renie A. Delgado, José Nilton de O. Lima Junior +5
This article introduces an open framework, called VSSS-RL, for studying Reinforcement Learning (RL) and sim-to-real in robot soccer, focusing on the IEEE Very Small Size Soccer (VS…
Deep Categorization with Semi-Supervised Self-Organizing Maps
Pedro H. M. Braga, Heitor R. Medeiros, Hansenclever F. Bassani
Nowadays, with the advance of technology, there is an increasing amount of unstructured data being generated every day. However, it is a painful job to label and organize it. Label…
Learning to Play Soccer by Reinforcement and Applying Sim-to-Real to Compete in the Real World
Hansenclever F. Bassani, Renie A. Delgado, Jose Nilton de O. Lima Junior +3
This work presents an application of Reinforcement Learning (RL) for the complete control of real soccer robots of the IEEE Very Small Size Soccer (VSSS), a traditional league in t…