4 papers
Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models
Lucas Rakotoarivony
Quantization has become essential for the efficient deployment of speech processing systems. Although widely studied, most existing quantization methods were developed for vision a…
Multi-Method Ensemble for Out-of-Distribution Detection
Lucas Rakotoarivony
Detecting out-of-distribution (OOD) samples is essential for neural networks operating in open-world settings, particularly in safety-critical applications. Existing methods have i…
Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labels
Lucas Rakotoarivony
Deep learning models have achieved state-of-the-art performance in many computer vision tasks. However, in real-world scenarios, novel classes that were unseen during training ofte…
Contrastive Learning through Auxiliary Branch for Video Object Detection
Lucas Rakotoarivony
Video object detection is a challenging task because videos often suffer from image deterioration such as motion blur, occlusion, and deformable shapes, making it significantly mor…