Knowledge Distillation for Face Recognition Using Synthetic Data With Dynamic Latent Sampling

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Self-supervised pretrained models exhibit competitive performance in automatic speech recognition (ASR) on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for streaming ASR because they are train ...

Early work has found that large language models (LLMs) can generate persuasive content. However, evidence on whether they can also personalize arguments to individual attributes remains limited, despite being crucial for assessing misuse. This preregistere ...

Developing agents that can reliably act on our behalf is central to artificial intelligence (AI). These agents must seamlessly interact with tools, like search engines and databases, and collaborate. In this thesis, we study the abstractions, methods, and ...

Given a ground-level query image and a geo-referenced aerial image that covers the query’s local surroundings, fine-grained cross-view localization aims to estimate the location of the ground camera inside the aerial image. Recent works have focused on dev ...

The optimistic gradient method is useful in addressing minimax optimization problems. Motivated by the observation that the conventional stochastic version suffers from the need for a large batch size on the order of O(ϵ-2) to achieve an ϵ-stationary solut ...

Object detection, a fundamental task in computer vision, is crucial for various intelligent edge computing applications. However, object detection algorithms are usually heavy in computation, hindering their deployments on resource-constrained edge devices ...

A robust anomaly detection mechanism should possess the capability to effectively remediate anomalies, restoring them to a healthy state, while preserving essential healthy information. Despite the efficacy of existing generative models in learning the und ...

Photorealistic synthetic data and novel rendering techniques significantly advanced computer vision research. However, datasets focused on computer vision applications cannot be easily applied to robotics because they typically lack physics-related informa ...

The digitization of 3D deformable objects remains a significant challenge in computer graphics and vision, particularly in the accurate modeling of garments. Garments exhibit complex shape variability, non-rigid deformations, and frequent self-occlusion, m ...

Estimating ecosystem-atmosphere fluxes such as evapotranspiration (ET) in a robust manner and at a global scale remains a challenge. Methods based on machine learning (ML) have shown promising results in achieving such upscaling, providing a complementary ...

The field of text-to-video retrieval has advanced significantly with the evolution of language models and large-scale pre-training on generated caption-video pairs. Current methods predominantly focus on visual and event-based details, making retrieval lar ...

In this paper, we present EdgeFace - a lightweight and efficient face recognition network inspired by the hybrid architecture of EdgeNeXt. By effectively combining the strengths of both CNN and Transformer models, and a low rank linear layer, EdgeFace achi ...

State-of-the-art results in large language models (LLMs) often rely on scale, which becomes computationally expensive. This has sparked a research agenda to reduce these models' parameter counts and computational costs without significantly impacting their ...

Given the prompt “Rome is in”, can we steer a language model to flip its prediction of an incorrect token “France” to a correct token “Italy” by only multiplying a few relevant activation vectors with scalars? We argue that successfully intervening on a mo ...

Writing high-quality procedural texts is a challenging task for many learners. While example-based learning has shown promise as a feedback approach, a limitation arises when all learners receive the same content without considering their individual input ...

Smart meters, devices measuring the electricity and gas consumption of a household, are currently being deployed at a fast rate throughout the world. The data they collect are extremely useful, including in the fight against climate change. However, these ...

The proliferation of microscopy methods for live-cell imaging offers many new possibilities for users but can also be challenging to navigate. The prevailing challenge in live-cell fluorescence microscopy is capturing intra-cellular dynamics while preservi ...

Utilization of small molecules as passivation materials for perovskite solar cells (PSCs) has gained significant attention recently, with hundreds of small molecules demonstrating passivation effects. In this study, a high-accuracy machine learning model i ...

The widespread application of machine learning (ML) to the chemical sciences is making it very important to understand how the ML models learn to correlate chemical structures with their properties, and what can be done to improve the training efficiency w ...

Spiking neural networks are of high current interest, both from the perspective of modelling neural networks of the brain and for porting their fast learning capability and energy efficiency into neuromorphic hardware. But so far we have not been able to r ...

Knowledge Distillation for Face Recognition Using Synthetic Data With Dynamic Latent Sampling

Chat with Graph Search

XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models

On the conversational persuasiveness of GPT-4

Collaborative AI Agents in the Era of Large Language Models

Adapting Fine-Grained Cross-View Localization to Areas Without Fine Ground Truth

Diffusion Stochastic Optimization for Min-Max Problems

Edge-Cloud Collaborated Object Detection via Bandwidth Adaptive Difficult-Case Discriminator

Self-Supervised Anomaly Segmentation via Diffusion Models with Dynamic Transformer UNet

GRADE: Generating Realistic and Dynamic Environments for robotics research with Isaac Sim

Neural Garment Modeling

On the added value of sequential deep learning for the upscaling of evapotranspiration

Beyond Essentials: Nuanced and Diverse Text-to-video Retrieval

EdgeFace: Efficient Face Recognition Model for Edge Devices

Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers

Activation Scaling for Steering and Interpreting Language Models

Enhancing Procedural Writing Through Personalized Example Retrieval: A Case Study on Cooking Recipes

Re-pseudonymization Strategies for Smart Meter Data Are Not Robust to Deep Learning Profiling Attacks

Live-cell imaging powered by computation

Machine Learning for Screening Small Molecules as Passivation Materials for Enhanced Perovskite Solar Cells

Prediction rigidities for data-driven chemistry

Fast learning without synaptic plasticity in spiking neural networks