Gradient-based Parameter Selection for Efficient Fine-Tuning
With the growing size of pre-trained models full fine-tuning and storing all the parameters for
various downstream tasks is costly and infeasible. In this paper we propose a new …
various downstream tasks is costly and infeasible. In this paper we propose a new …
Vehicle classification from low-frequency GPS data with recurrent neural networks
The categorization of the type of vehicles on a road network is typically achieved using
external sensors, like weight sensors, or from images captured by surveillance cameras. In …
external sensors, like weight sensors, or from images captured by surveillance cameras. In …
The channel as a traffic sensor: Vehicle detection and classification based on radio fingerprinting
Ubiquitously deployed Internet of Things (IoT)-based automatic vehicle classification
systems will catalyze data-driven traffic flow optimization in future smart cities and will …
systems will catalyze data-driven traffic flow optimization in future smart cities and will …
The image data and backbone in weakly supervised fine-grained visual categorization: A revisit and further thinking
Weakly-supervised fine-grained visual categorization (FGVC) aims to achieve subclass
classification within the same large class using only label information. Compared to general …
classification within the same large class using only label information. Compared to general …
Tuning pre-trained model via moment probing
Recently, efficient fine-tuning of large-scale pre-trained models has attracted increasing
research interests, where linear probing (LP) as a fundamental module is involved in …
research interests, where linear probing (LP) as a fundamental module is involved in …
Multi-task deep relative attribute learning for visual urban perception
Visual urban perception aims to quantify perceptual attributes (eg, safe and depressing
attributes) of physical urban environment from crowd-sourced street-view images and their …
attributes) of physical urban environment from crowd-sourced street-view images and their …
[图书][B] Atlas de IA: Poder, política y costes planetarios de la inteligencia artificial
K Crawford - 2023 - books.google.com
¿ Quiénes son los agentes implicados en la creación de significado en inteligencia
artificial?¿ Son esos resultados verdades indiscutibles científicamente?¿ A quién beneficia …
artificial?¿ Son esos resultados verdades indiscutibles científicamente?¿ A quién beneficia …
Museum exhibit identification challenge for the supervised domain adaptation and beyond
We study an open problem of artwork identification and propose a new dataset dubbed
Open Museum Identification Challenge (Open MIC). It contains photos of exhibits captured …
Open Museum Identification Challenge (Open MIC). It contains photos of exhibits captured …
Adapting shortcut with normalizing flow: An efficient tuning framework for visual recognition
Pretraining followed by fine-tuning has proven to be effective in visual recognition tasks.
However, fine-tuning all parameters can be computationally expensive, particularly for large …
However, fine-tuning all parameters can be computationally expensive, particularly for large …
A survey on visual transfer learning using knowledge graphs
The information perceived via visual observations of real-world phenomena is unstructured
and complex. Computer vision (CV) is the field of research that attempts to make use of that …
and complex. Computer vision (CV) is the field of research that attempts to make use of that …