paper-with-me

홈 › Papers

Pushing the envelope in deep visual recognition for mobile platforms

2017-10-16 · Lorenzo Alvino

Image classification is the task of assigning to an input image a label from a fixed set of categories. One of its most important applicative fields is that of robotics, in particular the needing of a robot to be aware of what's around and the consequent exploitation of that information as a benefit for its tasks. In this work we consider the problem of a robot that enters a new environment and wants to understand visual data coming from its camera, so to extract knowledge from them. As main novelty we want to overcome the needing of a physical robot, as it could be expensive and unhandy, so to hopefully enhance, speed up and ease the research in this field. That's why we propose to develop an application for a mobile platform that wraps several deep visual recognition tasks. First we deal with a simple Image classification, testing a model obtained from an AlexNet trained on the ILSVRC 2012 dataset. Several photo settings are considered to better understand which factors affect most the quality of classification. For the same purpose we are interested to integrate the classification task with an extra module dealing with segmentation of the object inside the image. In particular we propose a technique for extracting the object shape and moving out all the background, so to focus the classification only on the region occupied by the object. Another significant task that is included is that of object discovery. Its purpose is to simulate the situation in which the robot needs a certain object to complete one of its activities. It starts searching for what it needs by looking around and trying to understand the location of the object by scanning the surrounding environment. Finally we provide a tool for dealing with the creation of customized task-specific databases, meant to better suit to one's needing in a particular vision task.

📄 PDF Abstract BibTeX arXiv:1710.05982

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral Classificationimage-classificationImage ClassificationObjectObject Discovery

Methods 이 논문이 사용한 방법론

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Local Response Normalization Local Response Normalization is a normalization layer that implements the idea of lateral inhibition. Lateral inhibition is a concept in neurobiology that refers to the…
Grouped Convolution A Grouped Convolution uses a group of convolutions - multiple kernels per layer - resulting in multiple channel outputs per layer. This leads to wider networks helping a…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Similar Papers 제목 키워드 기반

Are State-of-the-art Visual Place Recognition Techniques any Good for Aerial Robotics?

2019-04-16 · Mubariz Zaffar, Ahmad Khaliq, Shoaib Ehsan, Michael Milford 외

Visual Place Recognition (VPR) has seen significant advances at the frontiers of matching performance and computational superiority over the past few years. However, these evaluations are performed for ground-based mobil…

Visual Place Recognition

One-class anomaly detection through color-to-thermal AI for building envelope inspection

2024-02-05 · Polina Kurtser, Kailun Feng, Thomas Olofsson, Aitor De Andres

We present a label-free method for detecting anomalies during thermographic inspection of building envelopes. It is based on the AI-driven prediction of thermal distributions from color images. Effectively the method per…

Anomaly DetectionOne-class classifier

Pushing the Envelope of LLM Inference with Ultra-Low-Bit Quantized Models

2025-08-08 · Evangelos Georganas, Dhiraj Kalamkar, Alexander Heinecke arxiv

The advent of ultra-low-bit LLM models, approaching the perplexity and task accuracy of their full precision counterparts, is ushering in a new era of LLM inference. While these advances promise models that are cost-effe…

Computational Efficiency

Deep Learning Acceleration Techniques for Real Time Mobile Vision Applications

2019-05-09 · Gael Kamdem De Teyou

Deep Learning (DL) has become a crucial technology for Artificial Intelligence (AI). It is a powerful technique to automatically extract high-level features from complex data which can be exploited for applications such …

Deep LearningDistributed Computingobject-detectionObject Detection

Bench-Push: Benchmarking Pushing-based Navigation and Manipulation Tasks for Mobile Robots

2025-12-12 · Ninghan Zhong, Steven Caro, Megnath Ramesh, Rishi Bhatnagar 외 arxiv

Mobile robots are increasingly deployed in cluttered environments with movable objects, posing challenges for traditional methods that prohibit interaction. In such settings, the mobile robot must go beyond traditional o…

Robot Navigation