Search Results for author:
Found 56 papers, 10 papers with code
Food Portion Estimation via 3D Object Scaling
Image-based methods to analyze food images have alleviated the user burden and biases associated with traditional methods.
Learning to Classify New Foods Incrementally Via Compressed Exemplars
Therefore, food image classification systems should adapt to and manage data that continuously evolves.
DELTA: Decoupling Long-Tailed Online Continual Learning
A significant challenge in achieving ubiquitous Artificial Intelligence is the limited ability of models to rapidly learn new information in real-world scenarios where data follows long-tailed distributions, all while avoiding forgetting previously acquired knowledge.
Flexible Variable-Rate Image Feature Compression for Edge-Cloud Systems
By compressing different intermediate features of a pre-trained vision task model, the proposed method can scale the encoding complexity without changing the overall size of the model.
Theoretical Bound-Guided Hierarchical VAE for Neural Image Codecs
Recent studies reveal a significant theoretical link between variational autoencoders (VAEs) and rate-distortion theory, notably in utilizing VAEs to estimate the theoretical upper bound of the information rate-distortion function of images.
Strategies to Improve Real-World Applicability of Laparoscopic Anatomy Segmentation Models
Accurate identification and localization of anatomical structures of varying size and appearance in laparoscopic imaging are necessary to leverage the potential of computer vision techniques for surgical decision support.
Probing Image Compression For Class-Incremental Learning
To this end, we introduce a new framework to incorporate image compression for continual ML including a pre-processing data compression step and an efficient compression rate/algorithm selection method.
Towards Backward-Compatible Continual Learning of Image Compression
This paper explores the possibility of extending the capability of pre-trained neural image compressors (e. g., adapting to new data or target bitrates) without breaking backward compatibility, the ability to decode bitstreams encoded by the original model.
Gradient Reweighting: Towards Imbalanced Class-Incremental Learning
Class-Incremental Learning (CIL) trains a model to continually recognize new classes from non-stationary data while retaining learned knowledge.
Another Way to the Top: Exploit Contextual Clustering in Learned Image Coding
While convolution and self-attention are extensively used in learned image compression (LIC) for transform coding, this paper proposes an alternative called Contextual Clustering based LIC (CLIC) which primarily relies on clustering operations and local attention for correlation characterization and compact representation of an image.
Deep Hierarchical Video Compression
Recently, probabilistic predictive coding that directly models the conditional distribution of latent features across successive frames for temporal redundancy removal has yielded promising results.
Personalized Food Image Classification: Benchmark Datasets and New Baseline
Personalized food classification aims to address this problem by training a deep neural network using food images that reflect the consumption pattern of each individual.
An Improved Upper Bound on the Rate-Distortion Function of Images
Recent work has shown that Variational Autoencoders (VAEs) can be used to upper-bound the information rate-distortion (R-D) function of images, i. e., the fundamental limit of lossy image compression.
An Improved Encoder-Decoder Framework for Food Energy Estimation
Dietary assessment is essential to maintaining a healthy lifestyle.
Diffusion Model with Clustering-based Conditioning for Food Image Generation
Image-based dietary assessment serves as an efficient and accurate solution for recording and analyzing nutrition intake using eating occasion images as input.
An End-to-end Food Portion Estimation Framework Based on Shape Reconstruction from Monocular Image
Dietary assessment is a key contributor to monitoring health status.
A Visual Quality Assessment Method for Raster Images in Scanned Document
Different from many existing works which aim to estimate a visual quality score, we propose a machine learning based classification method to determine whether the visual quality of a scanned raster image at a given resolution setting is acceptable.
Long-Tailed Continual Learning For Visual Food Recognition
First, as new foods appear sequentially overtime, a trained model needs to learn the new classes continuously without causing catastrophic forgetting for already learned knowledge of existing food types.
Single-Stage Heavy-Tailed Food Classification
Deep learning based food image classification has enabled more accurate nutrition content analysis for image-based dietary assessment by predicting the types of food in eating occasion images.
Self-Supervised Visual Representation Learning on Food Images
Food image analysis is the groundwork for image-based dietary assessment, which is the process of monitoring what kinds of food and how much energy is consumed using captured food or eating scene images.
Conditional Synthetic Food Image Generation
Therefore, we aim to explore the capability and improve the performance of GAN methods for food image generation.
QARV: Quantization-Aware ResNet VAE for Lossy Image Compression
This paper addresses the problem of lossy image compression, a fundamental problem in image processing and information theory that is involved in many real-world applications.
Improving Food Detection For Images From a Wearable Egocentric Camera
In this paper, we propose an approach to pre-process images collected by the AIM imaging sensor by rejecting extremely blurry images to improve the performance of food detection.
Online Class-Incremental Learning For Real-World Food Image Classification
In this work, we explore OCIL for real-world food image classification by first introducing a probabilistic framework to simulate realistic food consumption scenarios.
Efficient Feature Compression for Edge-Cloud Systems
Optimizing computation in an edge-cloud system is an important yet challenging problem.
Long-tailed Food Classification
Food classification serves as the basic step of image-based dietary assessment to predict the types of foods in each input image.
Lossy Image Compression with Quantized Hierarchical VAEs
Recent research has shown a strong theoretical connection between variational autoencoders (VAEs) and the rate-distortion theory.
Image Based Food Energy Estimation With Depth Domain Adaptation
In this paper, we propose an "Energy Density Map" which is a pixel-to-pixel mapping from the RGB image to the energy density of the food.
Simulating Personal Food Consumption Patterns using a Modified Markov Chain
Food image classification serves as the foundation of image-based dietary assessment to predict food categories.
3DG-STFM: 3D Geometric Guided Student-Teacher Feature Matching
To the best of our knowledge, 3DG-STFM is the first student-teacher learning method for the local feature matching task.
Towards the Creation of a Nutrition and Food Group Based Image Database
Food classification is critical to the analysis of nutrients comprising foods reported in dietary assessment.
Out-Of-Distribution Detection In Unsupervised Continual Learning
Our method is evaluated on CIFAR-100 dataset by following the proposed evaluation protocol and we show improved performance compared with existing OOD detection methods under the unsupervised continual learning scenario.
Opening the Black Box of Learned Image Coders
End-to-end learned lossy image coders (LICs), as opposed to hand-crafted image codecs, have shown increasing superiority in terms of the rate-distortion performance.
Exemplar-free Online Continual Learning
Targeted for real world scenarios, online continual learning aims to learn new tasks from sequentially available data under the condition that each data is observed only once by the learner.
Online Continual Learning Via Candidates Voting
Continual learning in online scenario aims to learn a sequence of new tasks from data stream using each data only once for training, which is more realistic than in offline mode assuming data from new task are all available.
An Integrated System for Mobile Image-Based Dietary Assessment
Accurate assessment of dietary intake requires improved tools to overcome limitations of current methods including user burden and measurement error.
Improving Dietary Assessment Via Integrated Hierarchy Food Classification
Image-based dietary assessment refers to the process of determining what someone eats and how much energy and nutrients are consumed from visual data.
Motion Artifact Reduction In Photoplethysmography For Reliable Signal Selection
Therefore, our proposed method can determine the reliability of the raw noisy PPG by considering quality of the corresponding pseudo clean PPG signal.
Online Continual Learning For Visual Food Classification
Food image classification is challenging for real-world applications since existing methods require static datasets for training and are not capable of learning from sequentially available new food images.
Unsupervised Continual Learning Via Pseudo Labels
Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives.
Towards Learning Food Portion From Monocular Images With Cross-Domain Feature Adaptation
We aim to estimate food portion size, a property that is strongly related to the presence of food object in 3D space, from single monocular images under real life setting.
Saliency-Aware Class-Agnostic Food Image Segmentation
Our method uses a pair of eating scene images, one before start eating and one after eating is completed.
Turkey Behavior Identification System with a GUI Using Deep Learning and Video Analytics
In this paper, we propose a video analytics system to identify the behavior of turkeys.
An End-to-End Food Image Analysis System
Our end-to-end framework is evaluated on a real life food image dataset collected from a nutrition feeding study.
Visual Aware Hierarchy Based Food Recognition
Experimental results demonstrate that our system can significantly improve both classification and recognition performance on 4 publicly available datasets and the new VFN dataset.
Decomposition, Compression, and Synthesis (DCS)-based Video Coding: A Neural Exploration via Resolution-Adaptive Learning
Inspired by the facts that retinal cells actually segregate the visual scene into different attributes (e. g., spatial details, temporal motion) for respective neuronal processing, we propose to first decompose the input video into respective spatial texture frames (STF) at its native spatial resolution that preserve the rich spatial details, and the other temporal motion frames (TMF) at a lower spatial resolution that retain the motion smoothness; then compress them together using any popular video coder; and finally synthesize decoded STFs and TMFs for high-fidelity video reconstruction at the same resolution as its native input.
Generative Autoregressive Ensembles for Satellite Imagery Manipulation Detection
Satellite imagery is becoming increasingly accessible due to the growing number of orbiting commercial satellites.
Multi-Task Image-Based Dietary Assessment for Food Recognition and Portion Size Estimation
Deep learning based methods have achieved impressive results in many applications for image-based diet assessment such as food classification and food portion size estimation.
Deepfakes Detection with Automatic Face Weighting
Altered and manipulated multimedia is increasingly present and widely distributed via social media platforms.
Incremental Learning In Online Scenario
Modern deep learning approaches have achieved great success in many vision applications by training a model using all available task-specific data.
Learning eating environments through scene clustering
The variation in the number of clusters and images captured by different individual makes this a very challenging problem.
Semi-Automatic Crowdsourcing Tool for Online Food Image Collection and Annotation
The web crawler is used to download large sets of online food images based on the given food labels.
A Reflectance Based Method For Shadow Detection and Removal
Shadows are common aspect of images and when left undetected can hinder scene understanding and visual processing.
Reliability Map Estimation For CNN-Based Camera Model Attribution
This refers to the problem of detecting which camera model has been used to acquire an image by only exploiting pixel information.
Single-View Food Portion Estimation: Learning Image-to-Energy Mappings Using Generative Adversarial Networks
We can then estimate food energy based on the energy distribution.
Texture Segmentation Based Video Compression Using Convolutional Neural Networks
There has been a growing interest in using different approaches to improve the coding efficiency of modern video codec in recent years as demand for web-based video consumption increases.
