Search Results for author:
Found 75 papers, 42 papers with code
Bilingual Lexicon Induction across Orthographically-distinct Under-Resourced Dravidian Languages
Bilingual lexicons are a vital tool for under-resourced languages and recent state-of-the-art approaches to this leverage pretrained monolingual word embeddings using supervised or semi-supervised approaches.
Dataset Clustering for Improved Offline Policy Learning
Offline policy learning aims to discover decision-making policies from previously-collected datasets without additional online interactions with the environment.
Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach
Video Anomaly Detection (VAD) is an open-set recognition task, which is usually formulated as a one-class classification (OCC) problem, where training data is comprised of videos with normal instances while test data contains both normal and anomalous instances.
Learning and reusing primitive behaviours to improve Hindsight Experience Replay sample efficiency
Hindsight Experience Replay (HER) is a technique used in reinforcement learning (RL) that has proven to be very efficient for training off-policy RL-based agents to solve goal-based robotic manipulation tasks using sparse rewards.
Self-Supervised and Semi-Supervised Polyp Segmentation using Synthetic Data
To address both challenges, we leverage synthetic data and propose an end-to-end model for polyp segmentation that integrates real and synthetic data to artificially increase the size of the datasets and aid the training when unlabeled samples are available.
Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Prompts
Meanwhile, recent developments in generative pretrained models like GPT-4 mean they can be used as advanced internet search tools.
Joint one-sided synthetic unpaired image translation and segmentation for colorectal cancer prevention
We take advantage of recent one-sided translation models because they use significantly less memory, allowing us to add a segmentation model in the training loop.
An Ensemble Deep Learning Approach for COVID-19 Severity Prediction Using Chest CT Scans
Chest X-rays have been widely used for COVID-19 screening; however, 3D computed tomography (CT) is a more effective modality.
Site-specific Deep Learning Path Loss Models based on the Method of Moments
This paper describes deep learning models based on convolutional neural networks applied to the problem of predicting EM wave propagation over rural terrain.
Identifying Expert Behavior in Offline Training Datasets Improves Behavioral Cloning of Robotic Manipulation Policies
However, BC's performance deteriorated when applied to mixed datasets, and the performance of offline RL algorithms was also unsatisfactory.
Improving Behavioural Cloning with Positive Unlabeled Learning
Learning control policies offline from pre-recorded datasets is a promising avenue for solving challenging real-world problems.
Unifying Synergies between Self-supervised Learning and Dynamic Computation
Computationally expensive training strategies make self-supervised learning (SSL) impractical for resource constrained industrial settings.
TinyHD: Efficient Video Saliency Prediction with Heterogeneous Decoders using Hierarchical Maps Distillation
Video saliency prediction has recently attracted attention of the research community, as it is an upstream task for several practical applications.
Motion Aware Self-Supervision for Generic Event Boundary Detection
In this work, we address this issue by revisiting a simple and effective self-supervised method and augment it with a differentiable motion feature learning module to tackle the spatial and temporal diversities in the GEBD task.
Is your noise correction noisy? PLS: Robustness to label noise with two stage detection
Experiments demonstrate the state-of-the-art performance of our Pseudo-Loss Selection (PLS) algorithm on a variety of benchmark datasets including curated data synthetically corrupted with in-distribution and out-of-distribution noise, and two real world web noise datasets.
BaseTransformers: Attention over base data-points for One Shot Learning
In this paper we propose to make use of the well-trained feature representations of the base dataset that are closest to each support instance to improve its representation during meta-test time.
Random Data Augmentation based Enhancement: A Generalized Enhancement Approach for Medical Datasets
To evaluate the generalization of the proposed method, we use four medical datasets and compare its performance with state-of-the-art methods for both classification and segmentation tasks.
Fast and Robust Video-Based Exercise Classification via Body Pose Tracking and Scalable Multivariate Time Series Classifiers
We analyze the accuracy and robustness of BodyMTS and show that it is robust to different types of noise caused by either video quality or pose estimation factors.
Cardiac Segmentation using Transfer Learning under Respiratory Motion Artifacts
Methods that are resilient to artifacts in the cardiac magnetic resonance imaging (MRI) while performing ventricle segmentation, are crucial for ensuring quality in structural and functional analysis of those tissues.
Dynamic Channel Selection in Self-Supervised Learning
Currently, convnets pre-trained with self-supervision have obtained comparable performance on downstream tasks in comparison to their supervised counterparts in computer vision.
Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasets
These noisy samples have been evidenced by previous works to be a mixture of in-distribution (ID) samples, assigned to the incorrect category but presenting similar visual semantics to other classes in the dataset, and out-of-distribution (OOD) images, which share no semantic correlation with any category from the dataset.
Segmentation Enhanced Lameness Detection in Dairy Cows from RGB and Depth Video
Cow lameness is a severe condition that affects the life cycle and life quality of dairy cows and results in considerable economic losses.
Dexterous Robotic Manipulation using Deep Reinforcement Learning and Knowledge Transfer for Complex Sparse Reward-based Tasks
Here we extend this method, by modifying the task of Phase 1 of the RRC to require the robot to maintain the cube in a particular orientation, while the cube is moved along the required positional trajectory.
Utilizing unsupervised learning to improve sward content prediction and herbage mass estimation
Sward species composition estimation is a tedious one.
Unsupervised domain adaptation and super resolution on drone images for autonomous dry herbage biomass estimation
In this context, deep learning algorithms offer a tempting alternative to the usual means of sward composition estimation, which involves the destructive process of cutting a sample from the herbage field and sorting by hand all plant species in the herbage.
Domain Randomization for Object Counting
We introduce a domain randomization approach for object counting based on synthetic datasets that are quick and inexpensive to generate.
Synthetic data for unsupervised polyp segmentation
Deep learning has shown excellent performance in analysing medical images.
BERTHA: Video Captioning Evaluation Via Transfer-Learned Human Assessment
The model is based on BERT, which is a language model that has been shown to work well in multiple NLP tasks.
Improving Person Re-Identification with Temporal Constraints
We apply state-of-the-art person re-identification models to our dataset and show that by leveraging the available timestamp information we are able to achieve a significant gain of 37. 43% in mAP and a gain of 30. 22% in Rank1 accuracy.
How Important is Importance Sampling for Deep Budgeted Training?
We suggest that, given a specific budget, the best course of action is to disregard the importance and introduce adequate data augmentation; e. g. when reducing the budget to a 30% in CIFAR-10/100, RICAP data augmentation maintains accuracy, while importance sampling does not.
Semi-supervised dry herbage mass estimation using automatic data and synthetic images
Deep learning for computer vision is a powerful tool in this context as it can accurately estimate the dry biomass of a herbage parcel using images of the grass canopy taken using a portable device.
Addressing out-of-distribution label noise in webly-labelled data
We propose a simple solution to bridge the gap with a fully clean dataset using Dynamic Softening of Out-of-distribution Samples (DSOS), which we design on corrupted versions of the CIFAR-100 dataset, and compare against state-of-the-art algorithms on the web noise perturbated MiniImageNet and Stanford datasets and on real label noise datasets: WebVision 1. 0 and Clothing1M.
Solving the Real Robot Challenge using Deep Reinforcement Learning
This paper details our winning submission to Phase 1 of the 2021 Real Robot Challenge; a challenge in which a three-fingered robot must carry a cube along specified goal trajectories.
Discerning Generic Event Boundaries in Long-Form Wild Videos
Detecting generic, taxonomy-free event boundaries invideos represents a major stride forward towards holisticvideo understanding.
Evaluating Contrastive Models for Instance-based Image Retrieval
In this work, we evaluate contrastive models for the task of image retrieval.
Extracting Pasture Phenotype and Biomass Percentages using Weakly Supervised Multi-target Deep Learning on a Small Dataset
In this paper, we demonstrate that applying data augmentation and transfer learning is effective in predicting multi-target biomass percentages of different plant species, even with a small training dataset.
The Importance of Importance Sampling for Deep Budgeted Training
For example, training in CIFAR-10/100 with 30% of the full training budget, a uniform sampling strategy with certain data augmentation surpasses the performance of 100% budget models trained with standard data augmentation.
Rethinking 360deg Image Visual Attention Modelling With Unsupervised Learning.
This performance is achieved using an encoder that is trained in a completely unsupervised way and a relatively lightweight supervised decoder (3. 8 X fewer parameters in the case of the ResNet50 encoder).
Temporal Bilinear Encoding Network of Audio-Visual Features at Low Sampling Rates
Current deep learning based video classification architectures are typically trained end-to-end on large volumes of data and require extensive computational resources.
Multi-Objective Interpolation Training for Robustness to Label Noise
We further propose a novel label noise detection method that exploits the robust feature representations learned via contrastive learning to estimate per-sample soft-labels whose disagreements with the original labels accurately identify noisy samples.
Ranked #21 on
Image Classification
on mini WebVision 1.0
ATSal: An Attention Based Architecture for Saliency Prediction in 360 Videos
The spherical domain representation of 360 video/image presents many challenges related to the storage, processing, transmission and rendering of omnidirectional videos (ODV).
Unsupervised Contrastive Learning of Sound Event Representations
Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data---a common scenario in sound event research.
How important are faces for person re-identification?
This paper investigates the dependence of existing state-of-the-art person re-identification models on the presence and visibility of human faces.
A Comparative Study of Existing and New Deep Learning Methods for Detecting Knee Injuries using the MRNet Dataset
Overall we achieved a performance of 93. 4% AUC on the validation data by using the more recent deep learning architectures and data augmentation strategies.
FastSal: a Computationally Efficient Network for Visual Saliency Prediction
This paper focuses on the problem of visual saliency prediction, predicting regions of an image that tend to attract human visual attention, under a constrained computational budget.
Reliable Label Bootstrapping for Semi-Supervised Learning
We propose Reliable Label Bootstrapping (ReLaB), an unsupervised preprossessing algorithm which improves the performance of semi-supervised algorithms in extremely low supervision settings.
Investigating Class-level Difficulty Factors in Multi-label Classification Problems
This work investigates the use of class-level difficulty factors in multi-label classification problems for the first time.
Towards Robust Learning with Different Label Noise Distributions
However, we show that different noise distributions make the application of this trick less straightforward and propose to continuously relabel all images to reveal a discriminative loss against multiple distributions.
MediaEval 2019: Concealed FGSM Perturbations for Privacy Preservation
This work tackles the Pixel Privacy task put forth by MediaEval 2019.
Predicting knee osteoarthritis severity: comparative modeling based on patient's data and plain X-ray images
Knee osteoarthritis (KOA) is a disease that impairs knee function and causes pain.
Feature Learning to Automatically Assess Radiographic Knee Osteoarthritis Severity
Also, this chapter demonstrates that feature learning in a supervised manner is more effective than using conventional handcrafted features for automatic detection of knee joints and fine-grained knee OA image classification.
Assessing Knee OA Severity with CNN attention-based end-to-end architectures
This work proposes a novel end-to-end convolutional neural network (CNN) architecture to automatically quantify the severity of knee osteoarthritis (OA) using X-Ray images, which incorporates trainable attention modules acting as unsupervised fine-grained detectors of the region of interest (ROI).
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
In the context of image classification, recent advances to learn from unlabeled samples are mainly focused on consistency regularization methods that encourage invariant predictions for different perturbations of unlabeled samples.
Simple vs complex temporal recurrences for video saliency prediction
This paper investigates modifying an existing neural network architecture for static saliency prediction using two types of recurrences that integrate information from the temporal domain.
On guiding video object segmentation
This guiding process relies on foreground masks from independent algorithms (i. e. state-of-the-art algorithms) to implement an attention mechanism that incorporates the spatial location of foreground and background to compute their separated representations.
Unsupervised Label Noise Modeling and Loss Correction
Specifically, we propose a beta mixture to estimate this probability and correct the loss by relying on the network prediction (the so-called bootstrapping loss).
Ranked #44 on
Image Classification
on Clothing1M
An Efficient Approximate kNN Graph Method for Diffusion on Image Retrieval
The application of the diffusion in many computer vision and artificial intelligence projects has been shown to give excellent improvements in performance.
Wav2Pix: Speech-conditioned Face Generation using Generative Adversarial Networks
Speech is a rich biometric signal that contains information about the identity, gender and emotional state of the speaker.
PathGAN: Visual Scanpath Prediction with Generative Adversarial Networks
We introduce PathGAN, a deep neural network for visual scanpath prediction trained on adversarial examples.
Saliency Weighted Convolutional Features for Instance Search
This work explores attention models to weight the contribution of local convolutional representations for the instance search task.
People, Penguins and Petri Dishes: Adapting Object Counting Models To New Visual Domains And Object Types Without Forgetting
In this paper we propose a technique to adapt a convolutional neural network (CNN) based object counter to additional visual domains and object types while still preserving the original counting function.
SaltiNet: Scan-path Prediction on 360 Degree Images using Saliency Volumes
The first part of the network consists of a model trained to generate saliency volumes, whose parameters are fit by back-propagation computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency volumes.
ResnetCrowd: A Residual Deep Learning Architecture for Crowd Counting, Violent Behaviour Detection and Crowd Density Level Classification
In this paper we propose ResnetCrowd, a deep residual architecture for simultaneous crowd counting, violent behaviour detection and crowd density level classification.
Automatic Detection of Knee Joints and Quantification of Knee Osteoarthritis Severity using Convolutional Neural Networks
We introduce a new approach to automatically detect the knee joints using a fully convolutional neural network (FCN).
SalGAN: Visual Saliency Prediction with Generative Adversarial Networks
We introduce SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples.
Fully Convolutional Crowd Counting On Highly Congested Scenes
In this paper we advance the state-of-the-art for crowd counting in high density scenes by further exploring the idea of a fully convolutional crowd counting model introduced by (Zhang et al., 2016).
An Interactive Segmentation Tool for Quantifying Fat in Lumbar Muscles using Axial Lumbar-Spine MRI
In this paper, we propose a method to precisely quantify the fat deposition / infiltration in a user-defined region of the lumbar muscles, which may aid better diagnosis and analysis.
Quantifying Radiographic Knee Osteoarthritis Severity using Deep Convolutional Neural Networks
We demonstrate that classification accuracy can be significantly improved using deep convolutional neural network models pre-trained on ImageNet and fine-tuned on knee OA images.
Where is my Phone ? Personal Object Retrieval from Egocentric Images
This work presents a retrieval pipeline and evaluation scheme for the problem of finding the last appearance of personal objects in a large dataset of images captured from a wearable camera.
Bags of Local Convolutional Features for Scalable Instance Search
This work proposes a simple instance retrieval pipeline based on encoding the convolutional features of CNN using the bag of words aggregation scheme (BoW).
Shallow and Deep Convolutional Networks for Saliency Prediction
The prediction of salient areas in images has been traditionally addressed with hand-crafted features based on neuroscience principles.
Improving Spatial Codification in Semantic Segmentation
This paper explores novel approaches for improving the spatial codification for the pooling of local descriptors to solve the semantic segmentation problem.
Exploring EEG for Object Detection and Retrieval
We show that it is indeed possible to detect such objects in complex images and, also, that users with previous knowledge on the dataset or experience with the RSVP outperform others.
