Search Results for author:
Found 64 papers, 25 papers with code
Frequency Attention for Knowledge Distillation
Inspired by the benefits of the frequency domain, we propose a novel module that functions as an attention mechanism in the frequency domain.
DiffAugment: Diffusion based Long-Tailed Visual Relationship Recognition
The task of Visual Relationship Recognition (VRR) aims to identify relationships between two interacting objects in an image and is particularly challenging due to the widely-spread and highly imbalanced distribution of <subject, relation, object> triplets.
Unveiling Camouflage: A Learnable Fourier-based Augmentation for Camouflaged Object Detection and Instance Segmentation
Camouflaged object detection (COD) and camouflaged instance segmentation (CIS) aim to recognize and segment objects that are blended into their surroundings, respectively.
Few-Shot Object Detection via Synthetic Features with Optimal Transport
Our overarching goal is to train a generator that captures the data variations of the base dataset.
Optimal Transport Model Distributional Robustness
Interestingly, our developed theories allow us to flexibly incorporate the concept of sharpness awareness into training, whether it's a single model, ensemble models, or Bayesian Neural Networks, by considering specific forms of the center model distribution.
Noisy-label Learning with Sample Selection based on Noise Rate Estimate
Even though the estimated noise rate from the training set appears to be a natural signal to be used in the definition of this curriculum, previous approaches generally rely on arbitrary thresholds or pre-defined selection functions to the best of our knowledge.
The Art of Camouflage: Few-shot Learning for Animal Detection and Segmentation
In this paper, we address the problem of few-shot learning for camouflaged object detection and segmentation.
Instance-level Few-shot Learning with Class Hierarchy Mining
In this paper, we exploit the hierarchical information to leverage discriminative and relevant features of base classes to effectively classify novel objects.
PASS: Peer-Agreement based Sample Selection for training with Noisy Labels
To address this limitation, we propose a novel peer-agreement based sample selection (PASS).
MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation
To overcome the disadvantage of the point estimation mechanism, we propose a novel approach, dubbed MaskDiff, which models the underlying conditional distribution of a binary mask, which is conditioned on an object region and $K-$shot information.
Towards the Identifiability in Noisy Label Learning: A Multinomial Mixture Approach
To meet this requirement without relying on additional $2C - 2$ manual annotations per instance, we propose a method that automatically generates additional noisy labels by estimating the noisy label distribution based on nearest neighbours.
Task Weighting in Meta-learning with Trajectory Optimisation
Developing meta-learning algorithms that are un-biased toward a subset of training tasks often requires hand-designed criteria to weight tasks, potentially resulting in sub-optimal solutions.
Collaborative Multi-Teacher Knowledge Distillation for Learning Low Bit-width Deep Neural Networks
Knowledge distillation which learns a lightweight student model by distilling knowledge from a cumbersome teacher model is an attractive approach for learning compact deep neural networks (DNNs).
Vision Transformer Visualization: What Neurons Tell and How Neurons Behave?
Our approach departs from the computational process of ViTs with a focus on visualizing the local and global information in input images and the latent feature embeddings at multiple levels.
Instance-Dependent Noisy Label Learning via Graphical Modelling
Noisy labels are unavoidable yet troublesome in the ecosystem of deep learning because models can easily overfit them.
Ranked #1 on
Learning with noisy labels
on CIFAR-100
Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing
First, to learn informative representations that can preserve both intra- and inter-modal similarities, we leverage the recent advances in estimating variational lower-bound of MI to maximize the MI between the binary representations and input features and between binary representations of different modalities.
Logic Rules Meet Deep Learning: A Novel Approach for Ship Type Classification
The shipping industry is an important component of the global trade and economy, however in order to ensure law compliance and safety it needs to be monitored.
Probabilistic task modelling for meta-learning
We propose probabilistic task modelling -- a generative probabilistic model for collections of tasks used in meta-learning.
Camouflaged Instance Segmentation In-The-Wild: Dataset, Method, and Benchmark Suite
We also provide a benchmark suite for the task of camouflaged instance segmentation.
Similarity of Classification Tasks
Recent advances in meta-learning has led to remarkable performances on several few-shot learning benchmarks.
Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks
With this approach, we can learn activation quantizers that minimize the quantization errors in the majority of channels.
Multiple interaction learning with question-type prior knowledge for constraining answer search space in visual question answering
Different approaches have been proposed to Visual Question Answering (VQA).
Deep Metric Learning Meets Deep Clustering: An Novel Unsupervised Approach for Feature Embedding
Based on pseudo labels, we propose a novel unsupervised metric loss which enforces the positive concentration and negative separation of samples in the embedding space.
Unsupervised Deep Cross-modality Spectral Hashing
This paper presents a novel framework, namely Deep Cross-modality Spectral Hashing (DCSH), to tackle the unsupervised learning problem of binary hash codes for efficient cross-modal retrieval.
MirrorNet: Bio-Inspired Camouflaged Object Segmentation
Differently from existing networks for segmentation, our proposed network possesses two segmentation streams: the main stream and the mirror stream corresponding with the original image and its flipped image, respectively.
Ranked #8 on
Camouflaged Object Segmentation
on CAMO
Sensor Data for Human Activity Recognition: Feature Representation and Benchmarking
In HAR, the development of Activity Recognition models is dependent upon the data captured by these devices and the methods used to analyse them, which directly affect performance metrics.
PAC-Bayes meta-learning with implicit task-specific posteriors
We introduce a new and rigorously-formulated PAC-Bayes meta-learning algorithm that solves few-shot learning.
Compact Trilinear Interaction for Visual Question Answering
In Visual Question Answering (VQA), answers have a great correlation with question meaning and visual contents.
Ranked #2 on
Visual Question Answering (VQA)
on TDIUC
Overcoming Data Limitation in Medical Visual Question Answering
Traditional approaches for Visual Question Answering (VQA) require large amount of labeled data for training.
Ranked #13 on
Medical Visual Question Answering
on VQA-RAD
(using extra training data)
Scalable Place Recognition Under Appearance Change for Autonomous Driving
Our experiments show that, compared to state-of-the-art techniques, our method has much greater potential for large-scale place recognition for autonomous driving.
Uncertainty in Model-Agnostic Meta-Learning using Variational Inference
We introduce a new, rigorously-formulated Bayesian meta-learning algorithm that learns a probability distribution of model parameter prior for few-shot learning.
Bayesian Generative Active Deep Learning
Deep learning models have demonstrated outstanding performance in several problems, but their training process tends to require immense amounts of computational and human resources for training and labeling, constraining the types of problems that can be tackled.
Simultaneous Feature Aggregating and Hashing for Compact Binary Code Learning
This global vector is then subjected to a hashing function to generate a binary hash code.
A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning
Another approach explored in the field relies on an ad-hoc linearization (in terms of N) of the triplet loss that introduces class centroids, which must be optimized using the whole training set for each mini-batch - this means that a naive implementation of this approach has run-time complexity O(N^2).
SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences
In particular, our work enables the use of randomized methods for point cloud registration without the need of putative correspondences.
V2CNet: A Deep Learning Framework to Translate Videos to Commands for Robotic Manipulation
We propose V2CNet, a new deep learning framework to automatically translate the demonstration videos to commands that can be directly used in robotic applications.
SASSE: Scalable and Adaptable 6-DOF Pose Estimation
In this paper, we present a novel 6-DOF localization system that for the first time simultaneously achieves all the three characteristics: significantly sub-linear storage growth, agnosticism to image descriptors, and customizability to available storage and computational resources.
Learning Pairwise Relationship for Multi-object Detection in Crowded Scenes
As the post-processing step for object detection, non-maximum suppression (GreedyNMS) is widely used in most of the detectors for many years.
Visual Localization Under Appearance Change: Filtering Approaches
Our approaches rely on local features with an encoding technique to represent an image as a single vector.
A Binary Optimization Approach for Constrained K-Means Clustering
This approach allows us to solve constrained K-Means where multiple types of constraints can be simultaneously enforced.
MediaEval 2018: Predicting Media Memorability Task
In this paper, we present the Predicting Media Memorability task, which is proposed as part of the MediaEval 2018 Benchmarking Initiative for Multimedia Evaluation.
G2D: from GTA to Data
This document describes G2D, a software that enables capturing videos from Grand Theft Auto V (GTA V), a popular role playing game set in an expansive virtual city.
Bayesian Semantic Instance Segmentation in Open Set World
In this paper, we present a novel open-set semantic instance segmentation approach capable of segmenting all known and unknown object classes in images, based on the output of an object detector trained on known object classes.
Object Captioning and Retrieval with Natural Language
The key idea of our approach is the use of object descriptions to provide the detailed understanding of an object.
Deep-6DPose: Recovering 6D Object Pose from a Single RGB Image
Detecting objects and their 6D poses from only RGB images is an important task for many robotic applications.
Binary Constrained Deep Hashing Network for Image Retrieval without Manual Annotation
However, training deep hashing networks for the task is challenging due to the binary constraints on the hash codes, the similarity preserving property, and the requirement for a vast amount of labelled images.
Simultaneous Compression and Quantization: A Joint Approach for Efficient Unsupervised Hashing
For unsupervised data-dependent hashing, the two most important requirements are to preserve similarity in the low-dimensional feature space and to minimize the binary quantization loss.
On-device Scalable Image-based Localization via Prioritized Cascade Search and Fast One-Many RANSAC
In order to overcome the resource constraints of mobile devices, we propose a system design that leverages the scalability advantage of image retrieval and accuracy of 3D model-based localization.
From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval
In the large-scale image retrieval task, the two most important requirements are the discriminability of image representations and the efficiency in computation and storage of representations.
Compact Hash Code Learning with Binary Deep Neural Network
This design has overcome a challenging problem in some previous works: optimizing non-smooth objective functions because of binarization.
Supervised Hashing with End-to-End Binary Deep Neural Network
Image hashing is a popular technique applied to large scale content-based visual retrieval due to its compact and efficient binary codes.
Deterministic Approximate Methods for Maximum Consensus Robust Fitting
Further, our approach is naturally applicable to estimation problems with geometric residuals
AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection
We propose AffordanceNet, a new deep learning approach to simultaneously detect multiple objects and their affordances from RGB images.
SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes
This paper presents SceneCut, a novel approach to jointly discover previously unseen objects and non-object surfaces using a single RGB-D image.
Real-Time 6DOF Pose Relocalization for Event Cameras with Stacked Spatial LSTM Networks
Our method first creates the event image from a list of events that occurs in a very short time interval, then a Stacked Spatial LSTM Network (SP-LSTM) is used to learn the camera pose.
Selective Deep Convolutional Features for Image Retrieval
Recent work adopts fine-tuned strategies to further improve the discriminative power of the descriptors.
Enhance Feature Discrimination for Unsupervised Hashing
We introduce a novel approach to improve unsupervised hashing.
Simultaneous Feature Aggregating and Hashing for Large-scale Image Search
This feature vector is then subjected to a hashing function that produces a binary hash code.
Binary Hashing with Semidefinite Relaxation and Augmented Lagrangian
This paper proposes two approaches for inferencing binary codes in two-step (supervised, unsupervised) hashing.
Learning to Hash with Binary Deep Neural Network
Our resulting optimization with these binary, independence, and balance constraints is difficult to solve.
Embedding based on function approximation for large scale image search
The objective of this paper is to design an embedding method that maps local features describing an image (e. g. SIFT) to a higher dimensional representation useful for the image retrieval problem.
Image-based Vehicle Analysis using Deep Neural Network: A Systematic Study
We address the vehicle detection and classification problems using Deep Neural Networks (DNNs) approaches.
Discrete Hashing with Deep Neural Network
This paper addresses the problem of learning binary hash codes for large scale image search by proposing a novel hashing method based on deep neural network.
FAemb: A Function Approximation-Based Embedding Method for Image Retrieval
The embedded vectors resulted by the function approximation process are then aggregated to form a single representation used in the image retrieval framework.
