Search Results for author:
Found 75 papers, 34 papers with code
GINet: Graph Interaction Network for Scene Parsing
GI unit is further improved by the SC-loss to enhance the semantic representations over the exemplar-based semantic graph.
DemoFusion: Democratising High-Resolution Image Generation With No $$$
High-resolution image generation with Generative Artificial Intelligence (GenAI) has immense potential but, due to the enormous capital investment required for training, it is increasingly centralised to a few large corporations, and hidden behind paywalls.
The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification
The proposed loss function, termed as mutual-channel loss (MC-Loss), consists of two channel-specific components: a discriminality component and a diversity component.
Ranked #29 on
Fine-Grained Image Classification
on FGVC Aircraft
Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches
In this work, we propose a novel framework for fine-grained visual classification to tackle these problems.
Ranked #17 on
Fine-Grained Image Classification
on Stanford Cars
Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis
To overcome these challenges, in this paper, we propose a dual graph convolutional networks (DualGCN) model that considers the complementarity of syntax structures and semantic correlations simultaneously.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Your "Flamingo" is My "Bird": Fine-Grained, or Not
For that, we re-envisage the traditional setting of FGVC, from single-label classification, to that of top-down traversal of a pre-defined coarse-to-fine label hierarchy -- so that our answer becomes "bird"-->"Phoenicopteriformes"-->"Phoenicopteridae"-->"flamingo".
Ranked #16 on
Fine-Grained Image Classification
on FGVC Aircraft
On-the-Fly Category Discovery
Our code is available at https://github. com/PRIS-CV/On-the-fly-Category-Discovery.
Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification
Conventional few-shot learning methods however cannot be naively adopted for this fine-grained setting -- a quick pilot study reveals that they in fact push for the opposite (i. e., lower inter-class variations and higher intra-class variations).
OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
A deep neural network of multiple nonlinear layers forms a large function space, which can easily lead to overfitting when it encounters small-sample data.
BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification
Motivated by this, we propose a so-called \textit{Bi-Similarity Network} (\textit{BSNet}) that consists of a single embedding module and a bi-similarity module of two similarity measures.
Progressive Co-Attention Network for Fine-grained Visual Classification
Fine-grained visual classification aims to recognize images belonging to multiple sub-categories within a same category.
Ranked #32 on
Fine-Grained Image Classification
on FGVC Aircraft
Mind the Gap: Enlarging the Domain Gap in Open Set Domain Adaptation
The key insight lies with how we exploit the mutually beneficial information between two networks; (a) to separate samples of known and unknown classes, (b) to maximize the domain confusion between source and target domain without the influence of unknown samples.
Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization
Due to lack of data, overfitting ubiquitously exists in real-world applications of deep neural networks (DNNs).
Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained Features
Finally, we can obtain multiple discriminative regions on high-level feature channels and obtain multiple more minute regions within these discriminative regions on middle-level feature channels.
ScaleNet: Searching for the Model to Scale
Recently, community has paid increasing attention on model scaling and contributed to developing a model family with a wide spectrum of scales.
Dual-attention Guided Dropblock Module for Weakly Supervised Object Localization
This module contains two key components, the channel attention guided dropout (CAGD) and the spatial attention guided dropblock (SAGD).
Super-Resolution Information Enhancement For Crowd Counting
As the proposed method requires SR labels, we further propose a Super-Resolution Crowd Counting dataset (SR-Crowd).
Multi-Semantic Fusion Model for Generalized Zero-Shot Skeleton-Based Action Recognition
In order to solve this dilemma, we propose a multi-semantic fusion (MSF) model for improving the performance of GZSSAR, where two kinds of class-level textual descriptions (i. e., action descriptions and motion descriptions), are collected as auxiliary semantic information to enhance the learning efficacy of generalizable skeleton features.
Action Recognition
Generalized Zero Shot skeletal action recognition
+1
SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval
Key to our network design is the embedding of unique characteristics of human sketch, where (i) a two-branch CNN-RNN architecture is adapted to explore the temporal ordering of strokes, and (ii) a novel hashing loss is specifically designed to accommodate both the temporal and abstract traits of sketches.
Knowledge Transfer Based Fine-grained Visual Classification
Convolution neural networks (CNNs), which employ the cross entropy loss (CE-loss) as the loss function, show poor performance since the model can only learn the most discriminative part and ignore other meaningful regions.
Ranked #36 on
Fine-Grained Image Classification
on CUB-200-2011
Learning Invariant Visual Representations for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to recognize novel compositions using knowledge learned from seen attribute-object compositions in the training set.
Clue Me In: Semi-Supervised FGVC with Out-of-Distribution Data
Despite great strides made on fine-grained visual classification (FGVC), current methods are still heavily reliant on fully-supervised paradigms where ample expert labels are called for.
Benchmarking Segmentation Models with Mask-Preserved Attribute Editing
We evaluate a broad variety of semantic segmentation models, spanning from conventional close-set models to recent open-vocabulary large models on their robustness to different types of variations.
CMF: Cascaded Multi-model Fusion for Referring Image Segmentation
To solve this problem, we propose a simple yet effective Cascaded Multi-modal Fusion (CMF) module, which stacks multiple atrous convolutional layers in parallel and further introduces a cascaded branch to fuse visual and linguistic features.
ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification
Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small.
Multi-View Active Fine-Grained Visual Recognition
Despite the remarkable progress of Fine-grained visual classification (FGVC) with years of history, it is still limited to recognizing 2 images.
Fine-Grained Image Classification
Fine-Grained Visual Recognition
HumanRecon: Neural Reconstruction of Dynamic Human Using Geometric Cues and Physical Priors
These priors ensure the color rendered along rays to be robust to view direction and reduce the inherent ambiguities of density estimated along rays.
GPCA: A Probabilistic Framework for Gaussian Process Embedded Channel Attention
In this paper, we propose Gaussian process embedded channel attention (GPCA) module and further interpret the channel attention schemes in a probabilistic way.
Caption Feature Space Regularization for Audio Captioning
To eliminate this negative effect, in this paper, we propose a two-stage framework for audio captioning: (i) in the first stage, via the contrastive learning, we construct a proxy feature space to reduce the distances between captions correlated to the same audio, and (ii) in the second stage, the proxy feature space is utilized as additional supervision to encourage the model to be optimized in the direction that benefits all the correlated captions.
Multi-View Active Fine-Grained Recognition
As fine-grained visual classification (FGVC) being developed for decades, great works related have exposed a key direction -- finding discriminative local regions and revealing subtle differences.
Competing Ratio Loss for Discriminative Multi-class Image Classification
However, during the training of the deep convolutional neural network, the value of NLLR is not always positive or negative, which severely affects the convergence of NLLR.
Structured DropConnect for Uncertainty Inference in Image Classification
For image classification tasks, we propose a structured DropConnect (SDC) framework to model the output of a deep neural network by a Dirichlet distribution.
Fine-Grained Age Estimation in the wild with Attention LSTM Networks
Then, we fine-tune the ResNets or the RoR on the target age datasets to extract the global features of face images.
Ranked #3 on
Age And Gender Classification
on Adience Age
(using extra training data)
Decorrelation of Neutral Vector Variables: Theory and Applications
In this paper, we propose novel strategies for neutral vector variable decorrelation.
Cross-modal Subspace Learning for Fine-grained Sketch-based Image Retrieval
Sketch-based image retrieval (SBIR) is challenging due to the inherent domain-gap between sketch and photo.
Ranked #5 on
Sketch-Based Image Retrieval
on Chairs
DNN Filter Bank Cepstral Coefficients for Spoofing Detection
In order to improve the reliability of speaker verification systems, we develop a new filter bank based cepstral feature, deep neural network filter bank cepstral coefficients (DNN-FBCC), to distinguish between natural and spoofed speech.
BALSON: Bayesian Least Squares Optimization with Nonnegative L1-Norm Constraint
In order to explicitly characterize the nonnegative L1-norm constraint of the parameters, we further approximate the true posterior distribution by a Dirichlet distribution.
Infinite Mixture of Inverted Dirichlet Distributions
In this work, we develop a novel Bayesian estimation method for the Dirichlet process (DP) mixture of the inverted Dirichlet distributions, which has been shown to be very flexible for modeling vectors with positive elements.
SEA: A Combined Model for Heat Demand Prediction
ENN and ARIMA are used to predict seasonal and trend components, respectively.
Dirichlet Mixture Model based VQ Performance Prediction for Line Spectral Frequency
In this paper, we continue our previous work on the Dirichlet mixture model (DMM)-based VQ to derive the performance bound of the LSF VQ.
Classification of EEG Signal based on non-Gaussian Neutral Vector
In the design of brain-computer interface systems, classification of Electroencephalogram (EEG) signals is the essential part and a challenging task.
Mobile big data analysis with machine learning
Finally, we summarize the main challenges and future development directions of mobile big data analysis.
Impacts of Weather Conditions on District Heat System
Using artificial neural network for the prediction of heat demand has attracted more and more attention.
Histogram Transform-based Speaker Identification
A novel text-independent speaker identification (SI) method is proposed.
Deep Neural Network for Analysis of DNA Methylation Data
Many researches demonstrated that the DNA methylation, which occurs in the context of a CpG, has strong correlation with diseases, including cancer.
Language Identification with Deep Bottleneck Features
In order to improve the SLD accuracy of short utterances a phase vocoder based time-scale modification(TSM) method is used to reduce and increase speech rated of the test utterance.
On the Convergence of Extended Variational Inference for Non-Gaussian Statistical Models
Recently, an improved framework, namely the extended variational inference (EVI), has been introduced and applied to derive analytically tractable solution by employing lower-bound approximation to the variational objective function.
Channel Max Pooling Layer for Fine-Grained Vehicle Classification
Experimental results on two fine-grained vehicle datasets, the Stanford Cars-196 dataset and the Comp Cars dataset, demonstrate that the proposed layer could improve classification accuracies of deep neural networks on fine-grained vehicle classification in the situation that a massive of parameters are reduced.
Deep Zero-Shot Learning for Scene Sketch
We introduce a novel problem of scene sketch zero-shot learning (SSZSL), which is a challenging task, since (i) different from photo, the gap between common semantic domain (e. g., word vector) and sketch is too huge to exploit common semantic knowledge as the bridge for knowledge transfer, and (ii) compared with single-object sketch, more expressive feature representation for scene sketch is required to accommodate its high-level of abstraction and complexity.
Competing Ratio Loss for Discriminative Multi-class Image Classification
A lot of studies of image classification based on deep convolutional neural network focus on the network structure to improve the image classification performance.
Semi-Heterogeneous Three-Way Joint Embedding Network for Sketch-Based Image Retrieval
How to align abstract sketches and natural images into a common high-level semantic space remains a key problem in SBIR.
Weakly Supervised Attention Pyramid Convolutional Neural Network for Fine-Grained Visual Classification
Classifying the sub-categories of an object from the same super-category (e. g. bird species, car and aircraft models) in fine-grained visual classification (FGVC) highly relies on discriminative feature representation and accurate region localization.
Fine-Grained Instance-Level Sketch-Based Video Retrieval
Existing sketch-analysis work studies sketches depicting static objects or scenes.
A Concise Review of Recent Few-shot Meta-learning Methods
Few-shot meta-learning has been recently reviving with expectations to mimic humanity's fast adaption to new concepts based on prior knowledge.
SSKD: Self-Supervised Knowledge Distillation for Cross Domain Adaptive Person Re-Identification
To this end, we propose a Self-Supervised Knowledge Distillation (SSKD) technique containing two modules, the identity learning and the soft label learning.
CC-Loss: Channel Correlation Loss For Image Classification
The loss function is a key component in deep learning models.
Actor and Action Modular Network for Text-based Video Segmentation
Previous methods fail to explicitly align the video content with the textual query in a fine-grained manner according to the actor and its action, due to the problem of \emph{semantic asymmetry}.
Ranked #9 on
Referring Expression Segmentation
on J-HMDB
DS-UI: Dual-Supervised Mixture of Gaussian Mixture Models for Uncertainty Inference
In the DS-UI, we combine the classifier of a DNN, i. e., the last fully-connected (FC) layer, with a mixture of Gaussian mixture models (MoGMM) to obtain an MoGMM-FC layer.
Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting
In this paper, we propose a simple yet efficient counting network based on point-level annotations.
TLRM: Task-level Relation Module for GNN-based Few-Shot Learning
We consider this method of measuring relation of samples only models the sample-to-sample relation, while neglects the specificity of different tasks.
Grad-CAM guided channel-spatial attention module for fine-grained visual classification
The proposed method outperforms the SOTA attention modules in the FGVC task.
Ranked #21 on
Fine-Grained Image Classification
on FGVC Aircraft
DF^2AM: Dual-level Feature Fusion and Affinity Modeling for RGB-Infrared Cross-modality Person Re-identification
Meanwhile, to further mining the relationships between global features from person images, we propose an Affinities Modeling (AM) module to obtain the optimal intra- and inter-modality image matching.
Cross-Modality Person Re-identification
Person Re-Identification
Unsupervised Person Re-identification via Simultaneous Clustering and Consistency Learning
Unsupervised person re-identification (re-ID) has become an important topic due to its potential to resolve the scalability problem of supervised re-ID models.
Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments
Few-shot image classification is a challenging problem that aims to achieve the human level of recognition based only on a small number of training images.
Channel DropBlock: An Improved Regularization Method for Fine-Grained Visual Classification
Classifying the sub-categories of an object from the same super-category (e. g., bird) in a fine-grained visual classification (FGVC) task highly relies on mining multiple discriminative features.
Cross-layer Navigation Convolutional Neural Network for Fine-grained Visual Classification
Then, attention mechanisms are used after feature fusion to extract spatial and channel information while linking the high-level semantic information and the low-level texture features, which can better locate the discriminative regions for the FGVC.
Domain Generalization via Frequency-domain-based Feature Disentanglement and Interaction
Adaptation to out-of-distribution data is a meta-challenge for all statistical learning algorithms that strongly rely on the i. i. d.
HCLD: A Hierarchical Framework for Zero-shot Cross-lingual Dialogue System
Recently, many task-oriented dialogue systems need to serve users in different languages.
An Erudite Fine-Grained Visual Classification Model
Therefore, we first propose a feature disentanglement module and a feature re-fusion module to reduce negative transfer and boost positive transfer between different datasets.
LaDA: Latent Dialogue Action For Zero-shot Cross-lingual Neural Network Language Modeling
The model consists of an additional layer of latent dialogue action.
Task-aware Adaptive Learning for Cross-domain Few-shot Learning
In this paper, we first observe the dependence of task-specific parameter configuration on the target task.
Vision-language Assisted Attribute Learning
Attribute labeling at large scale is typically incomplete and partial, posing significant challenges to model optimization.
