Search Results for author:
Found 47 papers, 21 papers with code
MetaMixer: A Regularization Strategy for Online Knowledge Distillation
Online knowledge distillation (KD) has received increasing attention in recent years.
Toward Extremely Lightweight Distracted Driver Recognition With Distillation-Based Neural Architecture Search and Knowledge Transfer
Experimental results on the Statefarm Distracted Driver Detection Dataset and AUC Distracted Driver Dataset show that the proposed approach is highly effective for recognizing distracted driving behaviors from photos: (1) the teacher network's accuracy surpasses the previous best accuracy; (2) the student network achieves very high accuracy with only 0. 42M parameters (around 55% of the previous most lightweight model).
Attribute-Guided Multi-Level Attention Network for Fine-Grained Fashion Retrieval
In branch 2, we first propose a multi-level attention module to extract a more discriminative representation under the guidance of a specific attribute.
Semi-supervised Fashion Compatibility Prediction by Color Distortion Prediction
In this paper, we propose a general color distortion prediction task forcing the baseline to recognize low-level image information to learn more discriminative representation for fashion compatibility prediction.
Fine-Grained Image Style Transfer with Visual Transformers
Such a design usually destroys the spatial information of the input images and fails to transfer fine-grained style patterns into style transfer results.
Improving Robustness to Out-of-Distribution Data by Frequency-based Augmentation
In order to improve the robustness against out-of-distribution data, we present a frequency-based data augmentation technique that replaces the frequency components with other images of the same class.
Prediction of Seismic Intensity Distributions Using Neural Networks
The ground motion prediction equation is commonly used to predict the seismic intensity distribution.
SAT: Self-adaptive training for fashion compatibility prediction
Then, we propose a self-adaptive triplet loss (SATL), where the DS of the outfit is considered.
Superclass Adversarial Attack
Adversarial attacks have only focused on changing the predictions of the classifier, but their danger greatly depends on how the class is mistaken.
Green Hierarchical Vision Transformer for Masked Image Modeling
We present an efficient approach for Masked Image Modeling (MIM) with hierarchical Vision Transformers (ViTs), allowing the hierarchical ViTs to discard masked patches and operate only on the visible ones.
Detecting Deepfakes with Self-Blended Images
In this paper, we present novel synthetic training data called self-blended images (SBIs) to detect deepfakes.
Learning Where to Learn in Cross-View Self-Supervised Learning
In this paper, we present a new approach, Learning Where to Learn (LEWEL), to adaptively aggregate spatial information of features, so that the projected embeddings could be exactly aligned and thus guide the feature learning better.
Edge-Level Explanations for Graph Neural Networks by Extending Explainability Methods for Convolutional Neural Networks
Graph Neural Networks (GNNs) are deep learning models that take graph data as inputs, and they are applied to various tasks such as traffic prediction and molecular property prediction.
Unsupervised Video Person Re-identification via Noise and Hard frame Aware Clustering
NHAC consists of a graph trimming module and a node re-sampling module.
Learning from Synthetic Shadows for Shadow Detection and Removal
To overcome this challenge, we present SynShadow, a novel large-scale synthetic shadow/shadow-free/matte image triplets dataset and a pipeline to synthesize it.
Predicting Online Video Advertising Effects with Multimodal Deep Learning
With expansion of the video advertising market, research to predict the effects of video advertising is getting more attention.
Are DNNs fooled by extremely unrecognizable images?
In this paper, we address the question of whether there can be fooling images with no characteristic pattern of natural objects locally or globally.
Image inpainting using frequency domain priors
To alleviate these problems, we investigate if it is possible to obtain better performance by training the networks using frequency domain information (Discrete Fourier Transform) along with the spatial domain information.
Re-identification = Retrieval + Verification: Back to Essence and Forward with a New Metric
In essence, current re-ID overemphasizes the importance of retrieval but underemphasizes that of verification, \textit{i. e.}, all returned images are considered as the target.
Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video Representation Leaning
It is convenient to treat PCL as a standard training strategy and apply it to many other works in self-supervised video feature learning.
Ranked #10 on
Self-supervised Video Retrieval
on UCF101
Self-Play Reinforcement Learning for Fast Image Retargeting
In this study, we address image retargeting, which is a task that adjusts input images to arbitrary sizes.
Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework
With the proposed Inter-Intra Contrastive (IIC) framework, we can train spatio-temporal convolutional networks to learn video representations.
Ranked #10 on
Self-supervised Video Retrieval
on HMDB51
Image Aesthetics Prediction Using Multiple Patches Preserving the Original Aspect Ratio of Contents
The spread of social networking services has created an increasing demand for selecting, editing, and generating impressive images.
Motion Representation Using Residual Frames with 3D CNN
In this paper, we propose a fast but effective way to extract motion features from videos utilizing residual frames as the input data in 3D ConvNets.
Investigating Generalization in Neural Networks under Optimally Evolved Training Perturbations
In this paper, we study the generalization properties of neural networks under input perturbations and show that minimal training data corruption by a few pixel modifications can cause drastic overfitting.
DeepSperm: A robust and real-time bull sperm-cell detection in densely populated semen videos
This study proposes an architecture, called DeepSperm, that solves the aforementioned challenges and is more accurate and faster than state-of-the-art architectures.
Rethinking Motion Representation: Residual Frames with 3D ConvNets for Better Action Recognition
Further analysis indicates that better motion features can be extracted using residual frames with 3D ConvNets, and our residual-frame-input path is a good supplement for existing RGB-frame-input models.
Assessing Robustness of Deep learning Methods in Dermatological Workflow
This paper aims to evaluate the suitability of current deep learning methods for clinical workflow especially by focusing on dermatology.
Weakly Supervised Video Summarization by Hierarchical Reinforcement Learning
For each subtask, the manager is trained to set a subgoal only by a task-level binary label, which requires much fewer labels than conventional approaches.
Hierarchical Reinforcement Learning
reinforcement-learning
+2
Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software
This paper tackles unpaired image enhancement, a task of learning a mapping function which transforms input images into enhanced images in the absence of input-output image pairs.
PixelRL: Fully Convolutional Network with Reinforcement Learning for Image Processing
However, the applications of deep reinforcement learning (RL) for image processing are still limited.
Object-Aware Instance Labeling for Weakly Supervised Object Detection
Weakly supervised object detection (WSOD), where a detector is trained with only image-level annotations, is attracting more and more attention.
Lunar surface image restoration using U-net based deep neural networks
Image restoration is a technique that reconstructs a feasible estimate of the original image from the noisy observation.
Improving image classifiers for small datasets by learning rate adaptations
Our paper introduces an efficient combination of established techniques to improve classifier performance, in terms of accuracy and training time.
Fully Convolutional Network with Multi-Step Reinforcement Learning for Image Processing
This paper tackles a new problem setting: reinforcement learning with pixel-wise rewards (pixelRL) for image processing.
Local and Global Optimization Techniques in Graph-Based Clustering
We propose a local optimization method, which is widely applicable to graph-based clustering cost functions.
Fast and Robust Estimation for Unit-Norm Constrained Linear Fitting Problems
M-estimator using iteratively reweighted least squares (IRLS) is one of the best-known methods for robust estimation.
Joint Optimization Framework for Learning with Noisy Labels
Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification.
Ranked #36 on
Image Classification
on Clothing1M
Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation
Can we detect common objects in a variety of image domains without instance-level annotations?
Ranked #4 on
Weakly Supervised Object Detection
on Watercolor2k
(using extra training data)
Object Detection for Comics using Manga109 Annotations
We annotated an existing image dataset of comics and created the largest annotation dataset, named Manga109-annotations.
Supervised classification of Dermatological diseases by Deep learning
This paper introduces a deep-learning based efficient classifier for common dermatological conditions, aimed at people without easy access to skin specialists.
PQk-means: Billion-scale Clustering for Product-quantized Codes
Data clustering is a fundamental operation in data analysis.
Residual Expansion Algorithm: Fast and Effective Optimization for Nonconvex Least Squares Problems
We propose the residual expansion (RE) algorithm: a global (or near-global) optimization method for nonconvex least squares problems.
PQTable: Non-exhaustive Fast Search for Product-quantized Codes using Hash Tables
In this paper, we propose a product quantization table (PQTable); a fast search method for product-quantized codes via hash-tables.
Uncalibrated Photometric Stereo by Stepwise Optimization Using Principal Components of Isotropic BRDFs
We propose a model that represents various isotropic reflectance functions by using the principal components of items in a dataset, and formulate the uncalibrated photometric stereo as a regression problem.
PQTable: Fast Exact Asymmetric Distance Neighbor Search for Product Quantization Using Hash Tables
We propose the product quantization table (PQTable), a product quantization-based hash table that is fast and requires neither parameter tuning nor training steps.
Sketch-based Manga Retrieval using Manga109 Dataset
From the experiments, we verified that: (1) the retrieval accuracy of the proposed method is higher than those of previous methods; (2) the proposed method can localize an object instance with reasonable runtime and accuracy; and (3) sketch querying is useful for manga search.
