Search Results for author:
Found 46 papers, 18 papers with code
Introducing Competition to Boost the Transferability of Targeted Adversarial Examples through Clean Feature Mixup
Deep neural networks are widely known to be susceptible to adversarial examples, which can cause incorrect predictions through subtle input modifications.
Sketch-based Video Object Localization
We introduce Sketch-based Video Object Localization (SVOL), a new task aimed at localizing spatio-temporal object boxes in video queried by the input sketch.
Liveness score-based regression neural networks for face anti-spoofing
In this paper, we propose a liveness score-based regression network for overcoming the dependency on third party networks and users.
RainUNet for Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts
This paper presents a solution to the Weather4cast 2022 Challenge Stage 2.
Towards Good Practices for Missing Modality Robust Action Recognition
We ask: how can we train a model that is robust to missing modalities?
Supervised Contrastive Learning on Blended Images for Long-tailed Recognition
The imbalanced data form a biased feature space, which deteriorates the performance of the recognition model.
Ranked #15 on
Long-tail Learning
on CIFAR-100-LT (ρ=10)
Bridging Implicit and Explicit Geometric Transformation for Single-Image View Synthesis
Although recent methods generate high-quality novel views, synthesizing with only one explicit or implicit 3D geometry has a trade-off between two objectives that we call the "seesaw" problem: 1) preserving reprojected contents and 2) completing realistic out-of-view regions.
Temporal Flow Mask Attention for Open-Set Long-Tailed Recognition of Wild Animals in Camera-Trap Images
Camera traps, unmanned observation devices, and deep learning-based image recognition systems have greatly reduced human effort in collecting and analyzing wildlife images.
Modality Mixer for Multi-modal Action Recognition
In multi-modal action recognition, it is important to consider not only the complementary nature of different modalities but also global action content.
Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input
To tackle this limitation, we propose the object-based diverse input (ODI) method that draws an adversarial image on a 3D object and induces the rendered image to be classified as the target class.
Balancing Domain Experts for Long-Tailed Camera-Trap Recognition
Here, we propose a unified framework and introduce two datasets for long-tailed camera-trap recognition.
Explore-And-Match: Bridging Proposal-Based and Proposal-Free With Transformer for Sentence Grounding in Videos
To our surprise, we found that training schedule shows divide-and-conquer-like pattern: time segments are first diversified regardless of the target, then coupled with each target, and fine-tuned to the target again.
Residual-Guided Learning Representation for Self-Supervised Monocular Depth Estimation
In this paper, we propose residual guidance loss that enables the depth estimation network to embed the discriminative feature by transferring the discriminability of auto-encoded features.
Geometrically Adaptive Dictionary Attack on Face Recognition
We apply the GADA strategy to two existing attack methods and show overwhelming performance improvement in the experiments on the LFW and CPLFW datasets.
Learning to Discriminate Information for Online Action Detection: Analysis and Application
To overcome this problem, we propose a novel recurrent unit, named Information Discrimination Unit (IDU), which explicitly discriminates the information relevancy between an ongoing action and others to decide whether to accumulate the input information.
Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization
It significantly outperforms traditional and deep neural network-based methods in detecting and localizing tampered regions.
DnD: Dense Depth Estimation in Crowded Dynamic Indoor Scenes
We present a novel approach for estimating depth from a monocular camera as it moves through complex and crowded indoor environments, e. g., a department store or a metro station.
Improving Few-shot Learning with Weakly-supervised Object Localization
In this work, we propose a novel framework that generates class representations by extracting features from class-relevant regions of the images.
Semi-Supervised Domain Adaptation via Selective Pseudo Labeling and Progressive Self-Training
In SSDA, a small number of labeled target images are given for training, and the effectiveness of those data is demonstrated by the previous studies.
Few-shot Open-set Recognition by Transformation Consistency
Based on the transformation consistency, our method measures the difference between the transformed prototypes and a modified prototype set.
On the Effectiveness of Small Input Noise for Defending Against Query-based Black-Box Attacks
In this paper, we pay attention to an implicit assumption of query-based black-box adversarial attacks that the target model's output exactly corresponds to the query input.
Just a Few Points Are All You Need for Multi-View Stereo: A Novel Semi-Supervised Learning Method for Multi-View Stereo
We generate the spare ground truth of the DTU dataset for evaluation and extensive experiments verify that our SGT-MVSNet outperforms the state-of-the-art MVS methods on the sparse ground truth setting.
Multi-view Arbitrary Style Transfer
We propose a photometric consistency loss, which directly enforces the geometrically consistent style texture across the view, and a stroke consistency loss, which matches the characteristics and directions of the brushstrokes by aligning the local patches of the corresponding pixels before minimizing feature deviation.
Robust Federated Learning with Noisy Labels
To solve these problems, we introduce a novel federated learning scheme that the server cooperates with local models to maintain consistent decision boundaries by interchanging class-wise centroids.
Meta Batch-Instance Normalization for Generalizable Person Re-Identification
To this end, we combine learnable batch-instance normalization layers with meta-learning and investigate the challenging cases caused by both batch and instance normalization layers.
SAFENet: Self-Supervised Monocular Depth Estimation with Semantic-Aware Feature Extraction
In this paper, we propose SAFENet that is designed to leverage semantic information to overcome the limitations of the photometric loss.
Arbitrary Style Transfer using Graph Instance Normalization
Style transfer is the image synthesis task, which applies a style of one image to another while preserving the content.
Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation
Finally, the exploration scheme locally aligns features in a class-wise manner complementary to the attraction scheme by selectively aligning unlabeled target features complementary to the perturbation scheme.
Partial Domain Adaptation Using Graph Convolutional Networks
Although existing partial domain adaptation methods effectively down-weigh outliers' importance, they do not consider data structure of each domain and do not directly align the feature distributions of the same class in the source and target domains, which may lead to misalignment of category-level distributions.
Single-view 2D CNNs with Fully Automatic Non-nodule Categorization for False Positive Reduction in Pulmonary Nodule Detection
Note that, instead of manual categorization requiring the heavy workload of radiologists, we propose to automatically categorize non-nodules based on the autoencoder and k-means clustering.
Learning to Discriminate Information for Online Action Detection
For online action detection, in this paper, we propose a novel recurrent unit to explicitly discriminate the information relevant to an ongoing action from others.
Ranked #7 on
Online Action Detection
on TVSeries
Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification
To implement our approach, we introduce an ID-preserving person image generation network and a hierarchical feature learning module.
SRG: Snippet Relatedness-based Temporal Action Proposal Generator
Recent temporal action proposal generation approaches have suggested integrating segment- and snippet score-based methodologies to produce proposals with high recall and accurate boundaries.
Combinational Class Activation Maps for Weakly Supervised Object Localization
Most previous methods utilize the activation map corresponding to the highest activation source.
BitNet: Learning-Based Bit-Depth Expansion
Since insufficient bit-depth may generate annoying false contours or lose detailed visual appearance, bit-depth expansion (BDE) from low bit-depth (LBD) images to high bit-depth (HBD) images becomes more and more important.
CNN-based Semantic Segmentation using Level Set Loss
Note that each binary image consists of background and regions belonging to a class.
RPM-Net: Robust Pixel-Level Matching Networks for Self-Supervised Video Object Segmentation
In this paper, we introduce a self-supervised approach for video object segmentation without human labeled data. Specifically, we present Robust Pixel-level Matching Net-works (RPM-Net), a novel deep architecture that matches pixels between adjacent frames, using only color information from unlabeled videos for training.
Learning to Align Multi-Camera Domains using Part-Aware Clustering for Unsupervised Video Person Re-Identification
Since the cost of labeling increases dramatically as the number of cameras increases, it is difficult to apply the re-identification algorithm to a large camera network.
Why Does the VQA Model Answer No?: Improving Reasoning through Visual and Linguistic Inference
Moreover, by modifying the VQA model’s answer through the output of the NLI model, we show that VQA performance increases by 1. 1% from the original model.
Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection
Experimental results show that our approach effectively improves the performance of the one-stage object detection in unsupervised domain adaptation setting.
Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation
Unsupervised domain adaptation seeks to adapt the model trained on the source domain to the target domain.
A Global-Local Emebdding Module for Fashion Landmark Detection
To that end, in this paper, we propose a fashion landmark detection network with a global-local embedding module.
Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation
To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation.
Semi-Supervised Image Classification
Unsupervised Domain Adaptation
Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection
We construct a structured domain adaptation framework for our learning paradigm and introduce a practical way of DD for implementation.
Water-Filling: An Efficient Algorithm for Digitized Document Shadow Removal
In this paper, we propose a novel algorithm to rectify illumination of the digitized documents by eliminating shading artifacts.
Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.
