Search Results for author:
Found 24 papers, 12 papers with code
SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers
For the first time, it achieves an ImageNet-1K top-1 accuracy of around 80% at a speed of 1. 0 frame/sec on the SBC.
Visual Abductive Reasoning Meets Driving Hazard Prediction
To enable research in this understudied area, a new dataset named the DHPR (Driving Hazard Prediction and Reasoning) dataset is created.
That's BAD: Blind Anomaly Detection by Implicit Local Feature Clustering
They consider an unsupervised setting, specifically the one-class setting, in which we assume the availability of a set of normal (\textit{i. e.}, anomaly-free) images for training.
Contextual Affinity Distillation for Image Anomaly Detection
The local student, which is used in previous studies mainly focuses on structural anomaly detection while the global student pays attention to logical anomalies.
Ranked #13 on
Anomaly Detection
on MVTec LOCO AD
Reference-based Motion Blur Removal: Learning to Utilize Sharpness in the Reference Image
We can utilize an alternative shot of the identical scene, just like in video deblurring, or we can even employ a distinct image from another scene.
RefVSR++: Exploiting Reference Inputs for Reference-based Video Super-resolution
Then, we propose an improved method, RefVSR++, which can aggregate two features in parallel in the temporal direction, one for aggregating the fused LR and Ref inputs and the other for Ref inputs over time.
Reference-based Video Super-Resolution
Video Super-Resolution
GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features
Current state-of-the-art methods for image captioning employ region-based features, as they provide object-level information that is essential to describe the content of images; they are usually extracted by an object detector such as Faster R-CNN.
Ranked #8 on
Image Captioning
on nocaps in-domain
Rectifying Open-set Object Detection: A Taxonomy, Practical Applications, and Proper Evaluation
In this paper, we first point out that the recent studies' formalization of OSOD, which generalizes open-set recognition (OSR) and thus considers an unlimited variety of unknown objects, has a fundamental issue.
Single-image Defocus Deblurring by Integration of Defocus Map Prediction Tracing the Inverse Problem Computation
Considering the spatial variant property of the defocus blur and the blur level indicated in the defocus map, we employ the defocus map as conditional guidance to adjust the features from the input blurring images instead of simple concatenation.
Learning Regularized Multi-Scale Feature Flow for High Dynamic Range Imaging
Reconstructing ghosting-free high dynamic range (HDR) images of dynamic scenes from a set of multi-exposure images is a challenging task, especially with large object motion and occlusions, leading to visible artifacts using existing methods.
Rethinking Unsupervised Domain Adaptation for Semantic Segmentation
Due to its high annotation cost, researchers have developed many UDA methods for semantic segmentation, which assume no labeled sample is available in the target domain.
Improved Few-shot Segmentation by Redefinition of the Roles of Multi-level CNN Features
This study is concerned with few-shot segmentation, i. e., segmenting the region of an unseen object class in a query image, given support image(s) of its instances.
Cross-Region Domain Adaptation for Class-level Alignment
To cope with this, we propose a method that applies adversarial training to align two feature distributions in the target domain.
Ranked #1 on
Domain Adaptation
on Synscapes-to-Cityscapes
Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes
To consider if and how well we can utilize such information stored in RAW-format images for image matching, we have created a new dataset named MID (matching in the dark).
Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks
It then integrates the prediction with the visual information etc., yielding the final prediction of an action and an object.
How Can CNNs Use Image Position for Segmentation?
We draw a mixed conclusion from the experimental results; the positional encoding certainly works in some cases, but the absolute image position may not be so important for segmentation tasks as we think.
Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs
It has been a primary concern in recent studies of vision and language tasks to design an effective attention mechanism dealing with interactions between the two modalities.
Ranked #7 on
Visual Dialog
on Visual Dialog v1.0 test-std
Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors
The employment of convolutional neural networks has led to significant performance improvement on the task of object detection.
Restoring Images with Unknown Degradation Factors by Recurrent Use of a Multi-branch Network
The employment of convolutional neural networks has achieved unprecedented performance in the task of image restoration for a variety of degradation factors.
Hyperparameter-Free Out-of-Distribution Detection Using Softmax of Scaled Cosine Similarity
The ability to detect out-of-distribution (OOD) samples is vital to secure the reliability of deep neural networks in real-world applications.
Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration
In this paper, we study design of deep neural networks for tasks of image restoration.
Attention-based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions
There are many different types of distortion which affect image quality.
Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search
Researchers have applied deep neural networks to image restoration tasks, in which they proposed various network architectures, loss functions, and training methods.
A Genetic Programming Approach to Designing Convolutional Neural Network Architectures
To evaluate the proposed method, we constructed a CNN architecture for the image classification task with the CIFAR-10 dataset.
