Search Results for author:
Found 50 papers, 25 papers with code
Deep Image Matting
We evaluate our algorithm on the image matting benchmark, our testing set, and a wide variety of real images.
Free-Form Image Inpainting with Gated Convolution
We present a generative image inpainting system to complete images with free-form mask and guidance.
Ranked #3 on
Image Inpainting
on Places2 val
Wide Activation for Efficient and Accurate Image Super-Resolution
Keras-based implementation of WDSR, EDSR and SRGAN for single image super-resolution
Ranked #4 on
Multi-Frame Super-Resolution
on PROBA-V
AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
Notably, by setting optimized channel numbers, our AutoSlim-MobileNet-v2 at 305M FLOPs achieves 74. 2% top-1 accuracy, 2. 4% better than default MobileNet-v2 (301M FLOPs), and even 0. 2% better than RL-searched MNasNet (317M FLOPs).
When AWGN-based Denoiser Meets Real Noises
In this paper, we propose a novel approach to boost the performance of a real image denoiser which is trained only with synthetic pixel-independent noise data dominated by AWGN.
Ranked #2 on
Denoising
on Darmstadt Noise Dataset
Slimmable Neural Networks
Instead of training individual networks with different width configurations, we train a shared network with switchable batch normalization.
Universally Slimmable Networks and Improved Training Techniques
We also evaluate the proposed US-Nets and improved training techniques on tasks of image super-resolution and deep reinforcement learning.
SkyNet: A Champion Model for DAC-SDC on Low Power Object Detection
Developing artificial intelligence (AI) at the edge is always challenging, since edge devices have limited computation capability and memory resources but need to meet demanding requirements, such as real-time processing, high throughput performance, and high inference accuracy.
SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems
Object detection and tracking are challenging tasks for resource-constrained embedded systems.
Devil in the Details: Towards Accurate Single and Multiple Human Parsing
Human parsing has received considerable interest due to its wide application potentials.
Ranked #2 on
Person Re-Identification
on Market-1501-C
Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification
Upon our SSG, we further introduce a clustering-guided semisupervised approach named SSG ++ to conduct the one-shot domain adaption in an open set setting (i. e. the number of independent identities from the target domain is unknown).
Revisiting RCNN: On Awakening the Classification Power of Faster RCNN
Recent region-based object detectors are usually built with separate classification and localization branches on top of shared feature extraction networks.
Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection
In particular, DCR places a separate classification network in parallel with the localization network (base detector).
Self-produced Guidance for Weakly-supervised Object Localization
A stagewise approach is proposed to incorporate high confident object regions to learn the SPG masks.
Ranked #1 on
Weakly-Supervised Object Localization
on ILSVRC 2015
SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation
In this way, the possibilities embedded in the produced similarity maps can be adapted to guide the process of segmenting objects.
Ranked #89 on
Few-Shot Semantic Segmentation
on PASCAL-5i (5-Shot)
Deep Interactive Object Selection
Interactive object selection is a very important research problem and has many applications.
Ranked #11 on
Interactive Segmentation
on SBD
Learning Hierarchical Semantic Image Manipulation through Structured Representations
In this work, we present a novel hierarchical framework for semantic image manipulation.
Improving Object Detection from Scratch via Gated Feature Reuse
In this paper, we present a simple and parameter-efficient drop-in module for one-stage object detectors like SSD when learning from scratch (i. e., without pre-trained models).
BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models
Without extra retraining or post-processing steps, we are able to train a single set of shared weights on ImageNet and use these weights to obtain child models whose sizes range from 200 to 1000 MFLOPs.
Ranked #30 on
Neural Architecture Search
on ImageNet
Horizontal Pyramid Matching for Person Re-identification
Despite the remarkable recent progress, person re-identification (Re-ID) approaches are still suffering from the failure cases where the discriminative body parts are missing.
Ranked #55 on
Person Re-Identification
on DukeMTMC-reID
YouTube-VOS: Sequence-to-Sequence Video Object Segmentation
End-to-end sequential learning to explore spatial-temporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i. e., even the largest video segmentation dataset only contains 90 short video clips.
Ranked #12 on
Video Object Segmentation
on YouTube-VOS 2018
(F-Measure (Unseen) metric)
Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction
Despite the recent advances in the literature, existing approaches are limited to moderately short-term prediction (less than a few seconds), while extrapolating it to a longer future quickly leads to destruction in structure and content.
Adversarial Complementary Learning for Weakly Supervised Object Localization
With such an adversarial learning, the two parallel-classifiers are forced to leverage complementary object regions for classification and can finally generate integral object localization together.
Ranked #2 on
Weakly-Supervised Object Localization
on ILSVRC 2016
NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results
This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+.
Unsupervised Representation Adversarial Learning Network: from Reconstruction to Generation
The newly proposed RepGAN is tested on MNIST, fashionMNIST, CelebA, and SVHN datasets to perform unsupervised classification, generation and reconstruction tasks.
Survey of Face Detection on Low-quality Images
However, previous proposed models are mostly trained and tested on good-quality images which are not always the case for practical applications like surveillance systems.
Deep GrabCut for Object Selection
In this paper, we propose a novel segmentation approach that uses a rectangle as a soft constraint by transforming it into an Euclidean distance map.
Joint Intermodal and Intramodal Label Transfers for Extremely Rare or Unseen Classes
One of our goals in this paper is to develop a model for revealing the functional relationships between text and image features as to directly transfer intermodal and intramodal labels to annotate the images.
Learning a Mixture of Deep Networks for Single Image Super-Resolution
This paper proposes the method of learning a mixture of SR inference modules in a unified framework to tackle this problem.
UnitBox: An Advanced Object Detection Network
In present object detection systems, the deep convolutional neural networks (CNNs) are utilized to predict bounding boxes of object candidates, and have gained performance advantages over the traditional region proposal methods.
Deep Networks for Image Super-Resolution with Sparse Prior
We show that a sparse coding model particularly designed for super-resolution can be incarnated as a neural network, and trained in a cascaded structure from end to end.
Scalable Similarity Learning using Large Margin Neighborhood Embedding
In this paper, we present an image similarity learning method that can scale well in both the number of images and the dimensionality of image descriptors.
GPU Asynchronous Stochastic Gradient Descent to Speed Up Neural Network Training
The ability to train large-scale neural networks has resulted in state-of-the-art performance in many areas of computer vision.
TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection
This work provides a simple approach to discover tight object bounding boxes with only image-level supervision, called Tight box mining with Surrounding Segmentation Context (TS2C).
Weakly Supervised Scene Parsing with Point-based Distance Metric Learning
Semantic scene parsing is suffering from the fact that pixel-level annotations are hard to be collected.
STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identification
Thus, a more robust clip-level feature representation can be generated according to a weighted sum operation guided by the mined 2-D attention score matrix.
Large-Scale Person Re-Identification
Video-Based Person Re-Identification
BodyPrint: Pose Invariant 3D Shape Matching of Human Bodies
3D human body shape matching has large potential on many real world applications, especially with the recent advances in the 3D range sensing technology.
Robust Video Super-Resolution With Learned Temporal Dynamics
Second, we reduce the complexity of motion between neighboring frames using a spatial alignment network that is much more robust and efficient than competing alignment methods and can be jointly trained with the temporal adaptive network in an end-to-end manner.
Towards Instance-level Image-to-Image Translation
The proposed INIT exhibits three import advantages: (1) the instance-level objective loss can help learn a more accurate reconstruction and incorporate diverse attributes of objects; (2) the styles used for target domain of local/global areas are from corresponding spatial regions in source domain, which intuitively is a more reasonable mapping; (3) the joint training process can benefit both fine and coarse granularity and incorporates instance information to improve the quality of global translation.
High Frequency Residual Learning for Multi-Scale Image Classification
We present a novel high frequency residual learning framework, which leads to a highly efficient multi-scale network (MSNet) architecture for mobile and embedded vision problems.
SPGNet: Semantic Prediction Guidance for Scene Parsing
The multi-scale context module refers to the operations to aggregate feature responses from a large spatial extent, while the single-stage encoder-decoder structure encodes the high-level semantic information in the encoder path and recovers the boundary information in the decoder path.
FLNet: Landmark Driven Fetching and Learning Network for Faithful Talking Facial Animation Synthesis
In this paper, We present a landmark driven two-stream network to generate faithful talking facial animation, in which more facial details are created, preserved and transferred from multiple source images instead of a single one.
FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimation
In clinical deployment, however, they suffer dramatic performance drops due to mismatched distributions between training and testing datasets, commonly encountered in the clinical environment.
Image Segmentation of Zona-Ablated Human Blastocysts
Automating human preimplantation embryo grading offers the potential for higher success rates with in vitro fertilization (IVF) by providing new quantitative and objective measures of embryo quality.
Inner Cell Mass and Trophectoderm Segmentation in Human Blastocyst Images using Deep Neural Network
Embryo quality assessment based on morphological attributes is important for achieving higher pregnancy rates from in vitro fertilization (IVF).
Context-Aware Automatic Text Simplification of Health Materials in Low-Resource Domains
We also show the enhanced accuracy of our system over directly-supervised neural methods in this low-resource setting.
Scaling Up Neural Architecture Search with Big Single-Stage Models
In this work, we propose BigNAS, an approach that simplifies this workflow and scales up neural architecture search to target a wide range of model sizes simultaneously.
YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark
End-to-end sequential learning to explore spatialtemporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i. e., even the largest video segmentation dataset only contains 90 short video clips.
AgentMD: Empowering Language Agents for Risk Prediction with Large-Scale Clinical Tool Learning
Clinical calculators play a vital role in healthcare by offering accurate evidence-based predictions for various purposes such as prognosis.
