Search Results for author:
Found 51 papers, 31 papers with code
SuperLoRA: Parameter-Efficient Unified Adaptation of Multi-Layer Attention Modules
Low-rank adaptation (LoRA) and its variants are widely employed in fine-tuning large models, including large language models for natural language processing and diffusion models for computer vision.
GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping
In particular, we propose an Efficient Feature Distillation (EFD) module that employs contrastive learning to efficiently and accurately distill language embeddings derived from foundational models.
Image Demoireing in RAW and sRGB Domains
Moire patterns frequently appear when capturing screens with smartphones or cameras, potentially compromising image quality.
A Comparative Study of Image Restoration Networks for General Backbone Network Design
Following this, we present the benchmark results and analyze the reasons behind the performance disparity of different models across various tasks.
Unifying Image Processing as Visual Prompting Question Answering
To address this issue, we propose a universal model for general image processing that covers image restoration, image enhancement, image feature extraction tasks, etc.
HAT: Hybrid Attention Transformer for Image Restoration
In the training stage, we additionally adopt a same-task pre-training strategy to further exploit the potential of the model for further improvement.
Towards Efficient SDRTV-to-HDRTV by Learning from Image Formation
However, the majority of available resources are still in standard dynamic range (SDR).
CNN Injected Transformer for Image Exposure Correction
Capturing images with incorrect exposure settings fails to deliver a satisfactory visual experience.
SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution
In particular, we cluster the extensive degradation space to create a set of representative degradation cases, which serves as a comprehensive test set.
Direction-aware Video Demoireing with Temporal-guided Bilateral Learning
In TDR, we propose a temporal-guided bilateral learning pipeline to mitigate the degradation of color and details caused by the moire patterns while preserving the restored frequency information in FDDA.
MOFA: A Model Simplification Roadmap for Image Restoration on Mobile Devices
Extensive experiments demonstrate that our approach decreases runtime by up to 13% and reduces the number of parameters by up to 23%, while increasing PSNR and SSIM on several image restoration datasets.
Aphid Cluster Recognition and Detection in the Wild Using Deep Learning Models
To facilitate the use of machine learning models, we further process the images by cropping them into patches, resulting in a labeled dataset comprising 151, 380 image patches.
Under-Display Camera Image Restoration with Scattering Effect
With the physical model of the scattering effect, we improve the image formation pipeline for the image synthesis to construct a realistic UDC dataset with ground truths.
A New Dataset and Comparative Study for Aphid Cluster Detection
Aphids are one of the main threats to crops, rural families, and global food security.
DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models
After detecting the artifact regions, we develop a finetune procedure to improve GAN-based SR models with a few samples, so that they can deal with similar types of artifacts in more unseen real data.
Gender, Smoking History and Age Prediction from Laryngeal Images
In this study, we made the first endeavor to employ deep learning models to predict patient demographic information to improve detector model performance.
Learning Iterative Neural Optimizers for Image Steganography
Image steganography is the process of concealing secret information in images through imperceptible changes.
Explicitly Increasing Input Information Density for Vision Transformers on Small Datasets
To boost the performance of vision Transformers on small datasets, this paper proposes to explicitly increase the input information density in the frequency domain.
Accumulated Trivial Attention Matters in Vision Transformers on Small Datasets
After carefully examining the self-attention modules, we discover that the number of trivial attention weights is far greater than the important ones and the accumulated trivial weights are dominating the attention in Vision Transformers due to their large quantity, which is not handled by the attention itself.
Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learning
Gradient inversion attack enables recovery of training samples from model gradients in federated learning (FL), and constitutes a serious threat to data privacy.
Efficient Image Super-Resolution using Vast-Receptive-Field Attention
In this work, we design an efficient SR network by improving the attention mechanism.
UDC-UNet: Under-Display Camera Image Restoration via U-Shape Dynamic Network
Particularly, flare and blur in UDC images could severely deteriorate the user experience in high dynamic range (HDR) scenes.
CMOS-based area-and-power-efficient neuron and synapse circuits for time-domain analog spiking neural networks
The proposed neuron and synapse occupy the area of 127 {\mu}m^{ 2} and 231 {\mu}m^{ 2}, respectively, while achieving millisecond time constants.
Low-Light Video Enhancement with Synthetic Event Guidance
Low-light video enhancement (LLVE) is an important yet challenging task with many applications such as photographing and autonomous driving.
Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions
Advances in perception for self-driving cars have accelerated in recent years due to the availability of large-scale datasets, typically collected at specific locations and under nice weather conditions.
NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results
The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i. e. solutions can not exceed a given number of operations).
Blueprint Separable Residual Network for Efficient Image Super-Resolution
One is the usage of blueprint separable convolution (BSConv), which takes place of the redundant convolution operation.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Activating More Pixels in Image Super-Resolution Transformer
In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement.
Ranked #1 on
Image Super-Resolution
on Set5 - 2x upscaling
Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception
Self-driving cars must detect vehicles, pedestrians, and other traffic participants accurately to operate safely.
TAPE: Task-Agnostic Prior Embedding for Image Restoration
In this paper, we propose a novel approach that embeds a task-agnostic prior into a transformer.
Dilated Continuous Random Field for Semantic Segmentation
Mean field approximation methodology has laid the foundation of modern Continuous Random Field (CRF) based solutions for the refinement of semantic segmentation.
Realtime Global Attention Network for Semantic Segmentation
In this paper, we proposed an end-to-end realtime global attention neural network (RGANet) for the challenging task of semantic segmentation.
Fixed Neural Network Steganography: Train the images, not the network
Recent attempts at image steganography make use of advances in deep learning to train an encoder-decoder network pair to hide and retrieve secret messages in images.
A New Journey from SDRTV to HDRTV
However, most available resources are still in standard dynamic range (SDR).
Improving the List Decoding Version of the Cyclically Equivariant Neural Decoder
In the same paper, a list decoding procedure was also introduced for two widely used classes of cyclic codes -- BCH codes and punctured Reed-Muller (RM) codes.
HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization
In this work, we propose a novel learning-based approach using a spatially dynamic encoder-decoder network, HDRUNet, to learn an end-to-end mapping for single image HDR reconstruction with denoising and dequantization.
Cyclically Equivariant Neural Decoders for Cyclic Codes
Finally, we propose a list decoding procedure that can significantly reduce the decoding error probability for BCH codes and punctured RM codes.
Few-Shot Learning by Integrating Spatial and Frequency Representation
We employ Discrete Cosine Transformation (DCT) to generate the frequency representation, then, integrate the features from both the spatial domain and frequency domain for classification.
Very Lightweight Photo Retouching Network with Conditional Sequential Modulation
In practice, photo retouching can be accomplished by a series of image processing operations.
On Channel Reciprocity in Reconfigurable Intelligent Surface Assisted Wireless Network
Channel reciprocity greatly facilitates downlink precoding in time-division duplexing (TDD) multiple-input multiple-output (MIMO) communications without the need for channel state information (CSI) feedback.
Information Theory Information Theory
Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision
Low-precision training has become a popular approach to reduce compute requirements, memory footprint, and energy consumption in supervised learning.
Path Loss Modeling and Measurements for Reconfigurable Intelligent Surfaces in the Millimeter-Wave Frequency Band
The refined model gives more accurate estimates of the path loss of RISs comprised of unit cells with a deep sub-wavelength size.
Robotic grasp detection using a novel two-stage approach
Recently, deep learning has been successfully applied to robotic grasp detection.
Train in Germany, Test in The USA: Making 3D Object Detectors Generalize
In the domain of autonomous driving, deep learning has substantially improved the 3D object detection accuracy for LiDAR and stereo camera data alike.
Transferable Active Grasping and Real Embodied Dataset
Grasping in cluttered scenes is challenging for robot vision systems, as detection accuracy can be hindered by partial occlusion of objects.
Combating noisy labels by agreement: A joint training method with co-regularization
The state-of-the-art approaches "Decoupling" and "Co-teaching+" claim that the "disagreement" strategy is crucial for alleviating the problem of learning with noisy labels.
Ranked #10 on
Learning with noisy labels
on CIFAR-10N-Random3
Wireless Communications with Reconfigurable Intelligent Surface: Path Loss Modeling and Experimental Measurement
The measurement results match well with the modeling results, thus validating the proposed free-space path loss models for RIS, which may pave the way for further theoretical studies and practical applications in this field.
Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection
In this paper, we propose a novel Aligned Region CNN (AR-CNN) to handle the weakly aligned multispectral data in an end-to-end way.
TRL: Discriminative Hints for Scalable Reverse Curriculum Learning
However, tasks with sparse rewards remain challenging when the state space is large.
