Search Results for author:
Found 46 papers, 9 papers with code
Learning with Noisy Class Labels for Instance Segmentation
Specifically, in instance segmentation, noisy class labels play different roles in the foreground-background sub-task and the foreground-instance sub-task.
HiHa: Introducing Hierarchical Harmonic Decomposition to Implicit Neural Compression for Atmospheric Data
To address this issue, we propose Hierarchical Harmonic decomposition implicit neural compression (HiHa) for atmospheric data.
ARIC: An Activity Recognition Dataset in Classroom Surveillance Images
The ARIC dataset has advantages of multiple perspectives, 32 activity categories, three modalities, and real-world classroom scenarios.
Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation
However, most recent third-view methods leverage the frozen Contrastive Language-Image Pre-training (CLIP) model, which is pre-trained on the semantic-oriented third-view data and lapses in the egocentric view due to the ``relation insensitive" problem.
Region Prompt Tuning: Fine-grained Scene Text Detection Utilizing Region Text Prompt
In this paper, we propose the region prompt tuning (RPT) method for fine-grained scene text detection, where region text prompt proposed would help focus on fine-grained features.
Few-Shot Continual Learning for Activity Recognition in Classroom Surveillance Images
In real classroom settings, normal teaching activities such as reading, account for a large proportion of samples, while rare non-teaching activities such as eating, continue to appear.
DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document Understanding
Text-rich document understanding (TDU) refers to analyzing and comprehending documents containing substantial textual content.
Distribution-Level Memory Recall for Continual Learning: Preserving Knowledge and Avoiding Confusion
To address this issue, we propose the Distribution-Level Memory Recall (DMR) method, which uses a Gaussian mixture model to precisely fit the feature distribution of old knowledge at the distribution level and generate pseudo features in the next stage.
No Re-Train, More Gain: Upgrading Backbones with Diffusion Model for Few-Shot Segmentation
For the second issue, due to the varying granularity of transformed priors from diverse annotation types, we conceptualize these multi-granular transformed priors as analogous to noisy intermediates at different steps of a diffusion model.
A Survey on Large Language Models with Multilingualism: Recent Advances and New Frontiers
To this end, we provide a survey with multiple perspectives on the utilization of LLMs in the multilingual scenario.
On the Adversarial Robustness of Learning-based Image Compression Against Rate-Distortion Attacks
Using the performance variations as indicators, we evaluate the adversarial robustness of eight predominant LIC algorithms against diverse attacks.
Bridging the Gap Between End-to-End and Two-Step Text Spotting
Subsequently, we introduce a Bridge that connects the locked detector and recognizer through a zero-initialized neural network.
Slightly Shift New Classes to Remember Old Classes for Video Class-Incremental Learning
So we propose SNRO, which slightly shifts the features of new classes to remember old classes.
MCF-VC: Mitigate Catastrophic Forgetting in Class-Incremental Learning for Multimodal Video Captioning
Further, in order to better constrain the knowledge characteristics of old and new tasks at the specific feature level, we have created the Two-stage Knowledge Distillation (TsKD), which is able to learn the new task well while weighing the old task.
SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting
In this paper, we propose a new end-to-end scene text spotting framework termed SwinTextSpotter v2, which seeks to find a better synergy between text detection and recognition.
Class Incremental Learning with Multi-Teacher Distillation
In this paper we propose the MTD method to find multiple diverse teachers for CIL.
Prompt-Driven Referring Image Segmentation with Instance Contrasting
Referring image segmentation (RIS) aims to segment the target referent described by natural language.
Dual-Consistency Model Inversion for Non-Exemplar Class Incremental Learning
In this paper we present a novel method termed Dual-Consistency Model Inversion (DCMI) to generate better synthetic samples of old classes through two pivotal consistency alignments: (1) the semantic consistency between the synthetic images and the corresponding prototypes and (2) domain consistency between synthetic and real images of new classes.
GRSDet: Learning to Generate Local Reverse Samples for Few-shot Object Detection
By transferring the knowledge of IFC from the base training to fine-tuning, the IFC generates plentiful novel samples to calibrate the novel class distribution.
Learning with Noisy Low-Cost MOS for Image Quality Assessment via Dual-Bias Calibration
Learning based image quality assessment (IQA) models have obtained impressive performance with the help of reliable subjective quality labels, where mean opinion score (MOS) is the most popular choice.
Cross-modal Cognitive Consensus guided Audio-Visual Segmentation
Then, we feed the unified-modal label back to the visual backbone as the explicit semantic-level guidance via a Cognitive Consensus guided Attention Module (CCAM), which highlights the local features corresponding to the interested object.
A System-Level Energy-Efficient Digital Twin Framework for Runtime Control of Batch Manufacturing Processes
To improve the scheduling and control of batch manufacturing processes, we propose a system-level energy-efficient Digital Twin framework that considers Time-of-Use (TOU) energy pricing for runtime decision-making.
Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning
However, the deficiency of related dataset hinders the development of multi-modal deep learning for egocentric activity recognition.
CafeBoost: Causal Feature Boost To Eliminate Task-Induced Bias for Class Incremental Learning
We place continual learning into a causal framework, based on which we find the task-induced bias is reduced naturally by two underlying mechanisms in task and domain incremental learning.
Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class
Most existing methods are based on convolutional networks and prevent forgetting through knowledge distillation, which (1) need to add additional convolutional layers to predict new classes, and (2) ignore to distinguish different regions corresponding to old and new classes during knowledge distillation and roughly distill all the features, thus limiting the learning of new classes.
Contrastive Continuity on Augmentation Stability Rehearsal for Continual Self-Supervised Learning
In order to address catastrophic forgetting without overfitting on the rehearsal samples, we propose Augmentation Stability Rehearsal (ASR) in this paper, which selects the most representative and discriminative samples by estimating the augmentation stability for rehearsal.
Forgetting to Remember: A Scalable Incremental Learning Framework for Cross-Task Blind Image Quality Assessment
More specifically, we develop a dynamic parameter isolation strategy to sequentially update the task-specific parameter subsets, which are non-overlapped with each other.
Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation
Specifically, we introduce a knowability-based labeling scheme which can be divided into two steps: 1) Knowability-guided detection of known and unknown samples based on the intrinsic structure of the neighborhoods of samples, where we leverage the first singular vectors of the affinity matrices to obtain the knowability of every target sample.
RefCrowd: Grounding the Target in Crowd with Referring Expressions
Unfortunately, there is no effort to explore crowd understanding in multi-modal domain that bridges natural language and computer vision.
Divide and Explore: Multi-Agent Separate Exploration with Shared Intrinsic Motivations
One of the greatest challenges of reinforcement learning is efficient exploration, especially when training signals are sparse or deceptive.
Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning
In this paper, we propose a Non-Homogeneous Haze Removal Network (NHRN) via artificial scene prior and bidimensional graph reasoning.
BA^2M: A Batch Aware Attention Module for Image Classification
Then, we feed the SARs of the whole batch to a normalization function to get the weights for each sample.
Advanced Geometry Surface Coding for Dynamic Point Cloud Compression
In video-based dynamic point cloud compression (V-PCC), 3D point clouds are projected onto 2D images for compressing with the existing video codecs.
CrossDet: Crossline Representation for Object Detection
In this paper, we propose a novel anchor-free object detection network, called CrossDet, which uses a set of growing cross lines along horizontal and vertical axes as object representations.
Deep Learning in Ultrasound Elastography Imaging
It is known that changes in the mechanical properties of tissues are associated with the onset and progression of certain diseases.
3D B-mode ultrasound speckle reduction using deep learning for 3D registration applications
Moreover, it is found that the speckle reduction using our deep learning model contributes to improving the 3D registration performance.
VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results
Results of 33 object detection algorithms are presented.
A New Local Transformation Module for Few-shot Segmentation
The result by the matrix transformation can be regarded as an attention map with high-level semantic cues, based on which a transformation module can be built simply. The proposed transformation module is a general module that can be used to replace the transformation module in the existing few-shot segmentation frameworks.
Ranked #82 on
Few-Shot Semantic Segmentation
on PASCAL-5i (5-Shot)
Subjective and Objective De-raining Quality Assessment Towards Authentic Rain Image
Then, a subjective study is conducted on our DQA database, which collects the subject-rated scores of all de-rained images.
Class Activation Map generation by Multiple Level Class Grouping and Orthogonal Constraint
Moreover, a new orthogonal module and a two-branch based CAM generation method are proposed to generate class regions that are orthogonal and complementary.
A New Few-shot Segmentation Network Based on Class Representation
This paper studies few-shot segmentation, which is a task of predicting foreground mask of unseen classes by a few of annotations only, aided by a set of rich annotations already existed.
Class Activation Map Generation by Representative Class Selection and Multi-Layer Feature Fusion
Existing method generates class activation map (CAM) by a set of fixed classes (i. e., using all the classes), while the discriminative cues between class pairs are not considered.
Hierarchy Neighborhood Discriminative Hashing for An Unified View of Single-Label and Multi-Label Image retrieval
Finally, we propose a hierarchy neighborhood discriminative hashing loss to unify the single-label and multilabel image retrieval problem with a one-stream deep neural network architecture.
Key-Word-Aware Network for Referring Expression Image Segmentation
On the other hand, the relationships of different image regions are not considered as well, even though they are greatly important to eliminate the undesired foreground object in accordance with specific query.
A Perceptually Weighted Rank Correlation Indicator for Objective Image Quality Assessment
By modifying the perception threshold, we can illustrate the sorting accuracy with a more sophisticated SA-ST curve, rather than a single rank correlation coefficient.
Group MAD Competition - A New Methodology to Compare Objective Image Quality Models
We first build a database that contains 4, 744 source natural images, together with 94, 880 distorted images created from them.
