Search Results for author:
Found 51 papers, 31 papers with code
Polynomial Regression Network for Variable-Number Lane Detection
Most of previous methods utilize semantic segmentation to identify the regions of traffic lanes in an image, and then adopt some curve-fitting method to reconstruct the lanes.
Towards Compatible Fine-tuning for Vision-Language Model Updates
So far, efficient fine-tuning has become a popular strategy for enhancing the capabilities of foundation models on downstream tasks by learning plug-and-play modules.
Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
Current multimodal large language models (MLLMs) struggle with fine-grained or precise understanding of visuals though they give comprehensive perception and reasoning in a spectrum of vision applications.
Multilevel semantic and adaptive actionness learning for weakly supervised temporal action localization
The AAL branch uses pseudo labels to learn class-agnostic action information.
DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization
This paper addresses the challenge of out-of-distribution (OOD) generalization in graph machine learning, a field rapidly advancing yet grappling with the discrepancy between source and target data distributions.
LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
And this low-rank gradient can be expressed in terms of the gradients of the two low-rank matrices in LoRA.
Weakly supervised temporal action localization with actionness-guided false positive suppression
Our method seeks to suppress false positive backgrounds without introducing the background category.
Weakly Supervised Action Localization
Weakly-supervised Temporal Action Localization
+1
Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models
This paper proposes a \textbf{C}ollabo\textbf{ra}tive \textbf{F}ine-\textbf{T}uning (\textbf{CraFT}) approach for fine-tuning black-box VLMs to downstream tasks, where one only has access to the input prompts and the output predictions of the model.
A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
Extensive results on 17 datasets validate that our method surpasses or achieves comparable results with state-of-the-art methods on few-shot classification, imbalanced learning, and out-of-distribution generalization.
Exploring Vacant Classes in Label-Skewed Federated Learning
As minority classes suffer from worse accuracy due to overfitting on local imbalanced data, prior methods often incorporate class-balanced learning techniques during local training.
Infer from What You Have Seen Before: Temporally-dependent Classifier for Semi-supervised Video Segmentation
Motivated by this observation we propose a novel temporally-dependent classifier (TDC) to mimic the human-like recognition procedure.
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach
It comprises two core components: a snippet clustering component that groups the snippets into multiple latent clusters and a cluster classification component that further classifies the cluster as foreground or background.
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification
The crux of learning vision-language models is to extract semantically aligned information from visual and linguistic data.
Exploiting Low-confidence Pseudo-labels for Source-free Object Detection
The LPU module consists of Proposal Soft Training (PST) and Local Spatial Contrastive Learning (LSCL).
Improving Zero-Shot Generalization for CLIP with Synthesized Prompts
Thereafter, we fine-tune CLIP with off-the-shelf methods by combining labeled and synthesized features.
Actionness Inconsistency-guided Contrastive Learning for Weakly-supervised Temporal Action Localization
In principle, the two branches are supposed to produce the same actionness activation.
Improve Temporal Action Proposals using Hierarchical Context
In this paper, we propose a novel hierarchical context network (HCN) to further explore the snippet-level and proposal-level contexts, which are used to improve the representations of snippets and proposals, respectively.
Ranked #1 on
Temporal Action Proposal Generation
on THUMOS' 14
SimpleNet: A Simple Network for Image Anomaly Detection and Localization
SimpleNet consists of four components: (1) a pre-trained Feature Extractor that generates local features, (2) a shallow Feature Adapter that transfers local features towards target domain, (3) a simple Anomaly Feature Generator that counterfeits anomaly features by adding Gaussian noise to normal features, and (4) a binary Anomaly Discriminator that distinguishes anomaly features from normal features.
Ranked #3 on
Anomaly Classification
on GoodsAD
Semantic Prompt for Few-Shot Image Recognition
Instead of the naive exploitation of semantic information for remedying classifiers, we explore leveraging semantic information as prompts to tune the visual feature extraction network adaptively.
AdaptGuard: Defending Against Universal Attacks for Model Adaptation
To address this issue, we propose a model preprocessing framework, named AdaptGuard, to improve the security of model adaptation algorithms.
Video Semantic Segmentation with Inter-Frame Feature Fusion and Inner-Frame Feature Refinement
In this paper, to tackle the misalignment issue, we propose a spatial-temporal fusion (STF) module to model dense pairwise relationships among multi-frame features.
Preparing the Future for Continual Semantic Segmentation
In this study, we focus on Continual Semantic Segmentation (CSS) and present a novel approach to tackle the issue of existing methods struggling to learn new classes.
Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation
The existing weakly supervised semantic segmentation (WSSS) methods pay much attention to generating accurate and complete class activation maps (CAMs) as pseudo-labels, while ignoring the importance of training the segmentation networks.
MSRA-SR: Image Super-resolution Transformer with Multi-scale Shared Representation Acquisition
In particular, self-attention with cross-scale matching and convolution filters with different kernel sizes are designed to exploit the multi-scale features in images.
Towards Effective Instance Discrimination Contrastive Loss for Unsupervised Domain Adaptation
We further propose a target-dominated cross-domain mixup that can incorporate accurate semantic information from the source domain.
Class Relationship Embedded Learning for Source-Free Unsupervised Domain Adaptation
To this end, we first regard the classifier weights of the source model as class prototypes to compute class relationship, and then propose a novel probability-based similarity between target-domain samples by embedding the source-domain class relationship, resulting in Class Relationship embedded Similarity (CRS).
Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation
Such a strategy can generate the object boundaries in target domain (edge of target-domain object areas) with the correct labels.
Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition
Furthermore, to leverage the complementarity of domain-shared features and target-specific features, we propose a novel collaborative clustering strategy to enforce pair-wise relationship consistency between the two branches.
Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations
Different from previous cross-domain FSL work (CD-FSL) that considers the domain shift between base and novel classes, the new problem, termed cross-domain cross-set FSL (CDSC-FSL), requires few-shot learners not only to adapt to the new domain, but also to be consistent between different domains within each novel class.
Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring
Attributes skew hinders the current federated learning (FL) frameworks from consistent optimization directions among the clients, which inevitably leads to performance reduction and unstable convergence.
Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization
C$^3$BN consists of two key ingredients: a micro data augmentation strategy that increases the diversity in-between adjacent snippets by convex combination of adjacent snippets, and a macro-micro consistency regularization that enforces the model to be invariant to the transformations~\textit{w. r. t.}
Low-confidence Samples Matter for Domain Adaptation
Representing the target data structure in such a way would overlook the huge low-confidence samples, resulting in sub-optimal transferability that is biased towards the samples similar to the source domain.
Semi-Supervised Video Semantic Segmentation With Inter-Frame Feature Reconstruction
For this task, we observe that the overfitting is surprisingly severe between labeled and unlabeled frames within a training video although they are very similar in style and contents.
5th Place Solution for VSPW 2021 Challenge
In this article, we introduce the solution we used in the VSPW 2021 Challenge.
Probabilistic Contrastive Learning for Domain Adaptation
However, it is undesirably observed that the standard contrastive paradigm (features+$\ell_{2}$ normalization) only brings little help for domain adaptation.
RPN Prototype Alignment for Domain Adaptive Object Detector
It essentially cooperates the learning of RPN prototypes and features to align the source and target RPN features.
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images
Few-shot learning is a challenging task since only few instances are given for recognizing an unseen class.
Video Semantic Segmentation with Distortion-Aware Feature Correction
Video semantic segmentation is active in recent years benefited from the great progress of image semantic segmentation.
Ranked #14 on
Semantic Segmentation
on UrbanLF
Progressive Boundary Refinement Network for Temporal Action Detection
Temporal action detection is a challenging task due to vagueness of action boundaries.
Context-Aware Dynamic Feature Extraction for 3D Object Detection in Point Clouds
Varying density of point clouds increases the difficulty of 3D detection.
Adaptive and Azimuth-Aware Fusion Network of Multimodal Local Features for 3D Object Detection
We adopt different modalities of LiDAR data to generate richer features and present an adaptive and azimuth-aware network to aggregate local features from image, bird's eye view maps and point cloud.
Meta-SR: A Magnification-Arbitrary Network for Super-Resolution
In this work, we propose a novel method called Meta-SR to firstly solve super-resolution of arbitrary scale factor (including non-integer scale factors) with a single model.
Towards Human-Level License Plate Recognition
License plate recognition (LPR) is a fundamental component of various intelligent transport systems, which is always expected to be accurate and efficient enough.
End-to-end View Synthesis for Light Field Imaging with Pseudo 4DCNN
Limited angular resolution has become the main bottleneck of microlens-based plenoptic cameras towards practical vision applications.
Lifelong Learning via Progressive Distillation and Retrospection
Lifelong learning aims at adapting a learned model to new tasks while retaining the knowledge gained earlier.
VegFru: A Domain-Specific Dataset for Fine-Grained Visual Categorization
While the existing datasets for FGVC are mainly focused on animal breeds or man-made objects with limited labelled data, VegFru is a larger dataset consisting of vegetables and fruits which are closely associated with the daily life of everyone.
DualNet: Learn Complementary Features for Image Recognition
Here two parallel neural networks are coordinated to learn complementary features and thus a wider network is constructed.
Highway Vehicle Counting in Compressed Domain
HCR hierarchically divides the traffic scenes into different cases according to vehicle density, such that the broad-variation characteristics of traffic scenes can be better approximated.
Deeply Exploit Depth Information for Object Detection
This paper addresses the issue on how to more effectively coordinate the depth with RGB aiming at boosting the performance of RGB-D object detection.
Look and Think Twice: Capturing Top-Down Visual Attention With Feedback Convolutional Neural Networks
While feedforward deep convolutional neural networks (CNNs) have been a great success in computer vision, it is important to remember that the human visual contex contains generally more feedback connections than foward connections.
