Search Results for author:
Found 69 papers, 41 papers with code
Single-temporal Supervised Remote Change Detection for Domain Generalization
In this paper, we propose a multimodal contrastive learning (ChangeCLIP) based on visual-language pre-training for change detection domain generalization.
Leveraging Fine-Grained Information and Noise Decoupling for Remote Sensing Change Detection
Next, a shape-aware and a brightness-aware module are designed to improve the capacity for representation learning.
DMAD: Dual Memory Bank for Real-World Anomaly Detection
To address the challenge of real-world anomaly detection, we propose a new framework named Dual Memory bank enhanced representation learning for Anomaly Detection (DMAD).
Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection
In the field of multi-class anomaly detection, reconstruction-based methods derived from single-class anomaly detection face the well-known challenge of ``learning shortcuts'', wherein the model fails to learn the patterns of normal samples as it should, opting instead for shortcuts such as identity mapping or artificial noise elimination.
PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Models
On top of that, PointSeg can incorporate with various segmentation models and even surpasses the supervised methods.
Dual-path Frequency Discriminators for Few-shot Anomaly Detection
We consider anomaly detection as a discriminative classification problem, wherefore the dual-path feature discrimination module is employed to detect and locate the image-level and feature-level anomalies in the feature space.
UniM-OV3D: Uni-Modality Open-Vocabulary 3D Scene Understanding with Fine-Grained Feature Representation
3D open-vocabulary scene understanding aims to recognize arbitrary novel categories beyond the base label space.
Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection
Industrial anomaly detection is generally addressed as an unsupervised task that aims at locating defects with only normal training samples.
Density Matters: Improved Core-set for Active Domain Adaptive Segmentation
Active domain adaptation has emerged as a solution to balance the expensive annotation cost and the performance of trained models in semantic segmentation.
Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection
Following this spirit, this paper explores plain ViT architecture for MUAD.
DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection
Reconstruction-based approaches have achieved remarkable outcomes in anomaly detection.
AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model
Existing anomaly inspection methods are limited in their performance due to insufficient anomaly data.
GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection
Large Multimodal Model (LMM) GPT-4V(ision) endows GPT-4 with visual grounding capabilities, making it possible to handle certain tasks through the Visual Question Answering (VQA) paradigm.
CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection
This paper considers zero-shot Anomaly Detection (AD), performing AD without reference images of the test objects.
Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption
To address these problems, we propose a novel phasic content fusing few-shot diffusion model with directional distribution consistency loss, which targets different learning objectives at distinct training stages of the diffusion model.
Stroke-based Neural Painting and Stylization with Dynamically Predicted Painting Region
To solve the problem, we propose Compositional Neural Painter, a novel stroke-based rendering framework which dynamically predicts the next painting region based on the current canvas, instead of dividing the image plane uniformly into painting regions.
Toward High Quality Facial Representation Learning
To improve the facial representation quality, we use feature map of a pre-trained visual backbone as a supervision item and use a partially pre-trained decoder for mask image modeling.
IIDM: Inter and Intra-domain Mixing for Semi-supervised Domain Adaptation in Semantic Segmentation
In this paper, we highlight the significance of exploiting the intra-domain information between the labeled target data and unlabeled target data.
PVG: Progressive Vision Graph for Vision Recognition
Convolution-based and Transformer-based vision backbone networks process images into the grid or sequence structures, respectively, which are inflexible for capturing irregular objects.
RFENet: Towards Reciprocal Feature Evolution for Glass Segmentation
Glass-like objects are widespread in daily life but remain intractable to be segmented for most existing methods.
Align, Perturb and Decouple: Toward Better Leverage of Difference Information for RSI Change Detection
In this paper, we revisit the importance of feature difference for change detection in RSI, and propose a series of operations to fully exploit the difference information: Alignment, Perturbation and Decoupling (APD).
Dual Path Transformer with Partition Attention
This paper introduces a novel attention mechanism, called dual attention, which is both efficient and effective.
Learning Global-aware Kernel for Image Harmonization
To address this issue, we propose a novel Global-aware Kernel Network (GKNet) to harmonize local regions with comprehensive consideration of long-distance background references.
Ranked #5 on
Image Harmonization
on iHarmony4
Transavs: End-To-End Audio-Visual Segmentation With Transformer
Generally AVS faces two key challenges: (1) Audio signals inherently exhibit a high degree of information density, as sounds produced by multiple objects are entangled within the same audio stream; (2) Objects of the same category tend to produce similar audio signals, making it difficult to distinguish between them and thus leading to unclear segmentation results.
Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution
Most of the existing blind image Super-Resolution (SR) methods assume that the blur kernels are space-invariant.
MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detection
Despite the remarkable progress made by modern detection models, this challenge is particularly evident in the semi-supervised case.
Calibrated Teacher for Sparsely Annotated Object Detection
Recent works on sparsely annotated object detection alleviate this problem by generating pseudo labels for the missing annotations.
Iterative Few-shot Semantic Segmentation from Image Label Text
Few-shot semantic segmentation aims to learn to segment unseen class objects with the guidance of only a few support images.
Ranked #40 on
Few-Shot Semantic Segmentation
on COCO-20i (1-shot)
Multimodal Industrial Anomaly Detection via Hybrid Fusion
2D-based Industrial Anomaly Detection has been widely discussed, however, multimodal industrial anomaly detection based on 3D point clouds and RGB images still has many untouched fields.
Ranked #3 on
RGB+3D Anomaly Detection and Segmentation
on MVTEC 3D-AD
(using extra training data)
Contrastive Learning
RGB+3D Anomaly Detection and Segmentation
Learning from Noisy Labels with Decoupled Meta Label Purifier
Training deep neural networks(DNN) with noisy labels is challenging since DNN can easily memorize inaccurate labels, leading to poor generalization ability.
Learning with Noisy labels via Self-supervised Adversarial Noisy Masking
Collecting large-scale datasets is crucial for training deep models, annotating the data, however, inevitably yields noisy labels, which poses challenges to deep learning algorithms.
Ranked #2 on
Image Classification
on Clothing1M
(using extra training data)
Self-Supervised Likelihood Estimation with Energy Guidance for Anomaly Segmentation in Urban Scenes
Based on the proposed estimators, we devise an adaptive self-supervised training framework, which exploits the contextual reliance and estimated likelihood to refine mask annotations in anomaly areas.
Exploring Efficient Few-shot Adaptation for Vision Transformers
Essentially, despite ViTs have been shown to enjoy comparable or even better performance on other vision tasks, it is still very nontrivial to efficiently finetune the ViTs in real-world FSL scenarios.
Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation
In this work, we explore a simple yet unified solution for FSIS as well as its incremental variants, and introduce a new framework named Reference Twice (RefT) to fully explore the relationship between support/query features based on a Transformer-like framework.
Rethinking Mobile Block for Efficient Attention-based Models
This paper focuses on developing modern, efficient, lightweight models for dense predictions while trading off parameters, FLOPs, and performance.
Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly Detection
Specifically, we first propose a normality recall memory (NR Memory) to strengthen the normality of student-generated features by recalling the stored normal information.
Ranked #11 on
Anomaly Detection
on MVTec AD
Split-PU: Hardness-aware Training Strategy for Positive-Unlabeled Learning
Since only part of the most confident positive samples are available and evidence is not enough to categorize the rest samples, many of these unlabeled data may also be the positive samples.
PatchMix Augmentation to Identify Causal Features in Few-shot Learning
We theoretically show that such an augmentation mechanism, different from existing ones, is able to identify the causal features.
Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling
Specifically, for the clean set, we deliberately design a memory-based modulation scheme to dynamically adjust the contribution of each sample in terms of its historical credibility sequence during training, thus alleviating the effect from noisy samples incorrectly grouped into the clean set.
Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation
Unsupervised Domain Adaptation (UDA) aims to adapt the model trained on the labeled source domain to an unlabeled target domain.
Ranked #14 on
Unsupervised Domain Adaptation
on SYNTHIA-to-Cityscapes
EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm
Motivated by biological evolution, this paper explains the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derives that both have consistent mathematical formulation.
FRIH: Fine-grained Region-aware Image Harmonization
Image harmonization aims to generate a more realistic appearance of foreground and background for a composite image.
Learning Distinctive Margin toward Active Domain Adaptation
Despite plenty of efforts focusing on improving the domain adaptation ability (DA) under unsupervised or few-shot semi-supervised settings, recently the solution of active learning started to attract more attention due to its suitability in transferring model in a more practical way with limited annotation resource on target data.
STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentation
In contrast, we present a simple and efficient single-stage VIS framework based on the instance segmentation method CondInst by adding an extra tracking head.
Ranked #36 on
Video Instance Segmentation
on YouTube-VIS validation
ASFD: Automatic and Scalable Face Detector
Along with current multi-scale based detectors, Feature Aggregation and Enhancement (FAE) modules have shown superior performance gains for cutting-edge object detection.
Ranked #1 on
Face Detection
on WIDER Face (Medium)
SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution
In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device.
ISDNet: Integrating Shallow and Deep Networks for Efficient Ultra-High Resolution Segmentation
The huge burden of computation and memory are two obstacles in ultra-high resolution image segmentation.
LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization
In this paper, we propose a novel framework built upon the transformer, termed LCTR (Local Continuity TRansformer), which targets at enhancing the local perception capability of global features among long-range feature dependencies.
LSTC: Boosting Atomic Action Detection with Long-Short-Term Context
We demonstrate that both temporal grains are beneficial to atomic action recognition.
Robust Learning with Adaptive Sample Credibility Modeling
For the clean set, we deliberately design a memory-based modulation scheme to dynamically adjust the contribution of each sample in terms of its historical credibility sequence during training, thus to alleviate the effect from potential hard noisy samples in clean set.
Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting
Therefore, we propose a novel count interval partition criterion called Uniform Error Partition (UEP), which always keeps the expected counting error contributions equal for all intervals to minimize the prediction risk.
Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework
In this paper, we propose a purely point-based framework for joint crowd counting and individual localization.
Ranked #2 on
Crowd Counting
on ShanghaiTech A
NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection
Non-Maximum Suppression (NMS) is essential for object detection and affects the evaluation results by incorporating False Positives (FP) and False Negatives (FN), especially in crowd occlusion scenes.
Ranked #6 on
Pedestrian Detection
on Caltech
Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model
Inspired by biological evolution, we explain the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derive that both of them have consistent mathematical representation.
SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking
In addition, we add a localization branch to predict the localization accuracy, so that it can work as the replacement of the regression assistance link during inference.
Learning Salient Boundary Feature for Anchor-free Temporal Action Localization
Temporal action localization is an important yet challenging task in video understanding.
Learning Comprehensive Motion Representation for Action Recognition
For action recognition learning, 2D CNN-based methods are efficient but may yield redundant features due to applying the same 2D convolution kernel to each frame.
Uniformity in Heterogeneity: Diving Deep Into Count Interval Partition for Crowd Counting
Therefore, we propose a novel count interval partition criterion called Uniform Error Partition (UEP), which always keeps the expected counting error contributions equal for all intervals to minimize the prediction risk.
Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework
In this paper, we propose a purely point-based framework for joint crowd counting and individual localization.
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task.
Ranked #2 on
Semantic Segmentation
on FoodSeg103
(using extra training data)
Dense Scene Multiple Object Tracking with Box-Plane Matching
Multiple Object Tracking (MOT) is an important task in computer vision.
Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking
Existing Multiple-Object Tracking (MOT) methods either follow the tracking-by-detection paradigm to conduct object detection, feature extraction and data association separately, or have two of the three subtasks integrated to form a partially end-to-end solution.
Temporal Distinct Representation Learning for Action Recognition
Motivated by the previous success of Two-Dimensional Convolutional Neural Network (2D CNN) on image recognition, researchers endeavor to leverage it to characterize videos.
ACFD: Asymmetric Cartoon Face Detector
Cartoon face detection is a more challenging task than human face detection due to many difficult scenarios is involved.
Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation
Unsupervised learning of optical flow, which leverages the supervision from view synthesis, has emerged as a promising alternative to supervised methods.
Ranked #2 on
Optical Flow Estimation
on KITTI 2012 unsupervised
ASFD: Automatic and Scalable Face Detector
In this paper, we propose a novel Automatic and Scalable Face Detector (ASFD), which is based on a combination of neural architecture search techniques as well as a new loss design.
TEINet: Towards an Efficient Architecture for Video Recognition
To relieve this problem, we propose an efficient temporal module, termed as Temporal Enhancement-and-Interaction (TEI Module), which could be plugged into the existing 2D CNNs (denoted by TEINet).
Fast Learning of Temporal Action Proposal via Dense Boundary Generator
In this paper, we propose an efficient and unified framework to generate temporal action proposals named Dense Boundary Generator (DBG), which draws inspiration from boundary-sensitive methods and implements boundary classification and action completeness regression for densely distributed proposals.
Ranked #7 on
Temporal Action Localization
on FineAction
DSFD: Dual Shot Face Detector
In this paper, we propose a novel face detection network with three novel contributions that address three key aspects of face detection, including better feature learning, progressive loss design and anchor assign based data augmentation, respectively.
Ranked #1 on
Face Detection
on FDDB
