Search Results for author:
Found 47 papers, 33 papers with code
ReMamber: Referring Image Segmentation with Mamba Twister
Referring Image Segmentation (RIS) leveraging transformers has achieved great success on the interpretation of complex visual-language tasks.
Modeling the Label Distributions for Weakly-Supervised Semantic Segmentation
Based on the label distributions, we leverage the GMM to generate high-quality pseudo labels for more reliable supervision.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture
To this end, we present FD4MM, a new paradigm of Frequency Decoupling for Motion Magnification with a Multi-level Isomorphic Architecture to capture multi-level high-frequency details and a stable low-frequency structure (motion field) in video space.
Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery
In this paper, we study the problem of Generalized Category Discovery (GCD), which aims to cluster unlabeled data from both known and unknown categories using the knowledge of labeled data from known categories.
Active Generalized Category Discovery
Generalized Category Discovery (GCD) is a pragmatic and challenging open-world task, which endeavors to cluster unlabeled samples from both novel and old classes, leveraging some labeled data of old classes.
Democratizing Fine-grained Visual Recognition with Large Language Models
Identifying subordinate-level categories from images is a longstanding task in computer vision and is referred to as fine-grained visual recognition (FGVR).
Memory Consistency Guided Divide-and-Conquer Learning for Generalized Category Discovery
Generalized category discovery (GCD) aims at addressing a more realistic and challenging setting of semi-supervised learning, where only part of the category labels are assigned to certain training samples.
Cross-Modality Perturbation Synergy Attack for Person Re-identification
For instance, infrared images are typically grayscale, unlike visible images that contain color information.
Semantic Connectivity-Driven Pseudo-labeling for Cross-domain Segmentation
This approach formulates pseudo-labels at the connectivity level and thus can facilitate learning structured and low-noise semantics.
Federated Generalized Category Discovery
On each client, GCL builds class-level contrastive learning with both local and global GMMs.
Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Feature
Recent research has shown that Deep Neural Networks (DNNs) are highly vulnerable to adversarial samples, which are highly transferable and can be used to attack other unknown black-box models.
Dynamic Conceptional Contrastive Learning for Generalized Category Discovery
This leads traditional novel category discovery (NCD) methods to be incapacitated for GCD, due to their assumption of unlabeled data are only from novel categories.
Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery
Discovering novel concepts from unlabelled data and in a continuous manner is an important desideratum of lifelong learners.
Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration
In this work, we provide a comprehensive investigation of the CE loss function and find that the logit margin between the targeted and untargeted classes will quickly obtain saturation in CE, which largely limits the transferability.
Dynamically Instance-Guided Adaptation: A Backward-Free Approach for Test-Time Domain Adaptive Semantic Segmentation
In this paper, we study the application of Test-time domain adaptation in semantic segmentation (TTDA-Seg) where both efficiency and effectiveness are crucial.
Sparsely Annotated Semantic Segmentation With Adaptive Gaussian Mixtures
Our AGMM can effectively endow reliable supervision for unlabeled pixels based on the distributions of labeled and unlabeled pixels.
Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization
Furthermore, we present a novel style hallucination module (SHM) to generate style-diversified samples that are essential to consistency learning.
Class-incremental Novel Class Discovery
We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a pre-trained model that has been trained on a labelled data set containing disjoint yet related categories.
Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation
Experiments on two synthetic-to-real semantic segmentation benchmarks demonstrate that AdvStyle can significantly improve the model performance on unseen real domains and show that we can achieve the state of the art.
Joint Representation Learning and Keypoint Detection for Cross-view Geo-localization
Inspired by the human visual system for mining local patterns, we propose a new framework called RK-Net to jointly learn the discriminative Representation and detect salient Keypoints with a single Network.
Ranked #2 on
Drone navigation
on University-1652
Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation
Furthermore, we present a novel style hallucination module (SHM) to generate style-diversified samples that are essential to consistency learning.
Ranked #4 on
Robust Object Detection
on DWD
Federated and Generalized Person Re-identification through Domain and Feature Hallucinating
During local training, the DFS are used to synthesize novel domain statistics with the proposed domain hallucinating, which is achieved by re-weighting DFS with random weights.
Cross-Modality Earth Mover's Distance for Visible Thermal Person Re-Identification
In this manner, the model will focus on reducing the inter-modality discrepancy while paying less attention to intra-identity variations, leading to a more effective modality alignment.
Novel Class Discovery in Semantic Segmentation
We introduce a new setting of Novel Class Discovery in Semantic Segmentation (NCDSS), which aims at segmenting unlabeled images containing new classes given prior knowledge from a labeled set of disjoint classes.
3D-Aware Semantic-Guided Generative Model for Human Synthesis
However, they usually struggle to generate high-quality images representing non-rigid objects, such as the human body, which is of a great interest for many computer graphics applications.
Bi-Mix: Bidirectional Mixing for Domain Adaptive Nighttime Semantic Segmentation
Specifically, in the image translation stage, Bi-Mix leverages the knowledge of day-night image pairs to improve the quality of nighttime image relighting.
High-Order-Interaction for weakly supervised Fine-Grained Visual Categorization
Of those, methods based on bilinear pooling are one of the main categories for computing the interaction between deep features and have shown high effectiveness.
Ranked #1 on
Fine-Grained Image Recognition
on CUB Birds
Fine-Grained Image Classification
Fine-Grained Image Recognition
+2
A Unified Objective for Novel Class Discovery
In this paper, we study the problem of Novel Class Discovery (NCD).
Ranked #3 on
Novel Object Detection
on LVIS v1.0 val
Neighborhood Contrastive Learning for Novel Class Discovery
In this paper, we address Novel Class Discovery (NCD), the task of unveiling new classes in a set of unlabeled samples given a labeled dataset with known classes.
Source-Free Open Compound Domain Adaptation in Semantic Segmentation
Second, CPSS can reduce the influence of noisy pseudo-labels and also avoid the model overfitting to the target domain during self-supervised learning, consistently boosting the performance on the target and open domains.
Transformer-Based Source-Free Domain Adaptation
In this paper, we study the task of source-free domain adaptation (SFDA), where the source data are not available during target adaptation.
Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation
In this paper we address multi-target domain adaptation (MTDA), where given one labeled source dataset and multiple unlabeled target datasets that differ in data distributions, the task is to learn a robust predictor for all the target domains.
Ranked #2 on
Multi-target Domain Adaptation
on Office-Home
Blended-target Domain Adaptation
Multi-target Domain Adaptation
Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification
This paper considers the problem of unsupervised person re-identification (re-ID), which aims to learn discriminative models with unlabeled data.
Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification
In this paper, we study the problem of multi-source domain generalization in ReID, which aims to learn a model that can perform well on unseen domains with only several labeled source domains.
OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World
In this paper, we tackle the problem of discovering new classes in unlabeled visual data given labeled data from disjoint classes.
Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification
This procedure encourages that the selected training samples can be both clean and miscellaneous, and that the two models can promote each other iteratively.
Ranked #9 on
Unsupervised Domain Adaptation
on Market to Duke
Learning to Adapt Invariance in Memory for Person Re-identification
This work considers the problem of unsupervised domain adaptation in person re-identification (re-ID), which aims to transfer knowledge from the source domain to the target domain.
Ranked #7 on
Unsupervised Domain Adaptation
on Market to MSMT
Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification
To achieve this goal, an exemplar memory is introduced to store features of the target domain and accommodate the three invariance properties.
Domain Adaptive Person Re-Identification
Person Re-Identification
+1
Leveraging Virtual and Real Person for Unsupervised Person Re-identification
For training of deep re-ID model, we divide it into three steps: 1) pre-training a coarse re-ID model by using virtual data; 2) collaborative filtering based positive pair mining from the real data; and 3) fine-tuning of the coarse re-ID model by leveraging the mined positive pairs and virtual data.
Generalizing A Person Retrieval Model Hetero- and Homogeneously
Person re-identification (re-ID) poses unique challenges for unsupervised domain adaptation (UDA) in that classes in the source and target sets (domains) are entirely different and that image variations are largely caused by cameras.
Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification
This paper considers the task of thorax disease classification on chest X-ray images.
Camera Style Adaptation for Person Re-identification
In this paper, we explicitly consider this challenge by introducing camera style (CamStyle) adaptation.
Ranked #71 on
Person Re-Identification
on DukeMTMC-reID
Random Erasing Data Augmentation
In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN).
Ranked #4 on
Image Classification
on Fashion-MNIST
Re-ranking Person Re-identification with k-reciprocal Encoding
Specifically, given an image, a k-reciprocal feature is calculated by encoding its k-reciprocal nearest neighbors into a single vector, which is used for re-ranking under the Jaccard distance.
Ranked #11 on
Person Re-Identification
on CUHK03
Re-ranking Object Proposals for Object Detection in Automatic Driving
In this paper, we propose a semantic, class-specific approach to re-rank object proposals, which can consistently improve the recall performance even with less proposals.
Detecting Ground Control Points via Convolutional Neural Network for Stereo Matching
Secondly, we present a ground control points selection scheme according to the maximum matching confidence of each pixel.
Unsupervised domain adaption dictionary learning for visual recognition
However, when the data instances of a target domain have a different distribution than that of a source domain, the dictionary learning method may fail to perform well.
