Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks106 from public data
- Multi-Label Image Recognition With Graph Convolutional Networks1,262
This work proposes a multi-label classification model based on Graph Convolutional Network (GCN), and proposes a novel re-weighted scheme to create an effective label correlation matrix to guide information propagation among the nodes in GCN.
- BBN: Bilateral-Branch Network With Cumulative Learning for Long-Tailed Visual Recognition1,027
A unified Bilateral-Branch Network (BBN) is proposed to take care of both representation learning and classifier learning simultaneously, where each branch does perform its own duty separately.
- Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval464
The selective convolutional descriptor aggregation (SCDA) method is proposed, which is unsupervised, using no image label or bounding box annotation, and achieves comparable retrieval results with the state-of-the-art general image retrieval approaches.
- Mask-CNN: Localizing parts and selecting descriptors for fine-grained bird species categorization392
It is proved that selecting useful deep descriptors contributes well to fine-grained image recognition, and a novel Mask-CNN model without the fully connected layers is proposed, which has a small feature dimensionality and efficient inference speed by comparing with other fine- grained approaches.
- Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation357
This work proposes a novel structure-aware convolutional network to implicitly take priors about the structure of human bodies into account during training of the deep network and significantly outperforms the state-of-the-art methods and almost always generates plausible human pose predictions.
- Exploring Categorical Regularization for Domain Adaptive Object Detection354
This work proposes a simple but effective categorical regularization framework for alleviating domain shift mitigation in the domain adaptive object detection problem, and obtains a significant performance gain over original Domain Adaptive Faster R-CNN detectors.
- Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification305
This work proposes a novel hybrid network structure being composed of a supervised contrastive loss to learn image representations and a cross-entropy loss to learning classifiers, where the learning is progressively transited from feature learning to the classifier learning to embody the idea that better features make better classifiers.
- Delving deep into spatial pooling for squeeze-and-excitation networks279
A simple but effective two-stage spatial pooling process: rich descriptor extraction and information fusion is introduced, which aims to obtain a set of diverse deep descriptors that contain more informative cues than global average-pooling.
- 192
- Bag of Tricks for Long-Tailed Visual Recognition with Deep Convolutional Neural Networks168
This paper collects existing tricks in long-tailed visual recognition and performs extensive and systematic experiments in order to give a detailed experimental guideline and obtain an effective combination of these tricks, and proposes a novel data augmentation approach based on class activation maps for long-tail recognition.
- Piecewise Classifier Mappings: Learning Fine-Grained Learners for Novel Categories With Few Examples159
An end-to-end trainable deep network inspired by the state-of-the-art fine-grained recognition model and is tailored for the FSFG task is proposed, which generates the decision boundary via learning a set of more attainable sub-classifiers in a more parameter-economic way.
- 139
- Distilling Virtual Examples for Long-tailed Recognition136
It is proved that distilling from these virtual examples is equivalent to label distribution learning under certain constraints, and it is shown that when the virtual example distribution becomes flatter than the original input distribution, the under-represented tail classes will receive significant improvements, which is crucial in long-tailed recognition.
- 126
- Unsupervised object discovery and co-localization by deep descriptor transformation110
Deep Descriptor Transformation (DDT) is proposed, a simple yet effective method for evaluating the correlations of descriptors and then obtaining the category-consistent regions, which can accurately locate the common object in a set of unlabeled images, i.e., object co-localization.
- 101
- Deep Bimodal Regression for Apparent Personality Analysis101
The Deep Bimodal Regression framework is proposed and a solution for the Apparent Personality Analysis competition track in the ChaLearn Looking at People challenge in association with ECCV 2016 is come up with.
- 98
- 95
- 95
- Learning Semantically Enhanced Feature for Fine-Grained Image Classification91
The approach learns fine-grained features by enhancing the semantics of sub-features of a global feature by arranging feature channels of a CNN into different groups through channel permutation.
- Structure-aware human pose estimation with graph convolutional networks91
This paper proposes a novel model, termed Pose Graph Convolutional Network (PGCN), to exploit the structural relationships between body key points to exploit these important relationships for pose estimation, and shows that this method consistently outperforms competing state-of-the-art methods.
- 85
- Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach76
Comprehensive experimental results and analyses on two new benchmark datasets demonstrate that the proposed method achieves superior performance over the competing baseline models and states-of-the-art.
- 75
- 72
- 70
- 58
- ExchNet: A Unified Hashing Network for Large-Scale Fine-Grained Image Retrieval56
This paper proposes a unified end-to-end trainable network, termed as ExchNet, which consistently outperforms state-of-the-art generic hashing methods on five fine-grained datasets and achieves the best speed-up and storage reduction, revealing its efficiency and practicality.
- CRSSC: Salvage Reusable Samples from Noisy Data for Robust Learning55
This work proposes a certainty-based reusable sample selection and correction approach, termed as CRSSC, for coping with label noise in training deep FG models with web images, which is to additionally identify and correct reusable samples, and then leverage them together with clean examples to update the networks.
- Dual Attention Networks for Few-Shot Fine-Grained Recognition49
To generate fine-grained tailored representations for few-shot recognition, a Dual Attention Network (Dual Att-Net) consisting of two dual branches of both hard- and soft-attentions is proposed, which outperforms other existing state-of-the-art methods.
- Attribute-Aware Deep Hashing With Self-Consistency for Large-Scale Fine-Grained Image Retrieval47
Qualitative results demonstrate that not only the obtained hash codes can strongly correspond to certain kinds of crucial properties of fine-grained objects, but also the self-consistency designs can effectively overcome simplicity bias in fine- grained hashing.
- Coarse-to-Fine: A RNN-Based Hierarchical Attention Model for Vehicle Re-identification47
This work proposes an end-to-end RNN-based Hierarchical Attention (RNN-HA) classification model for vehicle re-identification and demonstrates that the proposed model achieves superior performance over state-of-the-art methods.
- Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization44
This work proposes a novel structure-aware fully convolutional network to implicitly take such priors about the structure of pose components into account during training of the deep network, demonstrating the usefulness of implicit learning of structures using GANs.
- 42
- 41
- 41
- Deep Descriptor Transforming for Image Co-Localization39
This paper proposes a simple but effective method, named Deep Descriptor Transforming (DDT), for evaluating the correlations of descriptors and then obtaining the category-consistent regions, which can accurately locate the common object in a set of images.
- 39
- RPC: a large-scale and fine-grained retail product checkout dataset36
This essay proposes a new dataset, i.e., RPC, which is closer to the realistic setting and can derive a variety of research problems and benchmark the performance on this dataset with a cross-domain detection baseline method.
- An empirical study on image bag generators for multi-instance learning36
Two significant new observations are made: (1) Bag generators with a dense sampling strategy perform better than those with other strategies; and (2) the standard MIL assumption of learning algorithms is not suitable for image classification tasks.
- Relieving Long-tailed Instance Segmentation via Pairwise Class Balance32
This paper proposes a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences, and generates fightback soft labels for regularization during training.
- 31
- 30
- 30
- 25
- Prototype-based classifier learning for long-tailed visual recognition24
This paper tackles the long-tailed visual recognition problem from the categorical prototype perspective by proposing a prototype-based classifier learning (PCL) method, and proves that the proposed PCL can outperform state-of-the-arts.
- 24
- 24
- 23
- PyRetri: A PyTorch-based Library for Unsupervised Image Retrieval by Deep Convolutional Neural Networks20
PyRetri is an open source library for deep learning based unsupervised image retrieval that encapsulates the retrieval process in several stages and provides functionality that covers various prominent methods for each stage.
- 18
- CAT: a coarse-to-fine attention tree for semantic change detection17
This paper tackles the SCD and LCM tasks simultaneously by proposing a coarse-to-fine attention tree (CAT) model, which outperforms state-of-the-art models and equip a label distribution learning loss upon the model to address label ambiguity in SCD/LCM.
- 15
- 13
- 12
- Equiangular Basis Vectors12
Different from previous methods, the EBVs generate normalized vector embeddings as “predefined classifiers” which are required to not only be with the equal status between each other, but also be as orthogonal as possible.
- 12
- Contextualizing Meta-Learning via Learning to Decompose11
LeadNet is proposed to contextualize the meta-learned “support-to-target” strategy, leveraging the context of instances with one or mixed latent attributes in a support set, and demonstrates the superiority of LeadNet in various applications, including exploring multiple views of confusing data, out-of-distribution recognition, and few-shot image classification.
- Leveraging DNA-Based Nanostructures for Advanced Error Detection and Correction in Data Communication11
This study demonstrates the implementation of the Hamming code using DNA-based nanostructures for error detection and correction in communication systems and highlights the potential of DNA as a versatile platform for reliable data transmission.
- Piecewise Hashing: A Deep Hashing Method for Large-Scale Fine-Grained Search11
This paper introduces a novel multi-task hash training strategy, which can learn hash codes of different lengths simultaneously and not only accelerates training procedures, but also significantly improves the fine-grained search accuracy.
- 8
- Watch out Venomous Snake Species: A Solution to SnakeCLEF20238
This paper presents a method leveraging utilization of both images and metadata that achieves 91.31% score of the final metric combined of F1 and other metrics on private leaderboard, which is the 1st place among the participators.
- 8
- 8
- Object-Level Correlation for Few-Shot Segmentation7
An Object-level Correlation Network (OCNet) is designed by establishing the object-level correlation between the support target object and query general objects, which is mainly composed of the General Object Mining Module (GOMM) and Correlation Construction Module (CCM).
- Automatic Check-Out via Prototype-Based Classifier Learning from Single-Product Exemplars7
This work proposes a method, termed as PSP, to perform Prototype-based classifier learning from Single-Product exemplars, which achieves 86.69%, by 6.18% improvements over state-of-the-arts, which demonstrates the superiority of PSP.
- 7
- 7
- An Empirical Study on Training Paradigms for Deep Supervised Hashing6
Key findings include observations such as: pointwise hashing methods tend to exhibit higher retrieval accuracy in scenarios with seen-class queries but underperform significantly with unseen-class queries, whereas pairwise hashing methods with soft constraints excel when queries are from unseen classes.
- Delving Deep into Simplicity Bias for Long-Tailed Image Recognition6
This work empirically reports that self-supervised learning can mitigate SB and perform in complementary to the supervised counterpart by enriching the features extracted from tail samples and consequently taking better advantage of such rare samples.
- Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization6
The idea that CV adopts discrete and terminological task definitions (\eg, ``image segmentation''), which may be a key barrier to zero-shot task generalization is explored, and Explanatory Instructions are introduced, which provide an intuitive way to define CV task objectives through detailed linguistic transformations from input images to outputs.
- Webly-Supervised Fine-Grained Recognition with Partial Label Learning6
This paper utilizes a pre-trained deep model to perform deep descriptor transformation to estimate the positive correlation between these web images, and detects the open-set noises based on the correlation values, and develops a top-k recall optimization loss for firstly assigning a label set towards each web image to reduce the impact of hard label assignment for closed- set noises.
- 6
- Resource-constrained deep learning: challenges and practices6
This study first analyzes deep learnings thirst for various types of resources and the challenges they lead to and thereafter briefly introduces research progress from three aspects: data, label, and computation resources.
- 5
- Beyond Overfitting: Doubly Adaptive Dropout for Generalizable AU Detection5
This work proposes a doubly adaptive dropout approach for cross-domain AU detection, which enhances the robustness of convolutional feature maps and spatial tokens against domain shifts, and consistently outperforms existing techniques in cross-domain AU detection.
- Equiangular Basis Vectors: A Novel Paradigm for Classification Tasks5
By directly adding EBVs corresponding to newly added categories of equal status on the basis of existing EBVs, the Equiangular Basis Vectors method exhibits strong scalability to deal with the large increase of training categories in open-environment machine learning.
- 5
- [Establishment of a deep learning-based visual model for intelligent recognition of Oncomelania hupensis].5
This is the first visual model for intelligent recognition of O. hupensis based on deep learning, which shows a high accuracy for snail image recognition and is helpful to improve the accuracy of the model for snail recognition.
- 4
- 4
- Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization3
A novel method that harnesses learnable queries for attribute-aware hash codes learning and deploys a tailored set of queries to capture and represent nuanced attribute-level information within the hashing process, thereby enhancing both the interpretability and relevance of each hash bit.
- Data tells the truth: A Knowledge distillation method for genomic survival analysis by handling censoring2
The proposed method, KD (Knowledge Distillation), effectively addresses the supervision bias inherent in censored data for survival prediction by distilling knowledge from uncensored data, which enhances the accuracy of survival predictions and reveals hidden information from censored data.
- Task-specific Part Discovery for Fine-grained Few-shot Classification2
This paper designs an optimal transport solution that also utilizes query data in a transductive way to optimize the aforementioned distance calculation for the final predictions, and generates part-level categorical prototypes that are later employed by calculating distances to classify query data for evaluation.
- 2
- Efficient and Effective In-context Demonstration Selection with Coreset1
This paper proposes a novel demonstration selection framework named Coreset-based Dual Retrieval (CoDR), and introduces a cluster-pruning method to construct a diverse coreset that aligns more effectively with the query while maintaining diversity.
- 1
- 1
- –
- Beyond Static Uncertainty: Modeling Temporal Uncertainty Dynamics for Probabilistic Time Series Forecasting–
The Location-Scale Gaussian VAE (LSG-VAE), a simple but effective framework that explicitly parameterizes both the predictive mean and time-dependent variance through a location-scale likelihood formulation, enables LSG-VAE to faithfully capture het-eroscedastic aleatoric uncertainty and introduces an adaptive attenuation mechanism that automatically down-weights highly volatile observations during training, leading to improved robustness in trend prediction.
- Programmable DNA Strand-Displacement Circuits for Emulating Digital Sequential Logic Devices–
A programmable DNA circuit platform capable of emulating digital sequential logic elements, including a Set-Reset (SR) latch, a clocked Data (D) flip-flop, and a two-bit binary counter is presented.
- Masked Autoencoders that Feel the Heart: Unveiling Simplicity Bias for ECG Analyses–
A novel method comprising two key components: 1) Temporal-Frequency aware Filters to capture temporal-frequency features reflecting the dynamic characteristics of ECG signals, and 2) Multi-Grained Prototype Reconstruction for coarse and fine representation learning across dual domains, further mitigating SB.
- Hawkeye: A PyTorch-based Library for Fine-Grained Image Recognition with Deep Learning–
Hawkeye is designed with a modular architecture, emphasizing high-quality code and human-readable configuration, providing a comprehensive solution for FGIR tasks, and represents the first open-source PyTorch-based library dedicated to FGIR.
- –
- –
- –
- –
- –
- Preface–
This special section is launched and aims to seek high quality research work on self-learning with deep neural networks, including a comprehensive review of selfsupervised learning, improving the generalization performance of few-shot intent detection, and conducting musicdriven motion generation.
- –
- MULL'21–
This workshop aims to provide a platform for discussing the challenges and corresponding innovative approaches in multimedia with less labeling, and to invite several domain-specific experts for sharing their insights and research progress on the topic of MULL.
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.