Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks43 from public data
- Poly Kernel Inception Network for Remote Sensing Detection548
The Poly Kernel Inception Network (PKINet) is introduced, which employs multi-scale convolution kernels without dilation to extract object features of varying scales and capture local context in remote sensing images.
- Jo-SRC: A Contrastive Approach for Combating Noisy Labels206
A noise-robust approach named Jo-SRC (Joint Sample Selection and Model Regularization based on Consistency) that trains the network in a contrastive learning manner to advance the model generalization performance by introducing consistency regularization.
- 89
- 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.
- 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.
- 47
- 47
- 36
- Learning With Imbalanced Noisy Data by Preventing Bias in Sample Selection36
This work proposes Class-Balance-based sample Selection (CBS) to prevent the tail class samples from being neglected during training, and introduces the Average Confidence Margin (ACM) metric to measure the quality of corrected labels by leveraging the model's evolving training dynamics.
- VideoMAC: Video Masked Autoencoders Meet ConvNets33
This paper proposes a new approach termed as VideoMAC, which combines video masked autoencoders with resource-friendly Con-vNets, and demonstrates that VideoMAC, empowering classical / modern convolutional encoders to harness the benefits of MVM, outperforms ViT-based approaches on downstream tasks.
- Bridging the Web Data and Fine-Grained Visual Recognition via Alleviating Label Noise and Domain Mismatch24
This work mainly focuses on two critical issues including "label noise" and "domain mismatch" in the web images, and proposes an end-to-end deep denoising network (DDN) model to jointly solve these problems in the process of web images selection.
- 22
- Road segmentation with image-LiDAR data fusion in deep neural network19
A novel structure to fuse image and LiDAR point cloud in an end-to-end semantic segmentation network, in which the fusion is performed at decoder stage instead of at, more commonly, encoder stage to improve the road prediction compared with transpose convolution with skip layers.
- Dynamically Visual Disambiguation of Keyword-based Image Search18
An adaptive multi-model framework that resolves polysemy by visual disambiguation by adapting to the dynamic changes in the search results and employing the proposed saliency-guided deep multi-instance learning network to remove outliers and learn classification models for visual disAmbiguation.
- 17
- Exploiting textual queries for dynamically visual disambiguation16
A novel framework that resolves visual polysemy by dynamically matching candidate text queries with retrieved images by employing the proposed saliency-guided deep multi-instance learning (MIL) network to remove outliers and learn classification models for visual disambiguation.
- 15
- 15
- 14
- Enhancing Robustness in Learning with Noisy Labels: An Asymmetric Co-Training Approach14
An asymmetric training framework in which one model is robustly trained with a selected subset of clean samples while the other is conventionally trained using the entire training set is introduced, establishing asymmetric sample selection and mining.
- Relating CNN-Transformer Fusion Network for Change Detection7
RCTNet introduces an early fusion backbone to exploit both spatial and temporal features early on, a Cross-Stage Aggregation module for enhanced temporal representation, and an Efficient Self-deciphering Attention module utilizing transformers to capture global information and fine-grained details for accurate change detection.
- 5
- Exploiting Category Similarity-Based Distributed Labeling for Fine-Grained Visual Classification4
A simple yet effective approach named category similarity-based distributed labeling (CSDL) to tackle the problem of diversity within subcategories of fine-grained visual classification (FGVC).
- 3
- Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth Estimation2
Iris is a deterministic framework for Monocular Depth Estimation that integrates real-world priors into the diffusion model and achieves significant improvements in MDE performance with strong in-the-wild generalization.
- 2
- 2
- Attention Map Guided Transformer Pruning for Edge Device2
A novel attention map guided (AMG) transformer pruning method, which removes both redundant tokens and heads with the guidance of the attention map in a hardware-friendly way to reduce both the inference complexity and model size without sacrificing the comparable accuracy on person Re-ID.
- 2
- 1
- Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images1
This work proposes a dual-masking strategy that strengthens geometry induction in the encoder, develops a coarse-to-fine Gaussian splatting strategy that reduces appearance-semantics inconsistencies, and introduces a pose-conditioned recalibration mechanism that interrelates the outputs of multiple heads to ensure cross-task consistency.
- –
- –
- –
- Combating Noisy Labels through Fostering Self- and Neighbor-Consistency–
A noise-robust method named Jo-SNC, which proposes to employ the Jensen-Shannon divergence to measure the ``likelihood'' of a sample being clean or out-of-distribution, and proposes a triplet consistency regularization that promotes self-prediction consistency, neighbor-prediction consistency, and feature consistency.
- –
- –
- Towards lightweight noise-robust models via noise-aware pruning–
This work proposes a simple yet effective method, termed NAP (Noise-Aware Pruning), to prune noise-robust models, by identifying clean and noisy sample subsets from the noisy training data, utilizing both feature-based and prediction-based perspectives.
- –
- –
- –
- –
- –
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 2026-10-16. 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.