Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Qi TianSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works197 from public data
- Towards Optimal Structured CNN Pruning via Generative Adversarial Learning585
This paper proposes an effective structured pruning approach that jointly prunes filters as well as other structures in an end-to-end manner and effectively solves the optimization problem by generative adversarial learning (GAL), which learns a sparse soft mask in a label-free and an end to end manner.
- A novel features ranking metric with application to scalable visual and bioinformatics data classification396
A Max-Relevance-Max-Distance (MRMD) feature ranking method, which balances accuracy and stability of feature ranking and prediction task, and runs faster than other filtering and wrapping methods, such as mRMR and Information Gain.
- Multi-Task Collaborative Network for Joint Referring Expression Comprehension and Segmentation385
A novel Multi-task Collaborative Network (MCN) is proposed to achieve a joint learning of REC and RES for the first time and addresses a key challenge in this multi-task setup, i.e., the prediction conflict.
- Dual-level Collaborative Transformer for Image Captioning366
A novel Dual-Level Collaborative Transformer (DLCT) network is introduced to realize the complementary advantages ofriptive region features extracted by object detection networks and address the semantic noises caused by the direct fusion of these two features.
- SeqTR: A Simple Yet Universal Network for Visual Grounding247
Experiments on five benchmark datasets demonstrate that the proposed SeqTR outperforms (or is on par with) the existing state-of-the-arts, proving that a simple yet universal approach for visual grounding is indeed feasible.
- Image-to-image Translation via Hierarchical Style Disentanglement165
Hierarchical Style Disentanglement is proposed, which organizes the labels into a hierarchical tree structure, in which independent tags, exclusive attributes, and disentangled styles are allocated from top to bottom.
- SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distance147
A novel unsupervised FIQA method that incorporates Similarity Distribution Distance for Face Image Quality Assessment (SDD-FIQA), which generates quality pseudo-labels by calculating the Wasserstein Distance between the intra-class and inter-class similarity distributions and is capable of training a regression network for quality prediction.
- 130
- 114
- Filter Sketch for Network Pruning106
FilterSketch encodes the second-order information of pretrained weights, which enables the representation capacity of pruned networks to be recovered with a simple fine-tuning procedure, leading to a several-orders-of-magnitude reduction of time cost in the optimization of pruning.
- Active Teacher for Semi-Supervised Object Detection98
The experimental results not only validate the superior performance gain of Active Teacher over the compared methods, but also show that it enables the baseline network, i.e., Faster-RCNN, to achieve 100% supervised performance with much less label expenditure,i.e. 40% labeled examples on MS-COCO.
- You Only Segment Once: Towards Real-Time Panoptic Segmentation86
YOSO is the first real-time panoptic segmentation framework that delivers competitive performance compared to state-of-the-art models and re-parameterizes interpolation-first modules in a convolution-first way, which significantly speeds up the pipeline without any additional costs.
- Pruning Networks With Cross-Layer Ranking & k-Reciprocal Nearest Filters79
A novel pruning method, termed CLR-RNF, is proposed that reveals a “long-tail” pruning problem in magnitude-based weight pruning methods and proposes a computation-aware measurement for individual weight importance, followed by a cross-layer ranking (CLR) of weights to identify and remove the bottom-ranked weights.
- 74
- Occluded Person Re-identification via Saliency-Guided Patch Transfer69
Extensive experimental evaluations conducted on occluded and holistic person re-identification benchmarks demonstrate that SPT provides a significant performance gain among different ViT-based ReID algorithms on occluded ReID.
- Weakly supervised vehicle detection in satellite images via multi-instance discriminative learning66
An intelligent and labor-light scheme for large-scale training of vehicle detectors that only requires region-level group annotation and has achieved superior performance by comparing to a set of state-of-the-art and alternative approaches.
- Towards Lightweight Transformer Via Group-Wise Transformation for Vision-and-Language Tasks65
WL-Transformer applies Group-wise Transformation to reduce both the parameters and computations of Transformer, while also preserving its two main properties, i.e., the efficient attention modeling on diverse subspaces of MHA, and the expanding-scaling feature transformation of FFN.
- LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization65
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 and a relational patch-attention module (RPAM), which considers cross-patch information on a global basis.
- 65
- Vehicle detection from highway satellite images via transfer learning57
This paper adopts a novel transfer learning technology that transfers vehicle detectors trained in the aerial image domain to the satellite image domain, based on a supervised super-resolution algorithm, which learns mutually correlative sparse coefficients between high and low resolution image patches.
- 52
- 47
- 46
- 45
- DistilPose: Tokenized Pose Regression with Heatmap Distillation44
A novel human pose estimation framework termed DistilPose, which bridges the gaps between heatmap-based and regression-based methods and maximizes the transfer of knowledge from the teacher model to the student model through Token-distilling Encoder (TDE) and Simulated Heatmaps.
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 2026-10-13. 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.