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
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works65 from public data
- Random Erasing Data Augmentation4,342
In training, Random Erasing randomly selects a rectangle region in an image and erases its pixels with random values and yields consistent improvement over strong baselines in image classification, object detection and person re-identification.
- Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks1,096
The proposed Soft Filter Pruning (SFP) method enables the pruned filters to be updated when training the model after pruning, which has two advantages over previous works: larger model capacity and less dependence on the pretrained model.
- Contrastive Adaptation Network for Unsupervised Domain Adaptation1,013
This paper proposes Contrastive Adaptation Network optimizing a new metric which explicitly models the intra- class domain discrepancy and the inter-class domain discrepancy, and designs an alternating update strategy for training CAN in an end-to-end manner.
- Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification1,011
Through domain adaptation experiment, it is shown that images generated by SPGAN are more suitable for domain adaptation and yield consistent and competitive re-ID accuracy on two large-scale datasets.
- Multi-Interest Network with Dynamic Routing for Recommendation at Tmall554
This paper designs a multi-interest extractor layer based on the recently proposed dynamic routing mechanism, which is applicable for modeling and extracting diverse interests from user's behaviors, and proposes a technique named label-aware attention to help the learning process of user representations.
- 292
- Self-produced Guidance for Weakly-Supervised Object Localization269
Self-produced Guidance (SPG) masks which separate the foreground i.e., the object of interest, from the background to provide the classification networks with spatial correlation information of pixels are proposed.
- SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model225
This work presents an extensive analysis for continual learning on a pre-trained model (CLPM), and attributes the key challenge to a progressive overfitting problem, and proposes a simple but extremely effective approach named Slow Learner with Classifier Alignment (SLCA), which further improves the classification layer by modeling the class-wise distributions and aligning the classification layers in a post-hoc fashion.
- Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks191
An asymptotic soft filter pruning (ASFP) method to accelerate the inference procedure of the deep neural networks and shows the effectiveness of the ASFP on image classification benchmarks.
- Content-Consistent Matching for Domain Adaptive Semantic Segmentation168
This paper considers the adaptation of semantic segmentation from the synthetic source domain to the real target domain and proposes a content-consistent matching (CCM) model, which can alleviate the domain bias caused by those content-irrelevant synthetic images.
- 157
- Contrastive Adaptation Network for Single- and Multi-Source Domain Adaptation132
This paper proposes contrastive adaptation network (CAN) that optimizes a new metric named Contrastive Domain Discrepancy explicitly modeling the intra-classdomain discrepancy and the inter-class domain discrepancy and develops class-aware sampling to enable more efficient and effective training.
- Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: The Benefit of Target Expectation Maximization127
This paper proposes an attention alignment scheme on all the target convolutional layers to uncover the knowledge shared by the source domain, and estimates the posterior label distribution of the unlabeled data for target network training.
- AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning78
This paper proposes a non-incremental learner, named AttriCLIP, to incrementally extract knowledge of new classes or tasks, built upon the pre-trained visual-language model CLIP and compares it with CLIP-based and previous state-of-the-art continual learning methods in realistic settings with domain-shift and long-sequence learning.
- 76
- Attract or Distract: Exploit the Margin of Open Set67
This paper exploits the semantic structure of open set data from two aspects: 1)Semantic Categorical Alignment, which aims to achieve good separability of target known classes by categorically aligning the centroid of target with the source, and 2) Semantic Contrastive Mapping,Which aims to push the unknown class away from the decision boundary.
- Shakeout: A New Approach to Regularized Deep Neural Network Training63
It is demonstrated that Shakeout can effectively reduce the instability of the training process of the deep architecture and lead to sparser weights under both unsupervised and supervised settings.
- Shakeout: A New Regularized Deep Neural Network Training Scheme60
This paper presents a new training scheme: Shakeout, which leads to a combination of L1 regularization and L2 regularization imposed on the weights, which has been proved effective by the Elastic Net models in practice.
- 59
- 49
- 36
- 31
- PLGS: Robust Panoptic Lifting With 3D Gaussian Splatting27
This paper builds a panoptic-aware structured 3D Gaussian model to introduce smoothness and design effective noise reduction strategies, and presents a self-training approach using pseudo labels generated by merging the rendered masks with the noisy masks to enhance the robustness of PLGS.
- 26
- 25
- Progressive Deep Neural Networks Acceleration via Soft Filter Pruning25
The proposed Progressive Soft Filter Pruning method prunes the network progressively and enables the pruned filters to be updated when training the model after pruning, which has three advantages over previous works: larger model capacity, less dependence on the pre-trained model and better performance.
- Annotation Efficient Cross-Modal Retrieval with Adversarial Attentive Alignment21
A novel framework to leverage automatically extracted regional semantics from un-annotated images as additional weak supervision to learn visual-semantic embeddings through adversarial attentive alignments to close the inherent heterogeneous gaps between annotated and un- annotated portions of visual and textual domains is proposed.
- MMVG-INF-Etrol@TRECVID 2019: Activities in Extended Video.17
For detecting and localizing surveillance events in videos, Argus employs a spatial-temporal activity proposal generation module facilitating object detection and tracking, followed by a sequential classification module to spatially and temporally localize persons and objects involved in the activity.
- 13
- 13
- LatentWarp: Consistent Diffusion Latents for Zero-Shot Video-to-Video Translation13
This paper proposes a new zero-shot video-to-video translation framework, named \textit{LatentWarp], and finds the bottleneck lies in the unconstrained query tokens and proposes a warping operation in the latent space to constrain the query tokens.
- 13
- Training-free Monocular 3D Event Detection System for Traffic Surveillance13
This paper proposes a training-free monocular 3D event detection system for traffic surveillance that is robust to the occlusions and the viewpoint changes, and develops multiple simple yet effective ways to identify the events based on the kinematic patterns, which need no further training.
- SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training11
This work presents an in-depth analysis of the progressive overfitting problem from the lens of Seq FT, and introduces the advanced Slow Learner with Classifier Alignment (SLCA++) framework to unleash the power of Seq FT, serving as a strong baseline approach for CLPT.
- 9
- 9
- 7
- 6
- 5
- 5
- Normalizing Batch Normalization for Long-Tailed Recognition5
This paper identifies that the bias towards the frequent class may be encoded into features, i.e., the rare-specific features which play a key role in discriminating the rare class are much weaker than the frequent-specific features.
- 4
- 3
- Inf@TRECVID 2019: Instance Search Task.3
This work integrates person detection, person tracking and feature selection into a framework to get the 3D features for all tracklets in video shots in video shots.
- 2
- 2
- 2
- 2
- Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning2
This paper observes that introducing robustness-promoting regularization into MAML reduces the intrinsic dimension of clean sample features, which results in a lower capacity of clean representations, and proposes a simple strategy, i.e., increasing the number of training shots, to mitigate the loss of intrinsic dimension caused by robusts-promoted regularization.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
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.