173 citations · 416 across the 23 of their papers we have counts for
24 papers
Reusable Architecture Growth for Continual Stereo Matching
Chenghao Zhang, Gaofeng Meng, Bin Fan +4
The remarkable performance of recent stereo depth estimation models benefits from the successful use of convolutional neural networks to regress dense disparity. Akin to most tasks…
Enhancing Visual Continual Learning with Language-Guided Supervision
Bolin Ni, Hongbo Zhao, Chenghao Zhang +4
Continual learning (CL) aims to empower models to learn new tasks without forgetting previously acquired knowledge. Most prior works concentrate on the techniques of architectures,…
Defying Imbalanced Forgetting in Class Incremental Learning
Shixiong Xu, Gaofeng Meng, Xing Nie +3
We observe a high level of imbalance in the accuracy of different classes in the same old task for the first time. This intriguing phenomenon, discovered in replay-based Class Incr…
Continual Forgetting for Pre-trained Vision Models
Hongbo Zhao, Bolin Ni, Haochen Wang +6
For privacy and security concerns, the need to erase unwanted information from pre-trained vision models is becoming evident nowadays. In real-world scenarios, erasure requests ori…
ContentCTR: Frame-level Live Streaming Click-Through Rate Prediction with Multimodal Transformer
Jiaxin Deng, Dong Shen, Shiyao Wang +4
In recent years, live streaming platforms have gained immense popularity as they allow users to broadcast their videos and interact in real-time with hosts and peers. Due to the dy…
Free Lunch for Generating Effective Outlier Supervision
Sen Pei, Jiaxi Sun, Richard Yi Da Xu +3
When deployed in practical applications, computer vision systems will encounter numerous unexpected images (\emph{i.e.}, out-of-distribution data). Due to the potentially raised sa…
A Unified Model for Video Understanding and Knowledge Embedding with Heterogeneous Knowledge Graph Dataset
Jiaxin Deng, Dong Shen, Haojie Pan +7
Video understanding is an important task in short video business platforms and it has a wide application in video recommendation and classification. Most of the existing video unde…
Expanding Language-Image Pretrained Models for General Video Recognition
Bolin Ni, Houwen Peng, Minghao Chen +5
Contrastive language-image pretraining has shown great success in learning visual-textual joint representation from web-scale data, demonstrating remarkable "zero-shot" generalizat…
Domain Decorrelation with Potential Energy Ranking
Sen Pei, Jiaxi Sun, Richard Yi Da Xu +2
Machine learning systems, especially the methods based on deep learning, enjoy great success in modern computer vision tasks under experimental settings. Generally, these classic d…
Gradient Concealment: Free Lunch for Defending Adversarial Attacks
Sen Pei, Jiaxi Sun, Xiaopeng Zhang +1
Recent studies show that the deep neural networks (DNNs) have achieved great success in various tasks. However, even the \emph{state-of-the-art} deep learning based classifiers are…
Out-of-distribution Detection with Boundary Aware Learning
Sen Pei, Xin Zhang, Bin Fan +1
There is an increasing need to determine whether inputs are out-of-distribution (\emph{OOD}) for safely deploying machine learning models in the open world scenario. Typical neural…
Differentiable Convolution Search for Point Cloud Processing
Xing Nie, Yongcheng Liu, Shaohong Chen +6
Exploiting convolutional neural networks for point cloud processing is quite challenging, due to the inherent irregular distribution and discrete shape representation of point clou…
Enhanced Boundary Learning for Glass-like Object Segmentation
Hao He, Xiangtai Li, Guangliang Cheng +5
Glass-like objects such as windows, bottles, and mirrors exist widely in the real world. Sensing these objects has many applications, including robot navigation and grasping. Howev…
Density-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement
Chi Zhang, Zihang Lin, Liheng Xu +6
The key procedure of haze image translation through adversarial training lies in the disentanglement between the feature only involved in haze synthesis, i.e.style feature, and the…
Dynamic Scale Training for Object Detection
Yukang Chen, Peizhen Zhang, Zeming Li +5
We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection. Previous strategies like image pyramid, multi-scale tra…
FontGAN: A Unified Generative Framework for Chinese Character Stylization and De-stylization
Xiyan Liu, Gaofeng Meng, Shiming Xiang +1
Chinese character synthesis involves two related aspects, i.e., style maintenance and content consistency. Although some methods have achieved remarkable success in synthesizing a…
DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing
Yongcheng Liu, Bin Fan, Gaofeng Meng +3
Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable. A thorough grasp of the elusive shape requires sufficientl…
Joint haze image synthesis and dehazing with mmd-vae losses
Zongliang Li, Chi Zhang, Gaofeng Meng +1
Fog and haze are weathers with low visibility which are adversarial to the driving safety of intelligent vehicles equipped with optical sensors like cameras and LiDARs. Therefore i…
Differentiable Architecture Search with Ensemble Gumbel-Softmax
Jianlong Chang, Xinbang Zhang, Yiwen Guo +3
For network architecture search (NAS), it is crucial but challenging to simultaneously guarantee both effectiveness and efficiency. Towards achieving this goal, we develop a differ…
Deep Discriminative Clustering Analysis
Jianlong Chang, Yiwen Guo, Lingfeng Wang +3
Traditional clustering methods often perform clustering with low-level indiscriminative representations and ignore relationships between patterns, resulting in slight achievements…
DetNAS: Backbone Search for Object Detection
Yukang Chen, Tong Yang, Xiangyu Zhang +3
Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image classification…
EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search
Jiemin Fang, Yukang Chen, Xinbang Zhang +5
Neural architecture search (NAS) methods have been proposed to release human experts from tedious architecture engineering. However, most current methods are constrained in small-s…
Joint Neural Architecture Search and Quantization
Yukang Chen, Gaofeng Meng, Qian Zhang +4
Designing neural architectures is a fundamental step in deep learning applications. As a partner technique, model compression on neural networks has been widely investigated to gea…
Effective Spectral Unmixing via Robust Representation and Learning-based Sparsity
Feiyun Zhu, Ying Wang, Bin Fan +2
Hyperspectral unmixing (HU) plays a fundamental role in a wide range of hyperspectral applications. It is still challenging due to the common presence of outlier channels and the l…