159 citations · 392 across the 32 of their papers we have counts for
33 papers
Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model
Jiamin Xie, Ke Li, Jinxi Guo +7
Neural network pruning offers an effective method for compressing a multilingual automatic speech recognition (ASR) model with minimal performance loss. However, it entails several…
Forensic Histopathological Recognition via a Context-Aware MIL Network Powered by Self-Supervised Contrastive Learning
Chen Shen, Jun Zhang, Xinggong Liang +5
Forensic pathology is critical in analyzing death manner and time from the microscopic aspect to assist in the establishment of reliable factual bases for criminal investigation. I…
Prompting Large Language Models with Speech Recognition Abilities
Yassir Fathullah, Chunyang Wu, Egor Lakomkin +9
Large language models have proven themselves highly flexible, able to solve a wide range of generative tasks, such as abstractive summarization and open-ended question answering. I…
Integrating Multiple Sources Knowledge for Class Asymmetry Domain Adaptation Segmentation of Remote Sensing Images
Kuiliang Gao, Anzhu Yu, Xiong You +3
In the existing unsupervised domain adaptation (UDA) methods for remote sensing images (RSIs) semantic segmentation, class symmetry is an widely followed ideal assumption, where th…
Multi-modal Queried Object Detection in the Wild
Yifan Xu, Mengdan Zhang, Chaoyou Fu +4
We introduce MQ-Det, an efficient architecture and pre-training strategy design to utilize both textual description with open-set generalization and visual exemplars with rich desc…
DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion
Kiyohiro Nakayama, Mikaela Angelina Uy, Jiahui Huang +3
While the community of 3D point cloud generation has witnessed a big growth in recent years, there still lacks an effective way to enable intuitive user control in the generation p…
SketchXAI: A First Look at Explainability for Human Sketches
Zhiyu Qu, Yulia Gryaditskaya, Ke Li +3
This paper, for the very first time, introduces human sketches to the landscape of XAI (Explainable Artificial Intelligence). We argue that sketch as a ``human-centred'' data form,…
Reinforcement Learning Friendly Vision-Language Model for Minecraft
Haobin Jiang, Junpeng Yue, Hao Luo +2
One of the essential missions in the AI research community is to build an autonomous embodied agent that can achieve high-level performance across a wide spectrum of tasks. However…
Improving Fast-slow Encoder based Transducer with Streaming Deliberation
Ke Li, Jay Mahadeokar, Jinxi Guo +5
This paper introduces a fast-slow encoder based transducer with streaming deliberation for end-to-end automatic speech recognition. We aim to improve the recognition accuracy of th…
CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation
Yuqi Lin, Minghao Chen, Wenxiao Wang +5
Weakly supervised semantic segmentation (WSSS) with image-level labels is a challenging task. Mainstream approaches follow a multi-stage framework and suffer from high training cos…
Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning
Xialei Liu, Jiang-Tian Zhai, Andrew D. Bagdanov +2
Exemplar-free Class Incremental Learning (EFCIL) aims to sequentially learn tasks with access only to data from the current one. EFCIL is of interest because it mitigates concerns…
Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition
Suyoun Kim, Ke Li, Lucas Kabela +4
Recently, there has been an increasing interest in two-pass streaming end-to-end speech recognition (ASR) that incorporates a 2nd-pass rescoring model on top of the conventional 1s…
Long-Tailed Class Incremental Learning
Xialei Liu, Yu-Song Hu, Xu-Sheng Cao +3
In class incremental learning (CIL) a model must learn new classes in a sequential manner without forgetting old ones. However, conventional CIL methods consider a balanced distrib…
Evolutionary Multi-Task Injection Testing on Web Application Firewalls
Ke Li, Heng Yang, Willem Visser
Web application firewall (WAF) plays an integral role nowadays to protect web applications from various malicious injection attacks such as SQL injection, XML injection, and PHP in…
Streaming parallel transducer beam search with fast-slow cascaded encoders
Jay Mahadeokar, Yangyang Shi, Ke Li +5
Streaming ASR with strict latency constraints is required in many speech recognition applications. In order to achieve the required latency, streaming ASR models sacrifice accuracy…
Art-Attack: Black-Box Adversarial Attack via Evolutionary Art
Phoenix Williams, Ke Li
Deep neural networks (DNNs) have achieved state-of-the-art performance in many tasks but have shown extreme vulnerabilities to attacks generated by adversarial examples. Many works…
Variational Model Inversion Attacks
Kuan-Chieh Wang, Yan Fu, Ke Li +3
Given the ubiquity of deep neural networks, it is important that these models do not reveal information about sensitive data that they have been trained on. In model inversion atta…
End-To-End Optimization of LiDAR Beam Configuration for 3D Object Detection and Localization
Niclas Vödisch, Ozan Unal, Ke Li +2
Existing learning methods for LiDAR-based applications use 3D points scanned under a pre-determined beam configuration, e.g., the elevation angles of beams are often evenly distrib…
Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting
Binghui Chen, Zhaoyi Yan, Ke Li +4
In crowd counting, due to the problem of laborious labelling, it is perceived intractability of collecting a new large-scale dataset which has plentiful images with large diversity…
Combinatorial Bandits under Strategic Manipulations
Jing Dong, Ke Li, Shuai Li +1
Strategic behavior against sequential learning methods, such as "click framing" in real recommendation systems, have been widely observed. Motivated by such behavior we study the p…
Hyperspectral Image Super-Resolution with Spectral Mixup and Heterogeneous Datasets
Ke Li, Dengxin Dai, Ender Konukoglu +1
This work studies Hyperspectral image (HSI) super-resolution (SR). HSI SR is characterized by high-dimensional data and a limited amount of training examples. This exacerbates the…
Generating Unobserved Alternatives
Shichong Peng, Ke Li
We consider problems where multiple predictions can be considered correct, but only one of them is given as supervision. This setting differs from both the regression and class-con…
DeRF: Decomposed Radiance Fields
Daniel Rebain, Wei Jiang, Soroosh Yazdani +3
With the advent of Neural Radiance Fields (NeRF), neural networks can now render novel views of a 3D scene with quality that fools the human eye. Yet, generating these images is ve…
Knee Point Identification Based on Trade-Off Utility
Ke Li, Haifeng Nie, Huifu Gao +1
Knee points, characterised as their smallest trade-off loss at all objectives, are attractive to decision makers in multi-criterion decision-making. In contrast, other Pareto-optim…