60 citations · 178 across the 19 of their papers we have counts for
19 papers
Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise
Kumar Shubham, Pavan Karjol, Kiran M K +1
The performance of machine learning models often relies on large labeled datasets; however, data collected from diverse sources can contain label noise. Recent work has shown that,…
TDViT: Temporal Dilated Video Transformer for Dense Video Tasks
Guanxiong Sun, Yang Hua, Guosheng Hu +1
Deep video models, for example, 3D CNNs or video transformers, have achieved promising performance on sparse video tasks, i.e., predicting one result per video. However, challenges…
Efficient One-stage Video Object Detection by Exploiting Temporal Consistency
Guanxiong Sun, Yang Hua, Guosheng Hu +1
Recently, one-stage detectors have achieved competitive accuracy and faster speed compared with traditional two-stage detectors on image data. However, in the field of video object…
MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection
Guanxiong Sun, Yang Hua, Guosheng Hu +1
State-of-the-art video object detection methods maintain a memory structure, either a sliding window or a memory queue, to enhance the current frame using attention mechanisms. How…
ProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy State
Xinshao Wang, Yang Hua, Elyor Kodirov +3
There is a family of label modification approaches including self and non-self label correction (LC), and output regularisation. They are widely used for training robust deep neura…
Not All Knowledge Is Created Equal: Mutual Distillation of Confident Knowledge
Ziyun Li, Xinshao Wang, Di Hu +4
Mutual knowledge distillation (MKD) improves a model by distilling knowledge from another model. However, \textit{not all knowledge is certain and correct}, especially under advers…
Imbalance Robust Softmax for Deep Embeeding Learning
Hao Zhu, Yang Yuan, Guosheng Hu +2
Deep embedding learning is expected to learn a metric space in which features have smaller maximal intra-class distance than minimal inter-class distance. In recent years, one rese…
Off-Policy Self-Critical Training for Transformer in Visual Paragraph Generation
Shiyang Yan, Yang Hua, Neil M. Robertson
Recently, several approaches have been proposed to solve language generation problems. Transformer is currently state-of-the-art seq-to-seq model in language generation. Reinforcem…
ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks
Xinshao Wang, Yang Hua, Elyor Kodirov +2
To train robust deep neural networks (DNNs), we systematically study several target modification approaches, which include output regularisation, self and non-self label correction…
ParaCNN: Visual Paragraph Generation via Adversarial Twin Contextual CNNs
Shiyang Yan, Yang Hua, Neil Robertson
Image description generation plays an important role in many real-world applications, such as image retrieval, automatic navigation, and disabled people support. A well-developed t…
Instance Cross Entropy for Deep Metric Learning
Xinshao Wang, Elyor Kodirov, Yang Hua +1
Loss functions play a crucial role in deep metric learning thus a variety of them have been proposed. Some supervise the learning process by pairwise or tripletwise similarity cons…
ID-aware Quality for Set-based Person Re-identification
Xinshao Wang, Elyor Kodirov, Yang Hua +1
Set-based person re-identification (SReID) is a matching problem that aims to verify whether two sets are of the same identity (ID). Existing SReID models typically generate a feat…
Derivative Manipulation for General Example Weighting
Xinshao Wang, Elyor Kodirov, Yang Hua +1
Real-world large-scale datasets usually contain noisy labels and are imbalanced. Therefore, we propose derivative manipulation (DM), a novel and general example weighting approach…
GAN-based Pose-aware Regulation for Video-based Person Re-identification
Alessandro Borgia, Yang Hua, Elyor Kodirov +1
Video-based person re-identification deals with the inherent difficulty of matching unregulated sequences with different length and with incomplete target pose/viewpoint structure.…
Semantic Alignment: Finding Semantically Consistent Ground-truth for Facial Landmark Detection
Zhiwei Liu, Xiangyu Zhu, Guosheng Hu +5
Recently, deep learning based facial landmark detection has achieved great success. Despite this, we notice that the semantic ambiguity greatly degrades the detection performance.…
IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance Matters
Xinshao Wang, Yang Hua, Elyor Kodirov +2
In this work, we study robust deep learning against abnormal training data from the perspective of example weighting built in empirical loss functions, i.e., gradient magnitude wit…
Ranked List Loss for Deep Metric Learning
Xinshao Wang, Yang Hua, Elyor Kodirov +1
The objective of deep metric learning (DML) is to learn embeddings that can capture semantic similarity and dissimilarity information among data points. Existing pairwise or triple…
Deep Metric Learning by Online Soft Mining and Class-Aware Attention
Xinshao Wang, Yang Hua, Elyor Kodirov +2
Deep metric learning aims to learn a deep embedding that can capture the semantic similarity of data points. Given the availability of massive training samples, deep metric learnin…
Deep Stock Representation Learning: From Candlestick Charts to Investment Decisions
Guosheng Hu, Yuxin Hu, Kai Yang +8
We propose a novel investment decision strategy (IDS) based on deep learning. The performance of many IDSs is affected by stock similarity. Most existing stock similarity measureme…