125 citations · 227 across the 12 of their papers we have counts for
13 papers
What Does Softmax Probability Tell Us about Classifiers Ranking Across Diverse Test Conditions?
Weijie Tu, Weijian Deng, Liang Zheng +1
This work aims to develop a measure that can accurately rank the performance of various classifiers when they are tested on unlabeled data from out-of-distribution (OOD) distributi…
A Bag-of-Prototypes Representation for Dataset-Level Applications
Weijie Tu, Weijian Deng, Tom Gedeon +1
This work investigates dataset vectorization for two dataset-level tasks: assessing training set suitability and test set difficulty. The former measures how suitable a training se…
Adaptive Calibrator Ensemble for Model Calibration under Distribution Shift
Yuli Zou, Weijian Deng, Liang Zheng
Model calibration usually requires optimizing some parameters (e.g., temperature) w.r.t an objective function (e.g., negative log-likelihood). In this paper, we report a plain, imp…
Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation
Weijian Deng, Yumin Suh, Stephen Gould +1
This work aims to assess how well a model performs under distribution shifts without using labels. While recent methods study prediction confidence, this work reports prediction di…
On the Strong Correlation Between Model Invariance and Generalization
Weijian Deng, Stephen Gould, Liang Zheng
Generalization and invariance are two essential properties of any machine learning model. Generalization captures a model's ability to classify unseen data while invariance measure…
Ranking Models in Unlabeled New Environments
Xiaoxiao Sun, Yunzhong Hou, Weijian Deng +2
Consider a scenario where we are supplied with a number of ready-to-use models trained on a certain source domain and hope to directly apply the most appropriate ones to different…
What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?
Weijian Deng, Stephen Gould, Liang Zheng
Understanding classifier decision under novel environments is central to the community, and a common practice is evaluating it on labeled test sets. However, in real-world testing,…
Fine-grained Classification via Categorical Memory Networks
Weijian Deng, Joshua Marsh, Stephen Gould +1
Motivated by the desire to exploit patterns shared across classes, we present a simple yet effective class-specific memory module for fine-grained feature learning. The memory modu…
Are Labels Always Necessary for Classifier Accuracy Evaluation?
Weijian Deng, Liang Zheng
To calculate the model accuracy on a computer vision task, e.g., object recognition, we usually require a test set composing of test samples and their ground truth labels. Whilst s…
Domain Alignment with Triplets
Weijian Deng, Liang Zheng, Jianbin Jiao
Deep domain adaptation methods can reduce the distribution discrepancy by learning domain-invariant embedddings. However, these methods only focus on aligning the whole data distri…
Similarity-preserving Image-image Domain Adaptation for Person Re-identification
Weijian Deng, Liang Zheng, Qixiang Ye +2
This article studies the domain adaptation problem in person re-identification (re-ID) under a "learning via translation" framework, consisting of two components, 1) translating th…
Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
Weijian Deng, Liang Zheng, Qixiang Ye +3
Person re-identification (re-ID) models trained on one domain often fail to generalize well to another. In our attempt, we present a "learning via translation" framework. In the ba…
SVDNet for Pedestrian Retrieval
Yifan Sun, Liang Zheng, Weijian Deng +1
This paper proposes the SVDNet for retrieval problems, with focus on the application of person re-identification (re-ID). We view each weight vector within a fully connected (FC) l…