Classifier-head Informed Feature Masking and Prototype-based Logit Smoothing for Out-of-Distribution Detection

no code implementations • 27 Oct 2023 • Zhuohao Sun, Yiqiao Qiu, Zhijun Tan, Weishi Zheng, Ruixuan Wang

Logit smoothing computes the cosine similarity between the feature vector of the test sample and the prototype of the predicted ID class at the penultimate layer and uses the similarity as an adaptive temperature factor on the logit to alleviate the network's overconfidence prediction for OOD data.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

PAMI: partition input and aggregate outputs for model interpretation

no code implementations • 7 Feb 2023 • Wei Shi, Wentao Zhang, Weishi Zheng, Ruixuan Wang

There is an increasing demand for interpretation of model predictions especially in high-risk applications.

Prompt-based Learning for Unpaired Image Captioning

no code implementations • 26 May 2022 • Peipei Zhu, Xiao Wang, Lin Zhu, Zhenglong Sun, Weishi Zheng, YaoWei Wang, Changwen Chen

Inspired by the success of Vision-Language Pre-Trained Models (VL-PTMs) in this research, we attempt to infer the cross-domain cue information about a given image from the large VL-PTMs for the UIC task.

Image Captioning Image-text Retrieval +2

SATS: Self-Attention Transfer for Continual Semantic Segmentation

1 code implementation • 15 Mar 2022 • Yiqiao Qiu, Yixing Shen, Zhuohao Sun, Yanchong Zheng, Xiaobin Chang, Weishi Zheng, Ruixuan Wang

Considering that pixels belonging to the same class in each image often share similar visual properties, a class-specific region pooling is applied to provide more efficient relationship information for knowledge transfer.

Knowledge Distillation Overlapped 100-10 +8