5 papers
Boosting Adversarial Transferability via Commonality-Oriented Gradient Optimization
Yanting Gao, Yepeng Liu, Junming Liu +4
Exploring effective and transferable adversarial examples is vital for understanding the characteristics and mechanisms of Vision Transformers (ViTs). However, adversarial examples…
Perception Activator: An intuitive and portable framework for brain cognitive exploration
Le Xu, Qi Zhang, Qixian Zhang +3
Recent advances in brain-vision decoding have driven significant progress, reconstructing with high fidelity perceived visual stimuli from neural activity, e.g., functional magneti…
Transformer-Based Person Search with High-Frequency Augmentation and Multi-Wave Mixing
Qilin Shu, Qixian Zhang, Qi Zhang +3
The person search task aims to locate a target person within a set of scene images. In recent years, transformer-based models in this field have made some progress. However, they s…
Improving Prediction Certainty Estimation for Reliable Early Exiting via Null Space Projection
Jianing He, Qi Zhang, Duoqian Miao +4
Early exiting has demonstrated great potential in accelerating the inference of pre-trained language models (PLMs) by enabling easy samples to exit at shallow layers, eliminating t…
COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism
Jianing He, Qi Zhang, Hongyun Zhang +3
Early exiting is an effective paradigm for improving the inference efficiency of pre-trained language models (PLMs) by dynamically adjusting the number of executed layers for each…