4 papers
Learned JPEG Compression for DNN Vision
Kaixiang Zheng, Ahmed H. Salamah, Siyu Chen +1
JPEG, a lossy image compression technique designed for human viewers, has maintained its dominance for decades. However, in the era of artificial intelligence (AI), a substantial p…
Post-hoc Selective Classification for Reliable Synthetic Image Detection
Kaixiang Zheng, Jacob H. Seidman
As synthetic images become increasingly realistic, reliable synthetic image detection techniques are of pressing need to prevent their misuse. Despite satisfactory in-distribution…
JPEG Inspired Deep Learning
Ahmed H. Salamah, Kaixiang Zheng, Yiwen Liu +1
Although it is traditionally believed that lossy image compression, such as JPEG compression, has a negative impact on the performance of deep neural networks (DNNs), it is shown b…
Knowledge Distillation Based on Transformed Teacher Matching
Kaixiang Zheng, En-Hui Yang
As a technique to bridge logit matching and probability distribution matching, temperature scaling plays a pivotal role in knowledge distillation (KD). Conventionally, temperature…