C
Chang Xu
Researcher at University of Sydney
Publications - 467
Citations - 13012
Chang Xu is an academic researcher from University of Sydney. The author has contributed to research in topics: Computer science & Chemistry. The author has an hindex of 42, co-authored 260 publications receiving 7189 citations. Previous affiliations of Chang Xu include University of Melbourne & Information Technology University.
Papers
More filters
Journal ArticleDOI
VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale
TL;DR: Hao et al. as mentioned in this paper identify the small data pitfall that presents in previous KD methods, which results in the underestimation of the power of vanilla KD framework on large-scale datasets such as ImageNet-1K and show that employing stronger data augmentation techniques and using larger datasets can directly decrease the gap between vanilla KD and other meticulously designed KD variants.
Proceedings ArticleDOI
Contrastive Code-Comment Pre-training
TL;DR: C3P as discussed by the authors proposes a contrastive code-comment pre-training approach to solve various downstream code-related tasks, such as code search, clone detection, programming translation and code document generation.
The Two Point Function of the SK Model without External Field at High Temperature
TL;DR: In this paper , it was shown that the two point correlation matrix M = (h σ i σ j i ) 1 ≤ i,j ≤ N of the Sherrington-Kirkpatrick model with zero external field satisfies lim N → ∞ k M − (1 + β 2 − β G ) − 1 k op = 0 in probability, in the full high temperature regime β < 1.
Journal ArticleDOI
Anti-Compression Contrastive Facial Forgery Detection
TL;DR: Wang et al. as discussed by the authors proposed a novel anti-compression forgery detection framework by maintaining closer relations within data under different compression levels, which measures the pair-wise similarity within data as the relations, and forcing the relations of weak and strong compressed data close to each other, thus improving the discriminate power for detecting strong compression data.
Journal ArticleDOI
Inertia of two-qutrit entanglement witnesses
TL;DR: In this paper , the inertias of bipartite entanglement witnesses constructed by the partial transpose of NPT states were investigated and the results were extended to high dimensional states.