Timezone: »

Revisit the Power of Vanilla Knowledge Distillation: from Small Scale to Large Scale
Zhiwei Hao · Jianyuan Guo · Kai Han · Han Hu · Chang Xu · Yunhe Wang

Tue Dec 12 03:15 PM -- 05:15 PM (PST) @ Great Hall & Hall B1+B2 #1007
Event URL: https://github.com/Hao840/vanillaKD »

The tremendous success of large models trained on extensive datasets demonstrates that scale is a key ingredient in achieving superior results. Therefore, the reflection on the rationality of designing knowledge distillation (KD) approaches for limited-capacity architectures solely based on small-scale datasets is now deemed imperative. In this paper, we 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. Specifically, we 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. This highlights the necessity of designing and evaluating KD approaches in the context of practical scenarios, casting off the limitations of small-scale datasets. Our investigation of the vanilla KD and its variants in more complex schemes, including stronger training strategies and different model capacities, demonstrates that vanilla KD is elegantly simple but astonishingly effective in large-scale scenarios. Without bells and whistles, we obtain state-of-the-art ResNet-50, ViT-S, and ConvNeXtV2-T models for ImageNet, which achieve 83.1%, 84.3%, and 85.0% top-1 accuracy, respectively. PyTorch code and checkpoints can be found at https://github.com/Hao840/vanillaKD.

Author Information

Zhiwei Hao (Beijing Institute of Technology)
Jianyuan Guo (University of Sydney)
Kai Han (Huawei Noah's Ark Lab)
Han Hu (Beijing Institute of Technology)
Chang Xu (University of Sydney)
Yunhe Wang (Huawei Noah's Ark Lab)

More from the Same Authors