# Sample-level Adaptive Knowledge Distillation for Action Recognition

arXiv: https://arxiv.org/abs/2504.00606 · HTML: https://mlsanity.com/paper/2504.00606/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 31 of its 42 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [TinyViT: Fast Pretraining Distillation for Small Vision Transformers](https://mlsanity.com/paper/2207.10666/) (2022)
- [Learning Deep Representations with Probabilistic Knowledge Transfer](https://mlsanity.com/paper/1803.10837/) (2018)
- [Unmasked Teacher: Towards Training-Efficient Video Foundation Models](https://mlsanity.com/paper/2303.16058/) (2023)
- [Temporal Pyramid Network for Action Recognition](https://mlsanity.com/paper/2004.03548/) (2020)
- [Curriculum Temperature for Knowledge Distillation](https://mlsanity.com/paper/2211.16231/) (2022)
- [Logit Standardization in Knowledge Distillation](https://mlsanity.com/paper/2403.01427/) (2024)
- [From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels](https://mlsanity.com/paper/2303.13005/) (2023)
- [D3D: Distilled 3D Networks for Video Action Recognition](https://mlsanity.com/paper/1812.08249/) (2018)
- [CrossKD: Cross-Head Knowledge Distillation for Object Detection](https://mlsanity.com/paper/2306.11369/) (2023)
- [NORM: Knowledge Distillation via N-to-One Representation Matching](https://mlsanity.com/paper/2305.13803/) (2023)
- [Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation](https://mlsanity.com/paper/2206.06067/) (2022)
- [Frequency Attention for Knowledge Distillation](https://mlsanity.com/paper/2403.05894/) (2024)
- [Selecting and Composing Learning Rate Policies for Deep Neural Networks](https://mlsanity.com/paper/2210.12936/) (2022)
- [What Can Simple Arithmetic Operations Do for Temporal Modeling?](https://mlsanity.com/paper/2307.08908/) (2023)
- [Generative Model-based Feature Knowledge Distillation for Action Recognition](https://mlsanity.com/paper/2312.08644/) (2023)

## Built on by (most cited first, 4 of 4)

- [MobiAct: Efficient MAV Action Recognition Using MobileNetV4 with Contrastive Learning and Knowledge Distillation](https://mlsanity.com/paper/2510.19273/) (2025)
- [Following the Teacher's Footsteps: Scheduled Checkpoint Distillation for Domain-Specific LLMs](https://mlsanity.com/paper/2601.10114/) (2026)
- [Channel-wise Dynamic Knowledge Distillation via Adaptive Sample Generation for Action Recognition](https://mlsanity.com/paper/2608.03100/) (2026)
- [TeacherGRPO: Closing the Capacity Gap in Reasoning Distillation via Teacher Alignment](https://mlsanity.com/paper/2609.33426/) (2026)

## Abstract (arXiv)

Knowledge Distillation (KD) compresses neural networks by learning a small network (student) via transferring knowledge from a pre-trained large network (teacher). Many endeavours have been devoted to the image domain, while few works focus on video analysis which desires training much larger model making it be hardly deployed in resource-limited devices. However, traditional methods neglect two important problems, i.e., 1) Since the capacity gap between the teacher and the student exists, some knowledge w.r.t. difficult-to-transfer samples cannot be correctly transferred, or even badly affects the final performance of student, and 2) As training progresses, difficult-to-transfer samples may become easier to learn, and vice versa. To alleviate the two problems, we propose a Sample-level Adaptive Knowledge Distillation (SAKD) framework for action recognition. In particular, it mainly consists of the sample distillation difficulty evaluation module and the sample adaptive distillation module. The former applies the temporal interruption to frames, i.e., randomly dropout or shuffle the frames during training, which increases the learning difficulty of samples during distillation, so as to better discriminate their distillation difficulty. The latter module adaptively adjusts distillation ratio at sample level, such that KD loss dominates the training with easy-to-transfer samples while vanilla loss dominates that with difficult-to-transfer samples. More importantly, we only select those samples with both low distillation difficulty and high diversity to train the student model for reducing computational cost. Experimental results on two video benchmarks and one image benchmark demonstrate the superiority of the proposed method by striking a good balance between performance and efficiency.