The paper investigates how knowledge distillation from Vision Transformers to smaller CNNs can cause dimensional collapse in the student’s representation space. Using SVD and Shannon entropy, the authors show that cosine‑based distillation leads to a drastic reduction in effective rank, while adding an InfoNCE objective can double the rank but harms downstream accuracy due to signal dilution. They further demonstrate that a label‑aware contrastive objective (Supervised Contrastive distillation) can maintain or improve accuracy without unnecessary rank expansion, indicating that effective rank alone is not a reliable indicator of representation quality.
By Kabir Thayani
Vision Transformers underperform convolutional networks when training data is scarce, and distilling convolutional inductive biases from a CNN teacher is an effective remedy that leaves the deployed model unchanged. General-purpose feature distillation, however, transfers little in this setting.
arXiv:2604.05819v2 Announce Type: replace-cross
Abstract: Interpreting the decisions of complex computer vision models is crucial to establish trust and accountability, especially in safety-critical...
By David Schinagl, Christian Fruhwirth-Reisinger, Alexander Prutsch, Samuel Schulter, Horst Possegger
arXiv:2607. 22872v1 Announce Type: new Abstract: Post-training quantization (PTQ) has become a practical solution for deploying deep learning models on resource-constrained edge devices by compressing high-precision floating-point weights into low-precision representations without requiring retraining.
By Kazi Kamruzzaman Rabbi, Md. Zami Al Zunaed Farabe, M. Sohel Rahman
Post-training quantization (PTQ) has become a practical solution for deploying deep learning models on resource-constrained edge devices by compressing high-precision floating-point weights into low-precision representations without requiring retraining. Past research has demonstrated that quantization largely preserves classification accuracy; however, whether it also preserves the model's internal reasoning remains an open question.
arXiv:2606. 27527v1 Announce Type: cross Abstract: Large Language Models (LLMs) possess broad conceptual knowledge acquired through large-scale text pretraining, yet their potential to supervise models in other modalities remains underexplored.
By Thomas Shih-Chao Liang, Zhuoran Yu, Yong Jae Lee
The paper investigates how knowledge distillation (KD) applied at intermediate layers of a neural network can affect overfitting and model performance. While traditional KD focuses on the final output, this study explores block‑wise KD across eleven datasets, finding that on standard datasets the last block suffices, but on fine‑grained, data‑scarce settings intermediate supervision significantly improves accuracy. The authors also analyze optimal supervision granularity using attention maps, Centered Kernel Alignment, and Grad‑CAM, and examine teacher‑student fine‑tuning strategies.
By Irene Trigueros-Lorca, Leonardo Concepci\'on, Christian Wagner, Isaac Triguero, Daniel Molina
arXiv:2608. 09287v1 Announce Type: cross Abstract: Data-Free Knowledge Distillation (DFKD) transfers knowledge from a pretrained teacher model to a compact student model by synthesizing semantically informative data, eliminating the need for access to the original training dataset.
By Xuewan He, Tong Chu, Zihan Cheng, Yuchen Su, Qianxin Xia, Guoming Lu, Jielei Wang, Wen Li
arXiv:2606. 31048v1 Announce Type: cross Abstract: This paper investigates knowledge distillation from a large reasoning model (DeepSeek-R1) to a compact student model (Qwen2.
By Gaurab Baral, Aaditya Khanal, Yangyang Tao, Junxiu Zhou
The paper presents a method for cross‑architecture knowledge distillation from a fine‑tuned DINOv2 Vision Transformer teacher to a lightweight bidirectional Visual State Space Model (LVSSM) student for tea leaf disease classification. By addressing training‑stability issues with a progressive convolutional stem and gated selective‑scan block, the 4.45 M‑parameter student achieves a mean test accuracy of 95.41%—a 3.09‑point improvement over the teacher’s 92.32%—while using only one‑fifth of the teacher’s parameters. Ablation studies show that simple logit‑level distillation outperforms intermediate feature alignment, and the gains are specific to students that start below the teacher’s performance.
By Zibo Zhou, Zongsen Qiu, Rui Chen, Yujie Yao, Yue Zhou, Jianjun Wang
arXiv:2606. 04922v1 Announce Type: cross Abstract: Current prompt-based and adapter-based tuning of vision-language models (VLMs) is attractive for medical imaging, where clinical data sensitivity favors frozen backbones and annotations are limited.
By Tran Dinh Tien, Zhiqiang Shen
arXiv:2609.06232v1 Announce Type: cross
Abstract: Ground-truth defect masks in industrial inspection datasets are typically reserved for evaluation. This paper repurposes them as spatial supervision...
By Sajjad Rezvani Boroujeni, Muskan Saraf, Gnana Tulasi Makineni, Tom Bush, Hossein Abedi