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:2607. 14703v1 Announce Type: cross Abstract: Multiple instance learning (MIL) has become the main paradigm for whole-slide image (WSI) analysis in computational pathology.
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.
arXiv:2605.12491v2 Announce Type: replace Abstract: Vision Transformers (ViTs) learn rich visual-semantic representations through all-to-all self-attention among patch tokens. However, this design im...
IronViT proposes a new approach to building efficient generalist vision encoders by first consolidating the knowledge of multiple specialist teachers into a softmax attention bridge and then transferring this consolidated representation to a hybrid softmax‑linear attention architecture. This two‑stage distillation process, supported by a curated data pipeline, allows the model to capture semantic, spatial, language‑aligned, and action‑relevant cues while avoiding the high‑resolution cost of traditional softmax attention. Across tasks such as recognition, retrieval, dense prediction, multimodal understanding, and robotic learning, IronViT matches or exceeds the performance of leading specialist and generalist encoders, with the hybrid encoder offering increasing efficiency at higher resolutions.
arXiv:2607. 06796v1 Announce Type: cross Abstract: Deep learning has achieved remarkable success in various domains including time series analysis, computer vision and natural language processing.
arXiv:2609.10321v1 Announce Type: new Abstract: Knowledge distillation offers an efficient route to transfer a task-adapted vision-language teacher to a compact student. The training target in curren...
arXiv:2609.23561v1 Announce Type: new Abstract: Deploying efficient neural networks is essential in resource-constrained environments, yet compact models often sacrifice interpretability - a critical...
MLLMCLIP introduces a heterogeneous distillation framework that transfers multimodal knowledge from a generative Multimodal Large Language Model (MLLM) teacher directly into a discriminative CLIP student, eliminating the need for synthetic hard negatives. The method uses an attention-based per-layer token selection and a CKA-based distillation loss to bridge architectural differences between the two models. As a result, MLLMCLIP achieves state‑of‑the‑art compositional accuracy and improves zero‑shot classification and image‑text retrieval performance.
arXiv:2510.19266v3 Announce Type: replace Abstract: State-space models (SSMs) have emerged as promising alternatives to Transformers for sequence modeling. However, training competitive SSMs from scr...
arXiv:2609.09863v1 Announce Type: new Abstract: Choosing a deep learning architecture for label-free single-cell classification remains an open question, with microscopy benchmarks reporting conflict...
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.
arXiv:2505.16157v3 Announce Type: replace Abstract: Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Tran...