Logit-Based Losses Limit the Effectiveness of Feature Knowledge Distillation

• URL: http://arxiv.org/abs/2511.14981v1
• Date: Tue, 18 Nov 2025 23:50:31 GMT
• Title: Logit-Based Losses Limit the Effectiveness of Feature Knowledge Distillation
• Authors: Nicholas Cooper, Lijun Chen, Sailesh Dwivedy, Danna Gurari,
• Abstract summary: Knowledge distillation (KD) methods can transfer knowledge of a parameter-heavy teacher model to a light-weight student model.<n>We propose a feature KD framework for training the student's backbone using feature-based losses exclusively.<n>We demonstrate our KD method achieves state-of-the-art performance, delivering top-1 accuracy boosts of up to 15% over standard approaches.
• Score: 13.970649308150895
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Knowledge distillation (KD) methods can transfer knowledge of a parameter-heavy teacher model to a light-weight student model. The status quo for feature KD methods is to utilize loss functions based on logits (i.e., pre-softmax class scores) and intermediate layer features (i.e., latent representations). Unlike previous approaches, we propose a feature KD framework for training the student's backbone using feature-based losses exclusively (i.e., without logit-based losses such as cross entropy). Leveraging recent discoveries about the geometry of latent representations, we introduce a knowledge quality metric for identifying which teacher layers provide the most effective knowledge for distillation. Experiments on three image classification datasets with four diverse student-teacher pairs, spanning convolutional neural networks and vision transformers, demonstrate our KD method achieves state-of-the-art performance, delivering top-1 accuracy boosts of up to 15% over standard approaches. We publically share our code to facilitate future work at https://github.com/Thegolfingocto/KD_wo_CE.

Related papers

• Adaptive Explicit Knowledge Transfer for Knowledge Distillation [17.739979156009696]
  We show that the performance of logit-based knowledge distillation can be improved by effectively delivering the probability distribution for the non-target classes from the teacher model. We propose a new loss that enables the student to learn explicit knowledge along with implicit knowledge in an adaptive manner. Experimental results demonstrate that the proposed method, called adaptive explicit knowledge transfer (AEKT) method, achieves improved performance compared to the state-of-the-art KD methods.
  arXiv  Detail & Related papers  (2024-09-03T07:42:59Z)
• Multi Teacher Privileged Knowledge Distillation for Multimodal Expression Recognition [58.41784639847413]
  Human emotion is a complex phenomenon conveyed and perceived through facial expressions, vocal tones, body language, and physiological signals. In this paper, a multi-teacher PKD (MT-PKDOT) method with self-distillation is introduced to align diverse teacher representations before distilling them to the student. Results indicate that our proposed method can outperform SOTA PKD methods.
  arXiv  Detail & Related papers  (2024-08-16T22:11:01Z)
• Improving Knowledge Distillation via Regularizing Feature Norm and Direction [16.98806338782858]
  Knowledge distillation (KD) exploits a large well-trained model (i.e., teacher) to train a small student model on the same dataset for the same task. Treating teacher features as knowledge, prevailing methods of knowledge distillation train student by aligning its features with the teacher's, e.g., by minimizing the KL-divergence between their logits or L2 distance between their intermediate features. While it is natural to believe that better alignment of student features to the teacher better distills teacher knowledge, simply forcing this alignment does not directly contribute to the student's performance, e.g.
  arXiv  Detail & Related papers  (2023-05-26T15:05:19Z)
• Knowledge Diffusion for Distillation [53.908314960324915]
  The representation gap between teacher and student is an emerging topic in knowledge distillation (KD) We state that the essence of these methods is to discard the noisy information and distill the valuable information in the feature. We propose a novel KD method dubbed DiffKD, to explicitly denoise and match features using diffusion models.
  arXiv  Detail & Related papers  (2023-05-25T04:49:34Z)
• Gradient-Guided Knowledge Distillation for Object Detectors [3.236217153362305]
  We propose a novel approach for knowledge distillation in object detection, named Gradient-guided Knowledge Distillation (GKD) Our GKD uses gradient information to identify and assign more weights to features that significantly impact the detection loss, allowing the student to learn the most relevant features from the teacher. Experiments on the KITTI and COCO-Traffic datasets demonstrate our method's efficacy in knowledge distillation for object detection.
  arXiv  Detail & Related papers  (2023-03-07T21:09:09Z)
• Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation [66.25738680429463]
  Knowledge Distillation (KD) for object detection aims to train a compact detector by transferring knowledge from a teacher model. We propose inconsistent knowledge distillation (IKD) which aims to distill knowledge inherent in the teacher model's counter-intuitive perceptions. Our method outperforms state-of-the-art KD baselines on one-stage, two-stage and anchor-free object detectors.
  arXiv  Detail & Related papers  (2022-09-20T16:36:28Z)
• Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation [70.92135839545314]
  We propose the dynamic prior knowledge (DPK), which integrates part of teacher's features as the prior knowledge before the feature distillation. Our DPK makes the performance of the student model positively correlated with that of the teacher model, which means that we can further boost the accuracy of students by applying larger teachers.
  arXiv  Detail & Related papers  (2022-06-13T11:52:13Z)
• Impact of a DCT-driven Loss in Attention-based Knowledge-Distillation for Scene Recognition [64.29650787243443]
  We propose and analyse the use of a 2D frequency transform of the activation maps before transferring them. This strategy enhances knowledge transferability in tasks such as scene recognition. We publicly release the training and evaluation framework used along this paper at http://www.vpu.eps.uam.es/publications/DCTBasedKDForSceneRecognition.
  arXiv  Detail & Related papers  (2022-05-04T11:05:18Z)
• Knowledge Distillation with Deep Supervision [6.8080936803807734]
  We propose Deeply-Supervised Knowledge Distillation (DSKD), which fully utilizes class predictions and feature maps of the teacher model to supervise the training of shallow student layers. A loss-based weight allocation strategy is developed in DSKD to adaptively balance the learning process of each shallow layer, so as to further improve the student performance.
  arXiv  Detail & Related papers  (2022-02-16T03:58:21Z)
• EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation [61.33010904301476]
  Event cameras sense per-pixel intensity changes and produce asynchronous event streams with high dynamic range and less motion blur. We propose a novel approach, called bfEvDistill, to learn a student network on the unlabeled and unpaired event data. We show that EvDistill achieves significantly better results than the prior works and KD with only events and APS frames.
  arXiv  Detail & Related papers  (2021-11-24T08:48:16Z)
• How and When Adversarial Robustness Transfers in Knowledge Distillation? [137.11016173468457]
  This paper studies how and when the adversarial robustness can be transferred from a teacher model to a student model in Knowledge distillation (KD) We show that standard KD training fails to preserve adversarial robustness, and we propose KD with input gradient alignment (KDIGA) for remedy. Under certain assumptions, we prove that the student model using our proposed KDIGA can achieve at least the same certified robustness as the teacher model.
  arXiv  Detail & Related papers  (2021-10-22T21:30:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.