cs.CVNov 18, 2026

Angular Conditional Distillation: Overcoming Classifier Geometry Mismatch

Authors: Xuefei Zhang, Ruoqi Wang, Lei Cui

Organizations: Institute of AI for Industries (IAII), Chinese Academy of Sciences

Abstract

Classifier outputs provide a fundamental and univer- sally available knowledge interface for knowledge distil- lation (KD). However, standard logit objectives entangle transferable semantic relations with architecture-dependent parameterization artifacts, causing a classifier geometry mismatch that makes direct knowledge transfer unreliable. To address this, we propose Angular Conditional Distilla- tion (ACD). First, the Angular Coordinate Interface (ACI) reconstructs the student classifier using angular coordi- nates, suppressing magnitude and bias effects to provide a geometry-compatible space. Then, Scale-Invariant Condi- tional Distillation (SICD) standardizes outputs and exclu- sively transfers conditional non-target relations, filtering out untransferable absolute confidence. Together, ACI de- fines where to transfer, while SICD defines what to transfer. Extensive experiments show that ACD achieves state-of-the- art performance over existing KD methods. Moreover, as a universal drop-in replacement, it consistently improves existing distillation pipelines while requiring no feature adapters or additional inference-time cost. Code is avail- able at https://github.com/laniusnan/ACD.

Figures & tables

Explore similar work

Sep 30, 2026

Learning Beyond Full Imitation: Task-Preserving Knowledge Distillation

Knowledge distillation transfers knowledge by encouraging a student to match a teacher's predicted class probabilities. These probabilities express not only confidence in the correct class, but also relations among incorrect alternatives. Yet closer imitation does not necessarily yield a better student. A student may already distinguish the correct class more sharply than its teacher, so further imitation can require giving back discrimination it has acquired. Our main result is an exact separation between full imitation and conditional learning. When the correct class's score advantage over each alternative must be preserved, full teacher-to-student KL minimization is blocked exactly when the student assigns no more probability than the teacher to every incorrect class. Crucially, the teacher's relative probabilities among incorrect classes remain fully learnable. We characterize the exact price of this transfer: a minimum increase in correct-class log-odds that compensates for the largest conditional-probability mismatch. Label fitting and conditional matching can therefore be completed even as full teacher KL diverges. This separation motivates task-preserving knowledge distillation (TPKD), which keeps the label gradient intact and minimally corrects the conditional gradient so that its output update preserves the label step's gains against every incorrect alternative. The corrected conditional direction retains more than half of the original first-order conditional descent at the same step size, with a tight bound. For a fixed positive conditional target and sufficiently small constant output steps, label and conditional errors vanish together. Experiments trace this learning from exact head updates to ordinary network training. TPKD reaches 88.05% accuracy on CIFAR-100 and 93.81% on CLINC150, improving over standard distillation by 0.47 and 0.35 percentage points across three seeds.
Aug 14, 2026

Discovering and Preserving Category Correlation Knowledge via Adaptive Reciprocal Knowledge Distillation

Knowledge distillation aims to improve the performance of lightweight student models by transferring knowledge from larger and more powerful teacher models. However, a substantial size gap between teacher and student models often impedes effective knowledge transfer. Most existing approaches adopt a static, one-way teacher-to-student distillation paradigm, which overlooks the dynamic nature of student learning and fails to provide targeted guidance on hard samples. In this paper, we propose adaptive reciprocal knowledge distillation (AR-KD), a novel method that improves knowledge transfer by simplifying the teacher's output distribution. Specifically, AR-KD performs reciprocal adaptation on the teacher by matching its class correlation matrix to the student's relational representation, which reshapes the teacher's prediction structure to better suit the student's capacity. This relational alignment mitigates the collapse of inter-class dark knowledge caused by overconfident teachers, enabling the student to learn from richer and more compatible supervisory signals. We evaluate AR-KD on CIFAR-100 and ImageNet-1k classification datasets, where it outperforms state-of-the-art knowledge distillation baselines. Specifically, AR-KD improves student performance across homogeneous and heterogeneous setups: up to 7.13% accuracy gain for students, 1.42% to 4.15% higher than vanilla KD on average, and further improvements when integrated with other advanced methods. Our code is available at https://anonymous.4open.science/r/ARKD/.
Nov 18, 2026

TALD: Transferability-Aware Logit Disentanglement for Cross-Modal Knowledge Distillation

Cross-modal knowledge distillation can incur negative transfer when source-modality supervision conflicts with the target modality's discriminative characteristics. We propose TALD, a two-stage framework for Transferability-Aware Logit Disentanglement in class-aligned logit space. Guided by task-dependent self-benefiting and cross-modal exclusivity criteria, a Residual Disentangler decomposes logits from a teacher and an independently trained target-modality reference student into modality-general and modality-specific components. A Sample-Adaptive Modulator regulates decomposition constraints and sample-specific fusion weights. The learned modality-general components are then adaptively fused to supervise the final student. Across five benchmarks spanning vision, audio, and text, TALD achieves the largest mean accuracy gain and highest positive-transfer frequency among the compared methods. Across ten transfer directions with five runs each, TALD improves over training without distillation in 84% of evaluations, compared with at most 70% for the baselines, while offering a favorable accuracy-efficiency trade-off. We plan to release the code.