# Enhancing Pre-trained Representation Classifiability can Boost its Interpretability

arXiv: https://arxiv.org/abs/2510.24105 · HTML: https://mlsanity.com/paper/2510.24105/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 62 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://mlsanity.com/paper/2103.11251/) (2021)
- [Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification](https://mlsanity.com/paper/2211.11158/) (2022)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [A Survey on Multimodal Large Language Models for Autonomous Driving](https://mlsanity.com/paper/2311.12320/) (2023)
- [Label-Free Concept Bottleneck Models](https://mlsanity.com/paper/2304.06129/) (2023)
- [UniFormer: Unifying Convolution and Self-attention for Visual Recognition](https://mlsanity.com/paper/2201.09450/) (2022)
- [Interpreting CLIP's Image Representation via Text-Based Decomposition](https://mlsanity.com/paper/2310.05916/) (2023)
- [Promises and Pitfalls of Black-Box Concept Learning Models](https://mlsanity.com/paper/2106.13314/) (2021)
- [Revisiting Weakly Supervised Pre-Training of Visual Perception Models](https://mlsanity.com/paper/2201.08371/) (2022)

## Built on by (most cited first, 2 of 2)

- [ForensicConcept: Transferable Forensic Concepts for AIGI Detection](https://mlsanity.com/paper/2606.07034/) (2026)
- [On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training](https://mlsanity.com/paper/2609.36659/) (2026)

## Abstract (arXiv)

The visual representation of a pre-trained model prioritizes the classifiability on downstream tasks, while the widespread applications for pre-trained visual models have posed new requirements for representation interpretability. However, it remains unclear whether the pre-trained representations can achieve high interpretability and classifiability simultaneously. To answer this question, we quantify the representation interpretability by leveraging its correlation with the ratio of interpretable semantics within the representations. Given the pre-trained representations, only the interpretable semantics can be captured by interpretations, whereas the uninterpretable part leads to information loss. Based on this fact, we propose the Inherent Interpretability Score (IIS) that evaluates the information loss, measures the ratio of interpretable semantics, and quantifies the representation interpretability. In the evaluation of the representation interpretability with different classifiability, we surprisingly discover that the interpretability and classifiability are positively correlated, i.e., representations with higher classifiability provide more interpretable semantics that can be captured in the interpretations. This observation further supports two benefits to the pre-trained representations. First, the classifiability of representations can be further improved by fine-tuning with interpretability maximization. Second, with the classifiability improvement for the representations, we obtain predictions based on their interpretations with less accuracy degradation. The discovered positive correlation and corresponding applications show that practitioners can unify the improvements in interpretability and classifiability for pre-trained vision models. Codes are available at https://github.com/ssfgunner/IIS.