Overview of Class Activation Maps for Visualization Explainability

Recent research in deep learning methodology has led to a variety of complex modelling techniques in computer vision (CV) that reach or even outperform human performance. Although these black-box deep learning models have obtained astounding results, they are limited in their interpretability and transparency which are critical to take learning machines to the next step to include them in sensitive decision-support systems involving human supervision. Hence, the development of explainable techniques for computer vision (XCV) has recently attracted increasing attention. In the realm of XCV, Class Activation Maps (CAMs) have become widely recognized and utilized for enhancing interpretability and insights into the decision-making process of deep learning models. This work presents a comprehensive overview of the evolution of Class Activation Map methods over time. It also explores the metrics used for evaluating CAMs and introduces auxiliary techniques to improve the saliency of these methods. The overview concludes by proposing potential avenues for future research in this evolving field.

Using network metrics to explore the community structure that underlies movement patterns

This work aims to explore the community structure of Santiago de Chile by analyzing the movement patterns of its residents. We use a dataset containing the approximate locations of home and work places for a subset of anonymized residents to construct a network that represents the movement patterns within the city. Through the analysis of this network, we aim to identify the communities or sub-cities that exist within Santiago de Chile and gain insights into the factors that drive the spatial organization of the city. We employ modularity optimization algorithms and clustering techniques to identify the communities within the network. Our results present that the novelty of combining community detection algorithms with segregation tools provides new insights to further the understanding of the complex geography of segregation during working hours.

PRE: Vision-Language Prompt Learning with Reparameterization Encoder

Large pre-trained vision-language models such as CLIP have demonstrated great potential in zero-shot transferability to downstream tasks. However, to attain optimal performance, the manual selection of prompts is necessary to improve alignment between the downstream image distribution and the textual class descriptions. This manual prompt engineering is the major challenge for deploying such models in practice since it requires domain expertise and is extremely time-consuming. To avoid non-trivial prompt engineering, recent work Context Optimization (CoOp) introduced the concept of prompt learning to the vision domain using learnable textual tokens. While CoOp can achieve substantial improvements over manual prompts, its learned context is worse generalizable to wider unseen classes within the same dataset. In this work, we present Prompt Learning with Reparameterization Encoder (PRE) - a simple and efficient method that enhances the generalization ability of the learnable prompt to unseen classes while maintaining the capacity to learn Base classes. Instead of directly optimizing the prompts, PRE employs a prompt encoder to reparameterize the input prompt embeddings, enhancing the exploration of task-specific knowledge from few-shot samples. Experiments and extensive ablation studies on 8 benchmarks demonstrate that our approach is an efficient method for prompt learning. Specifically, PRE achieves a notable enhancement of 5.60% in average accuracy on New classes and 3% in Harmonic mean compared to CoOp in the 16-shot setting, all achieved within a good training time.