Related papers: Reproducibility study of "LICO: Explainable Models…

Deep Learning methods are renowned for their performances, yet their lack of interpretability prevents them from high-stakes contexts. Recent model agnostic methods address this problem by providing post-hoc interpretability methods by…

Masked Image Modeling (MIM) has emerged as a promising method for deriving visual representations from unlabeled image data by predicting missing pixels from masked portions of images. It excels in region-aware learning and provides strong…

As a fundamental visual attribute, image complexity significantly influences both human perception and the performance of computer vision models. However, accurately assessing and quantifying image complexity remains a challenging task. (1)…

Our target is to learn visual correspondence from unlabeled videos. We develop LIIR, a locality-aware inter-and intra-video reconstruction framework that fills in three missing pieces, i.e., instance discrimination, location awareness, and…

Most recent work on interpretability of complex machine learning models has focused on estimating $\textit{a posteriori}$ explanations for previously trained models around specific predictions. $\textit{Self-explaining}$ models where…

Benefit from flexible network designs and end-to-end joint optimization approach, learned image compression (LIC) has demonstrated excellent coding performance and practical feasibility in recent years. However, existing compression models…

Recent text-only models demonstrate remarkable mathematical reasoning capabilities. Extending these to visual domains requires vision-language models to translate images into text descriptions. However, current models, trained to produce…

The emergence of in-context learning (ICL) enables large pre-trained language models (PLMs) to make predictions for unseen inputs without updating parameters. Despite its potential, ICL's effectiveness heavily relies on the quality,…

Learning robust representations that allow to reliably establish relations between images is of paramount importance for virtually all of computer vision. Annotating the quadratic number of pairwise relations between training images is…

Post-hoc explainability methods aim to clarify predictions of black-box machine learning models. However, it is still largely unclear how well users comprehend the provided explanations and whether these increase the users ability to…

Reproducibility is an important requirement in evolutionary computation, where results largely depend on computational experiments. In practice, reproducibility relies on how algorithms, experimental protocols, and artifacts are documented…

Mechanistic interpretability (MI) is an emerging framework for interpreting neural networks. Given a task and model, MI aims to discover a succinct algorithmic process, an interpretation, that explains the model's decision process on that…

Person re-identification (ReID) has evolved from handcrafted feature-based methods to deep learning approaches and, more recently, to models incorporating large language models (LLMs). Early methods struggled with variations in lighting,…

One of the challenges in machine learning research is to ensure that presented and published results are sound and reliable. Reproducibility, that is obtaining similar results as presented in a paper or talk, using the same code and data…

In-context learning (ICL) has emerged as a successful paradigm for leveraging large language models (LLMs). However, it often struggles to generalize beyond the distribution of the provided demonstrations. A recent advancement in enhancing…

Learning multiple tasks sequentially without forgetting previous knowledge, called Continual Learning(CL), remains a long-standing challenge for neural networks. Most existing methods rely on additional network capacity or data replay. In…

The reproducibility of scientific articles is central to the advancement of science. Despite this importance, evaluating reproducibility remains challenging due to the scarcity of ground truth data. Predictive models can address this…

Large language models (LLMs) have significantly advanced natural language processing, excelling in areas like text generation, summarization, and question-answering. Despite their capabilities, these models face challenges when fine-tuned…

Contrastive learning models have demonstrated impressive abilities to capture semantic similarities by aligning representations in the embedding space. However, their performance can be limited by the quality of the training data and its…

While deep learning makes significant achievements in Artificial Intelligence (AI), the lack of transparency has limited its broad application in various vertical domains. Explainability is not only a gateway between AI and real world, but…