Related papers: Quantifying Learnability and Describability of Vis…

The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discriminative visual features. Collecting and annotating such…

Most research on the interpretability of machine learning systems focuses on the development of a more rigorous notion of interpretability. I suggest that a better understanding of the deficiencies of the intuitive notion of…

We consider the problem of discovering novel object categories in an image collection. While these images are unlabelled, we also assume prior knowledge of related but different image classes. We use such prior knowledge to reduce the…

Multimodal pre-trained models, such as CLIP, are popular for zero-shot classification due to their open-vocabulary flexibility and high performance. However, vision-language models, which compute similarity scores between images and class…

Concept discovery is one of the open problems in the interpretability literature that is important for bridging the gap between non-deep learning experts and model end-users. Among current formulations, concepts defines them by as a…

In computer vision, a prevailing method for quantifying dataset bias is to train a model to distinguish between datasets. High classification accuracy is then interpreted as evidence of meaningful semantic differences. This approach assumes…

Exemplar learning of visual similarities in an unsupervised manner is a problem of paramount importance to Computer Vision. In this context, however, the recent breakthrough in deep learning could not yet unfold its full potential. With…

Deep vision models often rely on biases learned from spurious correlations in datasets. To identify these biases, methods that interpret high-level, human-understandable concepts are more effective than those relying primarily on low-level…

The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on…

As humans, we can remember certain visuals in great detail, and sometimes even after viewing them once. What is even more interesting is that humans tend to remember and forget the same things, suggesting that there might be some general…

Image clustering, which involves grouping images into different clusters without labels, is a key task in unsupervised learning. Although previous deep clustering methods have achieved remarkable results, they only explore the intrinsic…

Many Machine Learning algorithms, such as deep neural networks, have long been criticized for being "black-boxes"-a kind of models unable to provide how it arrive at a decision without further efforts to interpret. This problem has raised…

Image clustering divides a collection of images into meaningful groups, typically interpreted post-hoc via human-given annotations. Those are usually in the form of text, begging the question of using text as an abstraction for image…

In this paper, we address an issue of finding explainable clusters of class-uniform data in labelled datasets. The issue falls into the domain of interpretable supervised clustering. Unlike traditional clustering, supervised clustering aims…

Developing inherently interpretable models for prediction has gained prominence in recent years. A subclass of these models, wherein the interpretable network relies on learning high-level concepts, are valued because of closeness of…

We present an interpretable deep model for fine-grained visual recognition. At the core of our method lies the integration of region-based part discovery and attribution within a deep neural network. Our model is trained using image-level…

Unsupervised disentangled representation learning is a long-standing problem in computer vision. This work proposes a novel framework for performing image clustering from deep embeddings by combining instance-level contrastive learning with…

Deep neural networks (DNNs) are known as black-box models. In other words, it is difficult to interpret the internal state of the model. Improving the interpretability of DNNs is one of the hot research topics. However, at present, the…

The recent series of innovations in deep learning (DL) have shown enormous potential to impact individuals and society, both positively and negatively. The DL models utilizing massive computing power and enormous datasets have significantly…

Image captioning is a technology that produces text-based descriptions for an image. Deep learning-based solutions built on top of feature recognition may very well serve the purpose. But as with any other machine learning solution, the…