Blar i forfatter "Chakraborty, Rwiddhi"

Viser treff 1-4 av 4

    • ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations 

      Chakraborty, Rwiddhi; Sletten, Adrian; Kampffmeyer, Michael Christian (Journal article; Tidsskriftartikkel, 2024-09-16)
      Group robustness strategies aim to mitigate learned biases in deep learning models that arise from spurious correlations present in their training datasets. However, most existing methods rely on the access to the label distribution of the groups, which is time-consuming and expensive to obtain. As a result, unsupervised group robustness strategies are sought. Based on the insight that a trained ...

    • Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddings 

      Trosten, Daniel Johansen; Chakraborty, Rwiddhi; Løkse, Sigurd Eivindson; Wickstrøm, Kristoffer; Jenssen, Robert; Kampffmeyer, Michael (Journal article; Tidsskriftartikkel; Peer reviewed, 2023-08-22)
      Distance-based classification is frequently used in transductive few-shot learning (FSL). However, due to the high-dimensionality of image representations, FSL classifiers are prone to suffer from the hubness problem, where a few points (hubs) occur frequently in multiple nearest neighbour lists of other points. Hubness negatively impacts distance-based classification when hubs from one class appear ...

    • Model and Data Diagnosis under Limited Supervision in Modern AI 

      Chakraborty, Rwiddhi (Doctoral thesis; Doktorgradsavhandling, 2024-12-13)
      Deep Learning in modern Artificial Intelligence (AI) has witnessed unprecedented success on a variety of domains over the past decade, ranging from computer vision to natural language reasoning tasks. This success is owed primarily to the availability of large, annotated datasets, the existence of powerful mathematical models, and the mechanism to train large models on such data with advanced resources ...

    • Visual Data Diagnosis and Debiasing with Concept Graphs 

      Chakraborty, Rwiddhi (Journal article; Tidsskriftartikkel, 2024-09-26)
      The widespread success of deep learning models today is owed to the curation of extensive datasets significant in size and complexity. However, such models frequently pick up inherent biases in the data during the training process, leading to unreliable predictions. Diagnosing and debiasing datasets is thus a necessity to ensure reliable model performance. In this paper, we present ConBias, a novel ...