Related papers: A Concept Learning Tool Based On Calculating Versi…

The goal of image ordinal estimation is to estimate the ordinal label of a given image with a convolutional neural network. Existing methods are mainly based on ordinal regression and particularly focus on modeling the ordinal mapping from…

Contrastive learning has revolutionized the field of computer vision, learning rich representations from unlabeled data, which generalize well to diverse vision tasks. Consequently, it has become increasingly important to explain these…

The goal of imitation learning (IL) is to learn a good policy from high-quality demonstrations. However, the quality of demonstrations in reality can be diverse, since it is easier and cheaper to collect demonstrations from a mix of experts…

Cross-modal distillation has been widely used to transfer knowledge across different modalities, enriching the representation of the target unimodal one. Recent studies highly relate the temporal synchronization between vision and sound to…

This work proposes a new image analysis tool called Label Consistent Transform Learning (LCTL). Transform learning is a recent unsupervised representation learning approach; we add supervision by incorporating a label consistency…

Variable names are critical for conveying intended program behavior. Machine learning-based program analysis methods use variable name representations for a wide range of tasks, such as suggesting new variable names and bug detection.…

Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separation between the…

The exemplar-free class incremental learning requires classification models to learn new class knowledge incrementally without retaining any old samples. Recently, the framework based on parallel one-class classifiers (POC), which trains a…

Cardinality estimation is a fundamental but long unresolved problem in query optimization. Recently, multiple papers from different research groups consistently report that learned models have the potential to replace existing cardinality…

Deformable shape representations, parameterized by deformations relative to a given template, have proven effective for improved image analysis tasks. However, their broader applicability is hindered by two major challenges. First, existing…

Evaluating image captions typically relies on reference captions, which are costly to obtain and exhibit significant diversity and subjectivity. While reference-free evaluation metrics have been proposed, most focus on cross-modal…

Active Learning (AL) methods have proven cost-saving against passive supervised methods in many application domains. An active learner, aiming to find some target hypothesis, formulates sequential queries to some oracle. The set of…

Despite recent successes, test-time scaling - i.e., dynamically expanding the token budget during inference as needed - remains brittle for vision-language models (VLMs): unstructured chains-of-thought about images entangle perception and…

Concept Bottleneck Models (CBMs) offer inherent interpretability by initially translating images into human-comprehensible concepts, followed by a linear combination of these concepts for classification. However, the annotation of concepts…

Video contrastive learning (V-CL) has emerged as a popular framework for unsupervised video representation learning, demonstrating strong results in tasks such as action classification and detection. Yet, to harness these benefits, it is…

Foundation models for vision have transformed visual recognition with powerful pretrained representations and strong zero-shot capabilities, yet their potential for data-efficient learning remains largely untapped. Active Learning (AL) aims…

Compositional Zero-Shot Learning (CZSL) aims to recognize novel attribute-object compositions by leveraging knowledge from seen compositions. Current methods align textual prototypes with visual features via Vision-Language Models (VLMs),…

In our work, we explore the synergistic capabilities of pre-trained vision-and-language models (VLMs) and large language models (LLMs) on visual commonsense reasoning (VCR) problems. We find that VLMs and LLMs-based decision pipelines are…

Large Language Models (LLMs) have recently achieved strong performance in software code generation. However, applying them to hardware description languages (HDLs), such as Verilog, remains challenging because high-quality training data are…

Semantic segmentation is a fundamental task in computer vision, which can be considered as a per-pixel classification problem. Recently, although fully convolutional neural network (FCN) based approaches have made remarkable progress in…