Related papers: Weakly-supervised Semantic Parsing with Abstract E…

High annotation costs are a major bottleneck for the training of semantic segmentation systems. Therefore, methods working with less annotation effort are of special interest. This paper studies the problem of semi-supervised semantic…

Owe to the powerful generative priors, the pre-trained text-to-image (T2I) diffusion models have become increasingly popular in solving the real-world image super-resolution problem. However, as a consequence of the heavy quality…

Semantic information has been proved effective in scene text recognition. Most existing methods tend to couple both visual and semantic information in an attention-based decoder. As a result, the learning of semantic features is prone to…

Due to the costliness of labelled data in real-world applications, semi-supervised learning, underpinned by pseudo labelling, is an appealing solution. However, handling confusing samples is nontrivial: discarding valuable confusing samples…

The Abstract Meaning Representation (AMR) is a representation for open-domain rich semantics, with potential use in fields like event extraction and machine translation. Node generation, typically done using a simple dictionary lookup, is…

The de-facto approach to many vision tasks is to start from pretrained visual representations, typically learned via supervised training on ImageNet. Recent methods have explored unsupervised pretraining to scale to vast quantities of…

State-of-the-art approaches for semantic segmentation rely on deep convolutional neural networks trained on fully annotated datasets, that have been shown to be notoriously expensive to collect, both in terms of time and money. To remedy…

Neurosymbolic systems promise to combine deep neural network's (DNN) processing of raw sensor inputs with few-shot performance of symbolic artificial intelligence. Two-stage approaches explicitly decouple DNN based perception from…

The CEGAR loop in software model checking notoriously diverges when the abstraction refinement procedure does not derive a loop invariant. An abstraction refinement procedure based on an SMT solver is applied to a trace, i.e., a restricted…

Deep learning based salient object detection has recently achieved great success with its performance greatly outperforms any other unsupervised methods. However, annotating per-pixel saliency masks is a tedious and inefficient procedure.…

Despite significant advancements in post-hoc explainability techniques for neural networks, many current methods rely on heuristics and do not provide formally provable guarantees over the explanations provided. Recent work has shown that…

Learning to perform abstract reasoning often requires decomposing the task in question into intermediate subgoals that are not specified upfront, but need to be autonomously devised by the learner. In Raven Progressive Matrices (RPM), the…

Neural abstractive summarization methods often require large quantities of labeled training data. However, labeling large amounts of summarization data is often prohibitive due to time, financial, and expertise constraints, which has…

This study proposes a novel approach to using TV subtitles within a weakly supervised (WS) Automatic Speech Recognition (ASR) framework. Although TV subtitles are readily available, their imprecise alignment with corresponding audio limits…

Semantic segmentation tasks based on weakly supervised condition have been put forward to achieve a lightweight labeling process. For simple images that only include a few categories, researches based on image-level annotations have…

Recently, researches related to unsupervised disentanglement learning with deep generative models have gained substantial popularity. However, without introducing supervision, there is no guarantee that the factors of interest can be…

Vector-space word representations obtained from neural network models have been shown to enable semantic operations based on vector arithmetic. In this paper, we explore the existence of similar information on vector representations of…

Recently proposed methods for weakly-supervised semantic segmentation have achieved impressive performance in predicting pixel classes despite being trained with only image labels which lack positional information. Because image annotations…

Large Language Models (LLMs) are traditionally viewed as black-box algorithms, therefore reducing trustworthiness and obscuring potential approaches to increasing performance on downstream tasks. In this work, we apply an effective LLM…

This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, namely computational…