Related papers: CoVLM: Leveraging Consensus from Vision-Language M…

Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives. However, existing approaches are designed in supervised fashion…

Large vision-language models (VLMs) can jointly interpret images and text, but they are also prone to absorbing and reproducing harmful social stereotypes when visual cues such as age, gender, race, clothing, or occupation are present. To…

Recent advances in semi-supervised object detection (SSOD) are largely driven by consistency-based pseudo-labeling methods for image classification tasks, producing pseudo labels as supervisory signals. However, when using pseudo labels,…

In the 21st-century information age, with the development of big data technology, effectively extracting valuable information from massive data has become a key issue. Traditional data mining methods are inadequate when faced with…

Hallucinations in Multimodal Large Language Models (MLLMs) where generated responses fail to accurately reflect the given image pose a significant challenge to their reliability. To address this, we introduce ConVis, a novel training-free…

Semi-supervised learning is a challenging problem which aims to construct a model by learning from limited labeled examples. Numerous methods for this task focus on utilizing the predictions of unlabeled instances consistency alone to…

While deep-learning models have been shown to perform well on image-to-text datasets, it is difficult to use them in practice for captioning images. This is because captions traditionally tend to be context-dependent and offer complementary…

We present SelfPrompt, a novel prompt-tuning approach for vision-language models (VLMs) in a semi-supervised learning setup. Existing methods for tuning VLMs in semi-supervised setups struggle with the negative impact of the miscalibrated…

Automatic image cropping models predict reframing boxes to enhance image aesthetics. Yet, the scarcity of labeled data hinders the progress of this task. To overcome this limitation, we explore the possibility of utilizing both labeled and…

Unsupervised representation learning algorithms such as word2vec and ELMo improve the accuracy of many supervised NLP models, mainly because they can take advantage of large amounts of unlabeled text. However, the supervised models only…

The proliferation of fake news across diverse domains highlights critical limitations in current detection systems, which often exhibit narrow domain specificity and poor generalization. Existing cross-domain approaches face two key…

Human language is grounded on multimodal knowledge including visual knowledge like colors, sizes, and shapes. However, current large-scale pre-trained language models rely on text-only self-supervised training with massive text data, which…

Semi-supervised semantic segmentation requires the model to effectively propagate the label information from limited annotated images to unlabeled ones. A challenge for such a per-pixel prediction task is the large intra-class variation,…

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…

Large vision-language models (LVLMs) suffer from hallucination a lot, generating responses that apparently contradict to the image content occasionally. The key problem lies in its weak ability to comprehend detailed content in a…

Recent Vision-based Large Language Models~(VisionLLMs) for autonomous driving have seen rapid advancements. However, such promotion is extremely dependent on large-scale high-quality annotated data, which is costly and labor-intensive. To…

While deep learning strategies achieve outstanding results in computer vision tasks, one issue remains: The current strategies rely heavily on a huge amount of labeled data. In many real-world problems, it is not feasible to create such an…

In recent years, the rapid evolution of large vision-language models (LVLMs) has driven a paradigm shift in multimodal fake news detection (MFND), transforming it from traditional feature-engineering approaches to unified, end-to-end…

The proliferation of misinformation in the digital age has led to significant societal challenges. Existing approaches often struggle with capturing long-range dependencies, complex semantic relations, and the social dynamics influencing…

The rapid advancements in Large Vision Language Models (LVLMs) offer the potential to surpass conventional labeling by generating richer, more detailed descriptions of on-device human behavior understanding (HBU) in low-resolution vision…