Related papers: Semantic Anchor Transport: Robust Test-Time Adapta…

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…

Vision-language models (VLMs) excel in zero-shot recognition but their performance varies greatly across different visual concepts. For example, although CLIP achieves impressive accuracy on ImageNet (60-80%), its performance drops below…

Weakly Supervised Semantic Segmentation (WSSS) using only image-level labels has gained significant attention due to its cost-effectiveness. The typical framework involves using image-level labels as training data to generate pixel-level…

Can in-context learning (ICL) override pre-trained label semantics, or does it merely refine an existing semantic backbone? We address this question by treating LLMs as prompt-induced classifiers and contrasting their behavior under…

Deep clustering, which learns representation and semantic clustering without labels information, poses a great challenge for deep learning-based approaches. Despite significant progress in recent years, most existing methods focus on…

Combining multiple object detection datasets offers a path to improved generalisation but is hindered by inconsistencies in class semantics and bounding box annotations. Some methods to address this assume shared label taxonomies and…

State-of-the-art empirical work has shown that visual representations learned by deep neural networks are robust in nature and capable of performing classification tasks on diverse datasets. For example, CLIP demonstrated zero-shot transfer…

Vision-Language Models (VLMs) have shown strong performance in zero-shot image classification tasks. However, existing methods, including Contrastive Language-Image Pre-training (CLIP), all rely on annotated text-to-image pairs for aligning…

Large-scale web-crawled datasets are fundamental for the success of pre-training vision-language models, such as CLIP. However, the inherent noise and potential irrelevance of web-crawled AltTexts pose challenges in achieving precise…

Establishing dense correspondences across semantically similar images remains a challenging task due to the significant intra-class variations and background clutters. Traditionally, a supervised learning was used for training the models,…

Vision language models such as CLIP have shown remarkable performance in zero shot classification, but remain susceptible to spurious correlations, where irrelevant visual features influence predictions. Existing debiasing methods often…

A fundamental reason for the dominance of attention over RNNs and LSTMs in LLMs is its ability to capture long-range dependencies by modeling direct interactions between all tokens, overcoming the sequential limitations of recurrent…

Training deep generative models usually requires a large amount of data. To alleviate the data collection cost, the task of zero-shot GAN adaptation aims to reuse well-trained generators to synthesize images of an unseen target domain…

Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biases. Existing post-hoc debiasing methods often operate…

Semi-supervised learning (SSL) is a widely used technique in scenarios where labeled data is scarce and unlabeled data is abundant. While SSL is popular for image and text classification, it is relatively underexplored for the task of…

The lack of labeled data is a common challenge in speech classification tasks, particularly those requiring extensive subjective assessment, such as cognitive state classification. In this work, we propose a Semi-Supervised Learning (SSL)…

Unsupervised adaptation of CLIP-based vision-language models (VLMs) for fine-grained image classification requires sensitivity to microscopic local cues. While CLIP exhibits strong zero-shot transfer, its reliance on coarse global features…

Learning with noisy labels (LNL) poses a significant challenge in training a well-generalized model while avoiding overfitting to corrupted labels. Recent advances have achieved impressive performance by identifying clean labels and…

Recently, the contrastive language-image pre-training, e.g., CLIP, has demonstrated promising results on various downstream tasks. The pre-trained model can capture enriched visual concepts for images by learning from a large scale of…

General-purpose AI models, particularly those designed for text and vision, demonstrate impressive versatility across a wide range of deep-learning tasks. However, they often underperform in specialised domains like medical imaging, where…