Related papers: Contextuality Helps Representation Learning for Ge…

In-context learning enables language models (LM) to adapt to downstream data or tasks by incorporating few samples as demonstrations within the prompts. It offers strong performance without the expense of fine-tuning. However, the…

Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to supervised learning tasks remains as a challenge in…

Category discovery methods aim to find novel categories in unlabeled visual data. At training time, a set of labeled and unlabeled images are provided, where the labels correspond to the categories present in the images. The labeled data…

Image recognition is a classic and common task in the computer vision field, which has been widely applied in the past decade. Most existing methods in literature aim to learn discriminative features from labeled images for classification,…

Causal discovery algorithms aim at untangling complex causal relationships from data. Here, we study causal discovery and inference methods based on staged tree models, which can represent complex and asymmetric causal relationships between…

Learning causal structure from observational data is a fundamental challenge in machine learning. However, the majority of commonly used differentiable causal discovery methods are non-identifiable, turning this problem into a continuous…

Learning robust contextual knowledge from unlabeled videos is essential for advancing self-supervised tracking. However, conventional self-supervised trackers lack effective context modeling, while existing context association methods based…

Contextual information plays an important role in many computer vision tasks, such as object detection, video action detection, image classification, etc. Recognizing a single object or action out of context could be sometimes very…

Learning decent representations from unlabeled time-series data with temporal dynamics is a very challenging task. In this paper, we propose an unsupervised Time-Series representation learning framework via Temporal and Contextual…

Despite their consistent performance improvements, cross-modal retrieval models (e.g., CLIP) show degraded performances with retrieving keys composed of fused image-text modality (e.g., Wikipedia pages with both images and text). To address…

Deep learning methods have shown promise in unsupervised domain adaptation, which aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain with a different distribution. However, such methods typically…

Deep neural network models have achieved remarkable progress in 3D scene understanding while trained in the closed-set setting and with full labels. However, the major bottleneck is that these models do not have the capacity to recognize…

Image retrieval from contextual descriptions (IRCD) aims to identify an image within a set of minimally contrastive candidates based on linguistically complex text. Despite the success of VLMs, they still significantly lag behind human…

Deep neural networks have achieved state-of-the-art performance in a wide range of recognition/classification tasks. However, when applying deep learning to real-world applications, there are still multiple challenges. A typical challenge…

Multi-view clustering can explore common semantics from multiple views and has attracted increasing attention. However, existing works punish multiple objectives in the same feature space, where they ignore the conflict between learning…

We consider the problem of discovering novel object categories in an image collection. While these images are unlabelled, we also assume prior knowledge of related but different image classes. We use such prior knowledge to reduce the…

Large language models (LLMs) excel at a range of tasks through in-context learning (ICL), where only a few task examples guide their predictions. However, prior research highlights that LLMs often overlook input-label mapping information in…

Cross-modal retrieval methods have been significantly improved in last years with the use of deep neural networks and large-scale annotated datasets such as ImageNet and Places. However, collecting and annotating such datasets requires a…

In this paper, we study the problem of Novel Class Discovery (NCD). NCD aims at inferring novel object categories in an unlabeled set by leveraging from prior knowledge of a labeled set containing different, but related classes. Existing…

During the past decade, deep neural networks have led to fast-paced progress and significant achievements in computer vision problems, for both academia and industry. Yet despite their success, state-of-the-art image classification…