Related papers: Instance-Level Generation for Representation Learn…

The ability to recognize patterns from examples and apply them to new ones is a primal ability for general intelligence, and is widely studied by psychology and AI researchers. Many benchmarks have been proposed to measure such ability for…

Automatic generation of executable Blender code from natural language remains challenging, with state-of-the-art LLMs producing frequent syntactic errors and geometrically inconsistent objects. We present BlenderRAG, a retrieval-augmented…

Diffusion models excel at photorealistic synthesis but struggle with precise object counts, especially in high-density settings. We introduce COUNTLOOP, a training-free framework that achieves precise instance control through iterative,…

Large language models (LLMs) have shown impressive in-context learning (ICL) ability in code generation. LLMs take a prompt consisting of requirement-code examples and a new requirement as input, and output new programs. Existing studies…

Different from the traditional supervised learning in which each training example has only one explicit label, superset label learning (SLL) refers to the problem that a training example can be associated with a set of candidate labels, and…

Most object-level mapping systems in use today make use of an upstream learned object instance segmentation model. If we want to teach them about a new object or segmentation class, we need to build a large dataset and retrain the system.…

A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data. In this work, we introduce a new training strategy,…

Many real-world visual recognition use-cases can not directly benefit from state-of-the-art CNN-based approaches because of the lack of many annotated data. The usual approach to deal with this is to transfer a representation pre-learned on…

Instance segmentation has gained recently huge attention in various computer vision applications. It aims at providing different IDs to different object of the scene, even if they belong to the same class. This is useful in various…

Named entity recognition often fails in idiosyncratic domains. That causes a problem for depending tasks, such as entity linking and relation extraction. We propose a generic and robust approach for high-recall named entity recognition. Our…

Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data. Traditional fully supervised…

The availability of data is limited in some fields, especially for object detection tasks, where it is necessary to have correctly labeled bounding boxes around each object. A notable example of such data scarcity is found in the domain of…

Domain adaptation aims to transfer the knowledge learned on (data-rich) source domains to (low-resource) target domains, and a popular method is invariant representation learning, which matches and aligns the data distributions on the…

Large language models (LLMs) are increasingly applied to sequential decision-making through in-context learning (ICL), yet their effectiveness is highly sensitive to prompt quality. Effective prompts should meet three principles: focus on…

Visual object localization is the key step in a series of object detection tasks. In the literature, high localization accuracy is achieved with the mainstream strongly supervised frameworks. However, such methods require object-level…

Learning representations for individual instances when only bag-level labels are available is a fundamental challenge in multiple instance learning (MIL). Recent works have shown promising results using contrastive self-supervised learning…

In this paper, we present a novel approach for object recognition in real-time by employing multilevel feature analysis and demonstrate the practicality of adapting feature extraction into a Naive Bayesian classification framework that…

In the field of emotion recognition, the development of high-performance models remains a challenge due to the scarcity of high-quality, diverse emotional datasets. Emotional expressions are inherently subjective, shaped by individual…

We propose a new and, arguably, a very simple reduction of instance segmentation to semantic segmentation. This reduction allows to train feed-forward non-recurrent deep instance segmentation systems in an end-to-end fashion using…

This work introduces a new task of instance-incremental scene graph generation: Given a scene of the point cloud, representing it as a graph and automatically increasing novel instances. A graph denoting the object layout of the scene is…