Related papers: Textual Inversion for Efficient Adaptation of Open…

In this work, we propose an open-vocabulary object detection method that, based on image-caption pairs, learns to detect novel object classes along with a given set of known classes. It is a two-stage training approach that first uses a…

Visual-language pre-training has achieved remarkable success in many multi-modal tasks, largely attributed to the availability of large-scale image-text datasets. In this work, we demonstrate that Multi-modal Large Language Models (MLLMs)…

Existing Multimodal Large Language Models (MLLMs) follow the paradigm that perceives visual information by aligning visual features with the input space of Large Language Models (LLMs), and concatenating visual tokens with text tokens to…

Open-vocabulary learning has emerged as a cutting-edge research area, particularly in light of the widespread adoption of vision-based foundational models. Its primary objective is to comprehend novel concepts that are not encompassed…

Humans can visualize new and unknown concepts from their natural language description, based on their experience and previous knowledge. Insipired by this, we present a way to extend this ability to Vision-Language Models (VLMs), teaching…

Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot recognition capability, but still underperform in dense prediction tasks. Self-distillation recently is emerging as a promising approach for…

Object Goal Navigation (ObjectNav) challenges robots to find objects in unseen environments, demanding sophisticated reasoning. While Vision-Language Models (VLMs) show potential, current ObjectNav methods often employ them superficially,…

Recent advancements in large vision-language models enabled visual object detection in open-vocabulary scenarios, where object classes are defined in free-text formats during inference. In this paper, we aim to probe the state-of-the-art…

The goal of this work is to establish a scalable pipeline for expanding an object detector towards novel/unseen categories, using zero manual annotations. To achieve that, we make the following four contributions: (i) in pursuit of…

3D Visual Grounding (3DVG) aims at localizing 3D object based on textual descriptions. Conventional supervised methods for 3DVG often necessitate extensive annotations and a predefined vocabulary, which can be restrictive. To address this…

Text-to-image diffusion models have made significant advancements in generating high-quality, diverse images from text prompts. However, the inherent limitations of textual signals often prevent these models from fully capturing specific…

In this work, we tackle the limitations of current LiDAR-based 3D object detection systems, which are hindered by a restricted class vocabulary and the high costs associated with annotating new object classes. Our exploration of…

In this paper, we present LOC-ZSON, a novel Language-driven Object-Centric image representation for object navigation task within complex scenes. We propose an object-centric image representation and corresponding losses for visual-language…

Vision-language models (VLMs) are impactful in part because they can be applied to a variety of visual understanding tasks in a zero-shot fashion, without any fine-tuning. We study $\textit{generative VLMs}$ that are trained for next-word…

In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. However, existing literature has highlighted the…

Visual relationship detection aims to identify objects and their relationships in images. Prior methods approach this task by adding separate relationship modules or decoders to existing object detection architectures. This separation…

Recent advancements in Surgical Visual Question Answering (Surgical-VQA) and related region grounding have shown great promise for robotic and medical applications, addressing the critical need for automated methods in personalized surgical…

Vision-language object detectors (VLODs) such as YOLO-World and Grounding DINO exhibit strong zero-shot generalization, but their performance degrades under distribution shift. Test-time adaptation (TTA) offers a practical way to adapt…

Existing Zero-Shot Composed Image Retrieval (ZS-CIR) methods typically train adapters that convert reference images into pseudo-text tokens, which are concatenated with the modifying text and processed by frozen text encoders in pretrained…

Visual target navigation in unknown environments is a crucial problem in robotics. Despite extensive investigation of classical and learning-based approaches in the past, robots lack common-sense knowledge about household objects and…