Related papers: Transferable and Principled Efficiency for Open-Vo…

Most existing underwater instance segmentation approaches are constrained by close-vocabulary prediction, limiting their ability to recognize novel marine categories. To support evaluation, we introduce \textbf{MARIS} (\underline{Mar}ine…

The deployment of vision-language models remains constrained by substantial computational requirements. We present \textbf{FrEVL}, a framework exploring whether frozen pretrained embeddings can support effective vision-language…

Despite the excellent performance of vision-language pre-trained models (VLPs) on conventional VQA task, they still suffer from two problems: First, VLPs tend to rely on language biases in datasets and fail to generalize to…

This paper delves into the challenges of achieving scalable and effective multi-object modeling for semi-supervised Video Object Segmentation (VOS). Previous VOS methods decode features with a single positive object, limiting the learning…

Open-vocabulary semantic segmentation enables models to identify novel object categories beyond their training data. While this flexibility represents a significant advancement, current approaches still rely on manually specified class…

Vision-language (VL) pre-training has recently gained much attention for its transferability and flexibility in novel concepts (e.g., cross-modality transfer) across various visual tasks. However, VL-driven segmentation has been…

The aim of audio-visual segmentation (AVS) is to precisely differentiate audible objects within videos down to the pixel level. Traditional approaches often tackle this challenge by combining information from various modalities, where the…

Recent vision-language pre-trained models (VL-PTMs) have shown remarkable success in open-vocabulary tasks. However, downstream use cases often involve further fine-tuning of VL-PTMs, which may distort their general knowledge and impair…

Open-Vocabulary Video Instance Segmentation (VIS) is attracting increasing attention due to its ability to segment and track arbitrary objects. However, the recent Open-Vocabulary VIS attempts obtained unsatisfactory results, especially in…

Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer. We evaluate the method on various vertical domains and…

Despite the impressive performance recently achieved by automatic speech recognition (ASR), we observe two primary challenges that hinder its broader applications: (1) The difficulty of introducing scalability into the model to support more…

Segmentation models exhibit significant vulnerability to adversarial examples in white-box settings, but existing adversarial attack methods often show poor transferability across different segmentation models. While some researchers have…

Retrieval-augmented models have proven to be effective in natural language processing tasks, yet there remains a lack of research on their optimization using variational inference. We introduce the Variational Open-Domain (VOD) framework…

Fine-tuning pre-trained vision-language models has emerged as a powerful approach for enhancing open-vocabulary semantic segmentation (OVSS). However, the substantial computational and resource demands associated with training on large…

A common problem for automatic speech recognition systems is how to recognize words that they did not see during training. Currently there is no established method of evaluating different techniques for tackling this problem. We propose…

Names are essential to both human cognition and vision-language models. Open-vocabulary models utilize class names as text prompts to generalize to categories unseen during training. However, the precision of these names is often overlooked…

The challenge of open-vocabulary recognition lies in the model has no clue of new categories it is applied to. Existing works have proposed different methods to embed category cues into the model, \eg, through few-shot fine-tuning,…

Why do pretrained diffusion or flow-matching policies fail when the same task is performed near an obstacle, on a shifted support surface, or amid mild clutter? Such failures rarely reflect missing motor skills; instead, they expose a…

Semantic segmentation is an extensively studied task in computer vision, with numerous methods proposed every year. Thanks to the advent of deep learning in semantic segmentation, the performance on existing benchmarks is close to…

Pretraining with large-scale 3D volumes has a potential for improving the segmentation performance on a target medical image dataset where the training images and annotations are limited. Due to the high cost of acquiring pixel-level…