Related papers: PromptAD: Learning Prompts with only Normal Sample…

Prompt learning has proven effective in adapting vision language models for downstream tasks. However, existing methods usually append learnable prompt tokens solely with the category names to obtain textual features, which fails to fully…

Unsupervised reconstruction networks using self-attention transformers have achieved state-of-the-art performance for multi-class (unified) anomaly detection with a single model. However, these self-attention reconstruction models primarily…

Video anomaly detection under weak supervision presents significant challenges, particularly due to the lack of frame-level annotations during training. While prior research has utilized graph convolution networks and self-attention…

Pre-trained vision-language models (VLMs) have shown remarkable generalization capabilities via prompting, which leverages VLMs as knowledge bases to extract information beneficial for downstream tasks. However, existing methods primarily…

Prompt-driven image analysis converts a single natural-language instruction into multiple steps: locate, segment, edit, and describe. We present a practical case study of a unified pipeline that combines open-vocabulary detection,…

Few-shot semantic segmentation aims to segment novel-class objects in a given query image with only a few labeled support images. Most advanced solutions exploit a metric learning framework that performs segmentation through matching each…

For downstream applications of vision-language pre-trained models, there has been significant interest in constructing effective prompts. Existing works on prompt engineering, which either require laborious manual designs or optimize the…

We study few-shot acoustic event detection (AED) in this paper. Few-shot learning enables detection of new events with very limited labeled data. Compared to other research areas like computer vision, few-shot learning for audio recognition…

Anomaly detection is a critical and challenging task that aims to identify data points deviating from normal patterns and distributions within a dataset. Various methods have been proposed using a one-class-one-model approach, but these…

From a safety perspective, a machine learning method embedded in real-world applications is required to distinguish irregular situations. For this reason, there has been a growing interest in the anomaly detection (AD) task. Since we cannot…

Pixel-wise annotations are notoriously labourious and costly to obtain in the medical domain. To mitigate this burden, weakly supervised approaches based on bounding box annotations-much easier to acquire-offer a practical alternative.…

Few-shot semantic segmentation aims to segment objects from previously unseen classes using only a limited number of labeled examples. In this paper, we introduce Label Anything, a novel transformer-based architecture designed for…

Prompt learning is an effective method to customize Vision-Language Models (VLMs) for various downstream tasks, involving tuning very few parameters of input prompt tokens. Recently, prompt pretraining in large-scale dataset (e.g.,…

Over-prompting, a phenomenon where excessive examples in prompts lead to diminished performance in Large Language Models (LLMs), challenges the conventional wisdom about in-context few-shot learning. To investigate this few-shot dilemma, we…

In practice, machine learning methods commonly require anomaly detection (AD) to filter inputs or detect distributional shifts. Typically, this is implemented by running a separate AD model alongside the primary model. However, this…

Prompt-based learning, with its capability to tackle zero-shot and few-shot NLP tasks, has gained much attention in community. The main idea is to bridge the gap between NLP downstream tasks and language modeling (LM), by mapping these…

Vision-language models (VLMs), such as CLIP, have shown strong generalization under zero-shot settings, yet adapting them to downstream tasks with limited supervision remains a significant challenge. Existing multi-modal prompt learning…

Out-of-distribution (OOD) detection attempts to distinguish outlier samples to prevent models trained on the in-distribution (ID) dataset from producing unavailable outputs. Most OOD detection methods require many IID samples for training,…

Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…

Zero-shot anomaly detection (ZSAD) aims to detect anomalies without any target domain training samples, relying solely on external auxiliary data. Existing CLIP-based methods attempt to activate the model's ZSAD potential via handcrafted or…