Zero-shot anomaly detection (ZSAD) methods detect anomalies without prior access to known normal or abnormal samples within target categories. Existing methods typically rely on pretrained multimodal models, computing similarities between manually crafted textual features representing ''normal'' or ''abnormal'' semantics and image patch features to detect anomalies. However, the generic descriptions of ''abnormal'' often fail to precisely match diverse types of anomalies across different object categories. Additionally, computing feature similarities for single patches struggles to pinpoint specific locations of anomalies with various sizes and scales. To address these issues, we propose a novel ZSAD method called FiLo, comprising two components: adaptively learned Fine-Grained Description (FG-Des) and position-enhanced High-Quality Localization (HQ-Loc). FG-Des introduces fine-grained anomaly descriptions for each category using Large Language Models (LLMs) and employs adaptively learned textual templates to enhance the accuracy and interpretability of anomaly detection. HQ-Loc, utilizing Grounding DINO for preliminary localization, position-enhanced text prompts, and Multi-scale Multi-shape Cross-modal Interaction (MMCI) module, facilitates more accurate localization of anomalies of different sizes and shapes. Experimental results on datasets like MVTec and VisA demonstrate that FiLo significantly improves the performance of ZSAD in both detection and localization, achieving state-of-the-art performance with an image-level AUC of 83.9% and a pixel-level AUC of 95.9% on the VisA dataset. Code is available at https://github.com/CASIA-IVA-Lab/FiLo.

Feature extraction and representation is one of the most important components for fast, accurate, and robust visual tracking. Very deep convolutional neural networks (CNNs) provide effective tools for feature extraction with good generalization ability. However, extracting features using very deep CNN models needs high performance hardware due to its large computation complexity, which prohibits its extensions in real-time applications. To alleviate this problem, we aim at obtaining small and fast-to-execute shallow models based on model compression for visual tracking. Specifically, we propose a small feature distilled network (FDN) for tracking by imitating the intermediate representations of a much deeper network. The FDN extracts rich visual features with higher speed than the original deeper network. To further speed-up, we introduce a shift-and-stitch method to reduce the arithmetic operations, while preserving the spatial resolution of the distilled feature maps unchanged. Finally, a scale adaptive discriminative correlation filter is learned on the distilled feature for visual tracking to handle scale variation of the target. Comprehensive experimental results on object tracking benchmark datasets show that the proposed approach achieves 5× speed-up with competitive performance to the state-of-the-art deep trackers.

Correlation filter has been demonstrated remarkable success for visual tracking recently. However, most existing methods often face model drift caused by several factors, such as unlimited boundary effect, heavy occlusion, fast motion, and distracter perturbation. To address the issue, this paper proposes a unified dynamic collaborative tracking framework that can perform more flexible and robust position prediction. Specifically, the framework learns the object appearance model by jointly training the objective function with three components: target regression submodule, distracter suppression submodule, and maximum margin relation submodule. The first submodule mainly takes advantage of the circulant structure of training samples to obtain the distinguishing ability between the target and its surrounding background. The second submodule optimizes the label response of the possible distracting region close to zero for reducing the peak value of the confidence map in the distracting region. Inspired by the structure output support vector machines, the third submodule is introduced to utilize the differences between target appearance representation and distracter appearance representation in the discriminative mapping space for alleviating the disturbance of the most possible hard negative samples. In addition, a CUR filter as an assistant detector is embedded to provide effective object candidates for alleviating the model drift problem. Comprehensive experimental results show that the proposed approach achieves the state-of-the-art performance in several public benchmark data sets.

Semantic image synthesis aims to generate images from given semantic layouts, which is a challenging task that requires training models to capture the relationship between layouts and images. Previous works are usually based on Generative Adversarial Networks (GAN) or autoregressive (AR) models. However, the GAN model's training process is unstable, and the AR model’s performance is seriously affected by the independent image encoder and the unidirectional generation bias. Due to the above limitations, these methods tend to synthesize unrealistic, poorly aligned images and only consider single-style image generation. In this paper, we propose a Multi-model Style-aware Diffusion Learning (MSDL) framework for semantic image synthesis, including a training module and a sampling module. In the training module, a layout-to-image model is introduced to transfer the learned knowledge from a model pretrained with massive weak correlated text-image pairs data, making the training process more efficient. In the sampling module, we designed a map-guidance technique and creatively designed a multi-model style-guidance strategy for creating images in multiple styles, e.g., oil painting, Disney Cartoon, and pixel style. We evaluate our method on Cityscapes, ADE20K, and COCO-Stuff, making visual comparisons and computing with multiple metrics such as FID, LPIPS, etc. Experimental results demonstrate that our model is highly competitive, especially in terms of fidelity and diversity.

This paper investigates the potential of dual CNN-transformer architectures for Generalizable Few-Shot Anomaly Detection (GFSAD), a practical yet understudied form of anomaly detection (AD). In GFSAD, a common model must be learned and shared across several categories, while simultaneously ensuring that the model is adaptable to new categories with a restricted number of normal images. While CNN-transformer architectures obtain high success in many vision tasks, the potential of CNN-transformer architectures in GFSAD is still to be discovered. In this paper, we introduce ADFormer, a dual CNN-transformer architecture that combines the strengths of CNNs and transformers, with the aim of learning discriminative features that have both local and global receptive fields. We also incorporate a self-supervised bipartite matching approach in ADFormer that reconstructs query images from support images, followed by detecting anomalies based on the high loss in reconstruction. Additionally, we present a consistency-enhanced loss to enhance the spatial and semantic consistency of features, thereby reducing the dependence on a large AD dataset for training. Experimental results show that ADFormer with consistency-enhanced loss significantly improves GFSAD performance. Compared to other anomaly detection methods, ADFormer outperforms considerably on the MVTec AD, MPDD, and VisA datasets.