Jingbo Xia

Tingfeng Huang, Weijia Kong, Yuxuan Cheng et al.

In unsupervised image anomaly detection, reconstruction methods aim to train models to capture normal patterns comprehensively for normal data reconstruction. Yet, these models sometimes retain unintended reconstruction capacity for anomalous regions during inference, leading to missed detections. To mitigate this issue, existing works perturb normal samples in a sample-agnostic manner, uniformly adding noise across spatial locations before reconstructing the original. Despite promising results, they disregard the fact that foreground locations are inherently more critical for robust reconstruction. Motivated by this, we present a novel reconstruction framework named Attention-Guided Perturbation Network (AGPNet) for industrial anomaly detection. Its core idea is to add perturbations guided by a sample-aware attention mask to improve the learning of invariant normal patterns at important locations. AGPNet consists of two branches, \ie, a reconstruction branch and an auxiliary attention-based perturbation one. The reconstruction branch learns to reconstruct normal samples, while the auxiliary one aims to produce attention masks to guide the noise perturbation process for normal samples. By perturbing more aggressively at those important regions, we encourage the reconstruction branch to learn inherent normal patterns both comprehensively and robustly. Extensive experiments are conducted on several popular benchmarks covering MVTec-AD, VisA, and MVTec-3D, and show that AGPNet consistently obtains leading anomaly detection performance across a variety of setups, including few-shot, one-class, and multi-class ones.

Xinwei He, Yansong Zheng, Qianru Han et al.

Vision foundation models have shown great promise for open-set 3D object retrieval (3DOR) through efficient adaptation to multi-view images. Leveraging semantically aligned latent space, previous work typically adapts the CLIP encoder to build view-based 3D descriptors. Despite CLIP's strong generalization ability, its lack of fine-grainedness prompted us to explore the potential of a more recent self-supervised encoder-DINO. To address this, we propose DINO Eats CLIP (DEC), a novel framework for dynamic multi-view integration that is regularized by synthesizing data for unseen classes. We first find that simply mean-pooling over view features from a frozen DINO backbone gives decent performance. Yet, further adaptation causes severe overfitting on average view patterns of known classes. To combat it, we then design a module named Chunking and Adapting Module (CAM). It segments multi-view images into chunks and dynamically integrates local view relations, yielding more robust features than the standard pooling strategy. Finally, we propose Virtual Feature Synthesis (VFS) module to mitigate bias towards known categories explicitly. Under the hood, VFS leverages CLIP's broad, pre-aligned vision-language space to synthesize virtual features for unseen classes. By exposing DEC to these virtual features, we greatly enhance its open-set discrimination capacity. Extensive experiments on standard open-set 3DOR benchmarks demonstrate its superior efficacy.