Person search aims to localize a person of interest in a large image gallery captured by multiple, non-overlapping cameras. Prevalent unified methods have suffered from (1) noisy proposals with mis-detection and occlusion, and (2) large appearance variation within a class, which deteriorates the prototype-based metric learning. To address these problems, we introduce a Prototype-guided Attention Distillation, shortly PAD, which exploits a prototype (a typical representation of an identity) as a guidance to the attention module to consistently highlight identity-inherent regions across different poses. To utilize the knowledge encoded in prototypes for matching unseen IDs, PAD conducts attention distillation to guide student Re-ID queries by deeply mimicking attention maps from the prototype query. Additionally, to address large intra-class variation induced by pose or camera views, we extend PAD with multiple part prototypes representing consistent local regions across different instances. Furthermore, we exploit an adaptive momentum strategy for robust attention distillation in PAD to update more distinct prototypes. Extensive experiments conducted on CUHK-SYSU and PRW demonstrate the effectiveness of PAD, showcasing state-of-the-art performance. Moreover, our distilled attention surprisingly highlights distinguished multiple regions for person search.

Compositional zero-shot learning (CZSL) aims to recognize unseen compositions with prior knowledge of known primitives (attribute and object). Previous works for CZSL often suffer from grasping the contextuality between attribute and object, as well as the discriminability of visual features, and the long-tailed distribution of real-world compositional data. We propose a simple and scalable framework called Composition Transformer (CoT) to address these issues. CoT employs object and attribute experts in distinctive manners to generate representative embeddings, using the visual network hierarchically. The object expert extracts representative object embeddings from the final layer in a bottom-up manner, while the attribute expert makes attribute embeddings in a top-down manner with a proposed object-guided attention module that models contextuality explicitly. To remedy biased prediction caused by imbalanced data distribution, we develop a simple minority attribute augmentation (MAA) that synthesizes virtual samples by mixing two images and oversampling minority attribute classes. Our method achieves SoTA performance on several benchmarks, including MIT-States, C-GQA, and VAW-CZSL. We also demonstrate the effectiveness of CoT in improving visual discrimination and addressing the model bias from the imbalanced data distribution. The code is available at https://github.com/HanjaeKim98/CoT.

Weakly supervised Video Anomaly Detection (wVAD) aims to distinguish anomalies from normal events based on video-level supervision. Most existing works utilize Multiple Instance Learning (MIL) with ranking loss to tackle this task. These methods, however, rely on noisy predictions from a MIL-based classifier for target instance selection in ranking loss, degrading model performance. To overcome this problem, we propose Normality Guided Multiple Instance Learning (NG-MIL) framework, which encodes diverse normal patterns from noise-free normal videos into prototypes for constructing a similarity-based classifier. By ensembling predictions of two classifiers, our method could refine the anomaly scores, reducing training instability from weak labels. Moreover, we introduce normality clustering and normality guided triplet loss constraining inner bag instances to boost the effect of NG-MIL and increase the discriminability of classifiers. Extensive experiments on three public datasets (ShanghaiTech, UCF-Crime, XD-Violence) demonstrate that our method is comparable to or better than existing weakly supervised methods, achieving state-of-the-art results.

Object detection in aerial images has achieved remarkable progress with the advent of deep convolutional neural networks (CNNs). It is, however, still a challenging task since the objects in aerial images are arbitrarily oriented and often densely packed. In this letter, we propose a novel method for oriented object detection in aerial images that represents objects as rotation equivariant semantic keypoints. Unlike conventional methods that represent object rotation according to angles from each axis in the Cartesian coordinate system, we represent object using a canonical orientation to ensure rotation equivariance. We accomplish this by representing an object as semantic keypoints, where each keypoint of the object consistently corresponds to the semantic part, regardless of rotation variation. To this end, we define the “head” point of the object as the canonical orientation and the remaining bounding box vectors as semantic keypoints in clockwise order. To discriminate visual attributes between different categories, we further use category-specific semantic keypoints, so that object classification and localization can be jointly solved in a cooperative manner. Our experiments demonstrate the effectiveness of rotation equivariant semantic keypoints on oriented object detection.

Existing person search methods integrate person detection and re-identification (re-ID) module into a unified system. Though promising results have been achieved, the misalignment problem, which commonly occurs in person search, limits the discriminative feature representation for re-ID. To overcome this limitation, we introduce a novel framework to learn the discriminative representation by utilizing prototype in OIM loss. Unlike conventional methods using prototype as a representation of person identity, we utilize it as guidance to allow the attention network to consistently highlight multiple instances across different poses. Moreover, we propose a new prototype update scheme with adaptive momentum to increase the discriminative ability across different instances. Extensive ablation experiments demonstrate that our method can significantly enhance the feature discriminative power, outperforming the state-of-the-art results on two person search benchmarks including CUHK-SYSU and PRW.

Existing techniques to encode spatial invariance within deep convolutional neural networks only model 2D transformation fields. This does not account for the fact that objects in a 2D space are a projection of 3D ones, and thus they have limited ability to severe object viewpoint changes. To overcome this limitation, we introduce a learnable module, cylindrical convolutional networks (CCNs), that exploit cylindrical representation of a convolutional kernel defined in the 3D space. CCNs extract a view-specific feature through a view-specific convolutional kernel to predict object category scores at each viewpoint. With the view-specific feature, we simultaneously determine objective category and viewpoints using the proposed sinusoidal soft-argmax module. Our experiments demonstrate the effectiveness of the cylindrical convolutional networks on joint object detection and viewpoint estimation.

Dense object detectors that are applied over a regular, dense grid have advanced and drawn their attention in recent days. Their fully convolutional nature greatly advances the computational efficiency of object detectors compared to the two-stage detectors. However, the lack of the ability to adjust shape variation on a regular grid is still limited. In this paper we introduce a new framework, shape-adaptive kernel network, to handle spatial manipulation of input data in convolutional kernel space. At the heart of out approach is to align the original kernel space recovering shape variation of each input feature on regular grid. To this end, we propose a shape-adaptive kernel sampler to adjust dynamic convolutional kernel conditioned on input. To increase the flexibility of geometric transformation, a cascade refinement module is designed, which first estimates the global transformation grid and then estimates local offset in convolutional kernel space. Our experiments demonstrate the effectiveness of the shape-adaptive kernel network for dense object detection on various benchmarks.