Search Results for author:
Found 15 papers, 5 papers with code
Multimodal Industrial Anomaly Detection by Crossmodal Reverse Distillation
Anomalies in one modality may not be effectively captured in the fused teacher features, leading to detection failures.
Unlocking the Potential of Reverse Distillation for Anomaly Detection
Knowledge Distillation (KD) is a promising approach for unsupervised Anomaly Detection (AD).
Ranked #4 on
Anomaly Detection
on BTAD
(using extra training data)
Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection
In DMDD, a Decouple Student-Teacher Network is proposed to decouple the initial student features into normality and abnormality features.
Unifying Visual Perception by Dispersible Points Learning
The method, called UniHead, views different visual perception tasks as the dispersible points learning via the transformer encoder architecture.
Self-slimmed Vision Transformer
Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation.
RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection
Moreover, semantics from non-adjacent levels are diluted in the feature pyramid since only features at adjacent pyramid levels are merged by the local fusion operation in a sequence manner.
Self-Slimming Vision Transformer
Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation.
RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes
We introduce RaidaR, a rich annotated image dataset of rainy street scenes, to support autonomous driving research.
KPNet: Towards Minimal Face Detector
The small receptive field and capacity of minimal neural networks limit their performance when using them to be the backbone of detectors.
Rethinking Loss Design for Large-scale 3D Shape Retrieval
In this paper, we propose the Collaborative Inner Product Loss (CIP Loss) to obtain ideal shape embedding that discriminative among different categories and clustered within the same class.
Angular Triplet-Center Loss for Multi-view 3D Shape Retrieval
How to obtain the desirable representation of a 3D shape, which is discriminative across categories and polymerized within classes, is a significant challenge in 3D shape retrieval.
Learning Discriminative 3D Shape Representations by View Discerning Networks
In this network, a Score Generation Unit is devised to evaluate the quality of each projected image with score vectors.
Beyond Trade-off: Accelerate FCN-based Face Detector with Higher Accuracy
Fully convolutional neural network (FCN) has been dominating the game of face detection task for a few years with its congenital capability of sliding-window-searching with shared kernels, which boiled down all the redundant calculation, and most recent state-of-the-art methods such as Faster-RCNN, SSD, YOLO and FPN use FCN as their backbone.
Region-based Quality Estimation Network for Large-scale Person Re-identification
One of the major restrictions on the performance of video-based person re-id is partial noise caused by occlusion, blur and illumination.
Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization
Based on GoogLeNet, firstly, a set of mid-level attribute features are discovered by novelly designed detection layers, where a max-pooling based weakly-supervised object detection technique is used to train these layers with only image-level labels without the need of bounding box annotations of pedestrian attributes.
