Search Results for author:
Found 18 papers, 11 papers with code
Foundation Model Assisted Weakly Supervised Semantic Segmentation
This work aims to leverage pre-trained foundation models, such as contrastive language-image pre-training (CLIP) and segment anything model (SAM), to address weakly supervised semantic segmentation (WSSS) using image-level labels.
Learning Intra and Inter-Camera Invariance for Isolated Camera Supervised Person Re-identification
To eliminate the confounding effect of camera bias, we propose to learn both intra- and inter-camera invariance under a unified framework.
Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification
Although prompt learning has enabled a recent work named CLIP-ReID to achieve promising performance, the underlying mechanisms and the necessity of prompt learning remain unclear due to the absence of semantic labels in ReID tasks.
Ranked #1 on
Unsupervised Vehicle Re-Identification
on VeRi-776
Contrastive Learning
Unsupervised Person Re-Identification
+1
Long-Short Temporal Co-Teaching for Weakly Supervised Video Anomaly Detection
That is, clip-level pseudo labels generated from each network are used to supervise the other one at the next training round, and the two networks are learned alternatively and iteratively.
Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detection
In this work, we propose a hierarchical semantic contrast (HSC) method to learn a scene-aware VAD model from normal videos.
Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification
To this end, we build a dual-branch network architecture based upon a modified Vision Transformer (ViT).
Online Convolutional Re-parameterization
Structural re-parameterization has drawn increasing attention in various computer vision tasks.
Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification
Assisted with the camera-aware proxies, we design two proxy-level contrastive learning losses that are, respectively, based on offline and online association results.
PENet: Towards Precise and Efficient Image Guided Depth Completion
More specifically, one branch inputs a color image and a sparse depth map to predict a dense depth map.
Ranked #3 on
Depth Completion
on KITTI Depth Completion
Self-supervised Visual-LiDAR Odometry with Flip Consistency
To this end, we design a self-supervised visual-lidar odometry (Self-VLO) framework.
Camera-aware Proxies for Unsupervised Person Re-Identification
These camera-aware proxies enable us to deal with large intra-ID variance and generate more reliable pseudo labels for learning.
Towards Precise Intra-camera Supervised Person Re-identification
Our approach performs even comparable to state-of-the-art fully supervised methods in two of the datasets.
Saliency Guided Self-attention Network for Weakly and Semi-supervised Semantic Segmentation
Weakly supervised semantic segmentation (WSSS) using only image-level labels can greatly reduce the annotation cost and therefore has attracted considerable research interest.
Ranked #35 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
(using extra training data)
Adaptive Fusion for RGB-D Salient Object Detection
RGB-D salient object detection aims to identify the most visually distinctive objects in a pair of color and depth images.
Deep Active Learning for Video-based Person Re-identification
With the gained annotations of the actively selected candidates, the tracklets' pesudo labels are updated by label merging and further used to re-train our re-ID model.
Saliency Guided End-to-End Learning for Weakly Supervised Object Detection
To address this issue, this paper integrates saliency into a deep architecture, in which the location in- formation is explored both explicitly and implicitly.
Saliency Guided Dictionary Learning for Weakly-Supervised Image Parsing
In this paper, we propose a novel method to perform weakly-supervised image parsing based on the dictionary learning framework.
Fusion Based Holistic Road Scene Understanding
This paper addresses the problem of holistic road scene understanding based on the integration of visual and range data.
