Search Results for author: Lihe Zhang

Found 35 papers, 27 papers with code

Catastrophic Overfitting: A Potential Blessing in Disguise

no code implementations28 Feb 2024 Mengnan Zhao, Lihe Zhang, Yuqiu Kong, BaoCai Yin

To tackle this issue, we initially employ the feature activation differences between clean and adversarial examples to analyze the underlying causes of CO. Intriguingly, our findings reveal that CO can be attributed to the feature coverage induced by a few specific pathways.

Adversarial Robustness

Separable Multi-Concept Erasure from Diffusion Models

1 code implementation3 Feb 2024 Mengnan Zhao, Lihe Zhang, Tianhang Zheng, Yuqiu Kong, BaoCai Yin

Large-scale diffusion models, known for their impressive image generation capabilities, have raised concerns among researchers regarding social impacts, such as the imitation of copyrighted artistic styles.

Image Generation Machine Unlearning

EipFormer: Emphasizing Instance Positions in 3D Instance Segmentation

no code implementations9 Dec 2023 Mengnan Zhao, Lihe Zhang, Yuqiu Kong, BaoCai Yin

It enhances the initial instance positions through weighted farthest point sampling and further refines the instance positions and proposals using aggregation averaging and center matching.

3D Instance Segmentation Position +1

Towards Automatic Power Battery Detection: New Challenge, Benchmark Dataset and Baseline

1 code implementation5 Dec 2023 Xiaoqi Zhao, Youwei Pang, Zhenyu Chen, Qian Yu, Lihe Zhang, Hanqi Liu, Jiaming Zuo, Huchuan Lu

We conduct a comprehensive study on a new task named power battery detection (PBD), which aims to localize the dense cathode and anode plates endpoints from X-ray images to evaluate the quality of power batteries.

Crowd Counting object-detection +2

Open-Vocabulary Camouflaged Object Segmentation

no code implementations19 Nov 2023 Youwei Pang, Xiaoqi Zhao, Jiaming Zuo, Lihe Zhang, Huchuan Lu

To fill in the gaps, we introduce a new task, open-vocabulary camouflaged object segmentation (OVCOS) and construct a large-scale complex scene dataset (\textbf{OVCamo}) which containing 11, 483 hand-selected images with fine annotations and corresponding object classes.

Camouflaged Object Segmentation Image Segmentation +4

ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection

1 code implementation31 Oct 2023 Youwei Pang, Xiaoqi Zhao, Tian-Zhu Xiang, Lihe Zhang, Huchuan Lu

Apart from the high intrinsic similarity between camouflaged objects and their background, objects are usually diverse in scale, fuzzy in appearance, and even severely occluded.

Camouflaged Object Segmentation

Referring Image Segmentation Using Text Supervision

1 code implementation ICCV 2023 Fang Liu, Yuhao Liu, Yuqiu Kong, Ke Xu, Lihe Zhang, BaoCai Yin, Gerhard Hancke, Rynson Lau

Hence, we propose a novel weakly-supervised RIS framework to formulate the target localization problem as a classification process to differentiate between positive and negative text expressions.

Image Segmentation Object Localization +4

Fast Adversarial Training with Smooth Convergence

1 code implementation ICCV 2023 Mengnan Zhao, Lihe Zhang, Yuqiu Kong, BaoCai Yin

To address this, we analyze the training process of prior FAT work and observe that catastrophic overfitting is accompanied by the appearance of loss convergence outliers.

Adversarial Robustness

ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformer

1 code implementation23 Jul 2023 Youwei Pang, Xiaoqi Zhao, Lihe Zhang, Huchuan Lu

Specifically, unlike existing methods that over-specialize in a single task or a subset of tasks, ComPtr starts from the more general concept of bi-source dense prediction.

Change Detection Crowd Counting +4

M$^{2}$SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation

2 code implementations20 Mar 2023 Xiaoqi Zhao, Hongpeng Jia, Youwei Pang, Long Lv, Feng Tian, Lihe Zhang, Weibing Sun, Huchuan Lu

Next, we expand the single-scale SU to the intra-layer multi-scale SU, which can provide the decoder with both pixel-level and structure-level difference information.

Computed Tomography (CT) Image Segmentation +3

Towards Diverse Binary Segmentation via A Simple yet General Gated Network

1 code implementation18 Mar 2023 Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu, Lei Zhang

They ignore two key problems when the encoder exchanges information with the decoder: one is the lack of interference control mechanism between them, the other is without considering the disparity of the contributions from different encoder levels.

Segmentation Semantic Segmentation

Deeply Interleaved Two-Stream Encoder for Referring Video Segmentation

no code implementations30 Mar 2022 Guang Feng, Lihe Zhang, Zhiwei Hu, Huchuan Lu

To address this task, we first design a two-stream encoder to extract CNN-based visual features and transformer-based linguistic features hierarchically, and a vision-language mutual guidance (VLMG) module is inserted into the encoder multiple times to promote the hierarchical and progressive fusion of multi-modal features.

Referring Expression Segmentation Video Segmentation +2

Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction

1 code implementation9 Mar 2022 Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu

In this paper, we propose a novel multi-task and multi-modal filtered transformer (MMFT) network for RGB-D salient object detection (SOD).

Depth Estimation object-detection +2

CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection

1 code implementation4 Dec 2021 Youwei Pang, Xiaoqi Zhao, Lihe Zhang, Huchuan Lu

Most of the existing bi-modal (RGB-D and RGB-T) salient object detection methods utilize the convolution operation and construct complex interweave fusion structures to achieve cross-modal information integration.

object-detection RGB-D Salient Object Detection +1

Temporal Knowledge Graph Reasoning Triggered by Memories

1 code implementation17 Oct 2021 Mengnan Zhao, Lihe Zhang, Yuqiu Kong, BaoCai Yin

Specifically, the transient learning network considers transient memories as a static knowledge graph, and the time-aware recurrent evolution network learns representations through a sequence of recurrent evolution units from long-short-term memories.

Attribute Decision Making +2

MODNet-V: Improving Portrait Video Matting via Background Restoration

1 code implementation24 Sep 2021 Jiayu Sun, Zhanghan Ke, Lihe Zhang, Huchuan Lu, Rynson W. H. Lau

In this work, we observe that instead of asking the user to explicitly provide a background image, we may recover it from the input video itself.

Image Matting Video Matting

Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation

1 code implementation11 Aug 2021 Xiaoqi Zhao, Youwei Pang, Jiaxing Yang, Lihe Zhang, Huchuan Lu

In this paper, we propose a novel multi-source fusion network for zero-shot video object segmentation.

 Ranked #1 on Video Object Segmentation on FBMS (Jaccard (Mean) metric)

Depth Estimation Object +3

Automatic Polyp Segmentation via Multi-scale Subtraction Network

2 code implementations11 Aug 2021 Xiaoqi Zhao, Lihe Zhang, Huchuan Lu

\keywords{Colorectal Cancer \and Automatic Polyp Segmentation \and Subtraction \and LossNet.}

Segmentation

Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation

no code implementations CVPR 2021 Guang Feng, Zhiwei Hu, Lihe Zhang, Huchuan Lu

In this work, we propose an encoder fusion network (EFN), which transforms the visual encoder into a multi-modal feature learning network, and uses language to refine the multi-modal features progressively.

Image Segmentation Semantic Segmentation

Self-Supervised Pretraining for RGB-D Salient Object Detection

1 code implementation29 Jan 2021 Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu, Xiang Ruan

Existing CNNs-Based RGB-D salient object detection (SOD) networks are all required to be pretrained on the ImageNet to learn the hierarchy features which helps provide a good initialization.

Object object-detection +3

Multi-scale Interactive Network for Salient Object Detection

1 code implementation CVPR 2020 Youwei Pang, Xiaoqi Zhao, Lihe Zhang, Huchuan Lu

To obtain more efficient multi-scale features from the integrated features, the self-interaction modules are embedded in each decoder unit.

Object object-detection +2

A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection

1 code implementation ECCV 2020 Xiaoqi Zhao, Lihe Zhang, Youwei Pang, Huchuan Lu, Lei Zhang

In this work, we design a single stream network to directly use the depth map to guide early fusion and middle fusion between RGB and depth, which saves the feature encoder of the depth stream and achieves a lightweight and real-time model.

object-detection RGB-D Salient Object Detection +3

Multi-source weak supervision for saliency detection

1 code implementation CVPR 2019 Yu Zeng, Yunzhi Zhuge, Huchuan Lu, Lihe Zhang, Mingyang Qian, Yizhou Yu

To this end, we propose a unified framework to train saliency detection models with diverse weak supervision sources.

Saliency Prediction

Detect Globally, Refine Locally: A Novel Approach to Saliency Detection

no code implementations CVPR 2018 Tiantian Wang, Lihe Zhang, Shuo Wang, Huchuan Lu, Gang Yang, Xiang Ruan, Ali Borji

Moreover, to effectively recover object boundaries, we propose a local Boundary Refinement Network (BRN) to adaptively learn the local contextual information for each spatial position.

object-detection RGB Salient Object Detection +2

Learning to Promote Saliency Detectors

1 code implementation CVPR 2018 Yu Zeng, Huchuan Lu, Lihe Zhang, Mengyang Feng, Ali Borji

The categories and appearance of salient objects vary from image to image, therefore, saliency detection is an image-specific task.

Saliency Detection Small Data Image Classification +1

A Stagewise Refinement Model for Detecting Salient Objects in Images

1 code implementation ICCV 2017 Tiantian Wang, Ali Borji, Lihe Zhang, Pingping Zhang, Huchuan Lu

To remedy this problem, here we propose to augment feedforward neural networks with a novel pyramid pooling module and a multi-stage refinement mechanism for saliency detection.

Ranked #13 on RGB Salient Object Detection on DUTS-TE (max F-measure metric)

object-detection RGB Salient Object Detection +2

Cannot find the paper you are looking for? You can Submit a new open access paper.