Search Results for author:
Found 52 papers, 22 papers with code
LatticeNet: Towards Lightweight Image Super-resolution with Lattice Block
Drawing lessons from lattice filter bank, we design the lattice block (LB) in which two butterfly structures are applied to combine two RBs.
One-for-More: Continual Diffusion Model for Anomaly Detection
Finally, considering the risk of ``over-fitting'' to normal images of the diffusion model, we propose an anomaly-masked network to enhance the condition mechanism of the diffusion model.
CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP
Then these modality-specific embeddings are used to enhance original representations of CLIP for better matching ability.
Fusion-then-Distillation: Toward Cross-modal Positive Distillation for Domain Adaptive 3D Semantic Segmentation
In cross-modal unsupervised domain adaptation, a model trained on source-domain data (e. g., synthetic) is adapted to target-domain data (e. g., real-world) without access to target annotation.
LLaCA: Multimodal Large Language Continual Assistant
We observe existing gradient update would heavily destroy the tuning performance on previous datasets and the zero-shot ability during continual instruction tuning.
Data-free Distillation with Degradation-prompt Diffusion for Multi-weather Image Restoration
Multi-weather image restoration has witnessed incredible progress, while the increasing model capacity and expensive data acquisition impair its applications in memory-limited devices.
Mutual Information Guided Optimal Transport for Unsupervised Visible-Infrared Person Re-identification
In the training stage, we utilize this matching information to introduce prototype-based contrastive learning for minimizing the intra- and cross-modality entropy ("Sharpness").
Exploring the Untouched Sweeps for Conflict-Aware 3D Segmentation Pretraining
We utilized timestamps and the semantic priors from VFMs to identify well-synchronized training pairs and to discover samples with diverse content.
CLIP3D-AD: Extending CLIP for 3D Few-Shot Anomaly Detection with Multi-View Images Generation
Specifically, we synthesize anomalous images on given normal images as sample pairs to adapt CLIP for 3D anomaly classification and segmentation.
Gradient Projection For Continual Parameter-Efficient Tuning
Parameter-efficient tunings (PETs) have demonstrated impressive performance and promising perspectives in training large models, while they are still confronted with a common problem: the trade-off between learning new content and protecting old knowledge, leading to zero-shot generalization collapse, and cross-modal hallucination.
Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception
Such inconsiderate consistency greatly hampers the promising path of reaching an universal pre-training framework: (1) The cross-scene semantic self-conflict, i. e., the intense collision between primitive segments of the same semantics from different scenes; (2) Lacking a globally unified bond that pushes the cross-scene semantic consistency into 3D representation learning.
Robust Pseudo-label Learning with Neighbor Relation for Unsupervised Visible-Infrared Person Re-Identification
Unsupervised Visible-Infrared Person Re-identification (USVI-ReID) presents a formidable challenge, which aims to match pedestrian images across visible and infrared modalities without any annotations.
PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection
The vision-language model has brought great improvement to few-shot industrial anomaly detection, which usually needs to design of hundreds of prompts through prompt engineering.
Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification
To address the problem, we propose a Progressive Contrastive Learning with Hard and Dynamic Prototypes method for USVI-ReID.
Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification
To associate cross-modality clustered pseudo-labels, we design a Multi-Memory Learning and Matching (MMLM) module, ensuring that optimization explicitly focuses on the nuances of individual perspectives and establishes reliable cross-modality correspondences.
CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Data
For server-side learning, in order to mitigate the heterogeneity and class-distribution imbalance, we generate federated features to retrain the server model.
Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation
Second, in the Image Branch, we propose the Instance Position-scale Learning (IPSL) Module to learn and fuse the information of instance position and scale, which is from a 2D pre-trained detector and a type of latent label obtained from 3D to 2D projection.
COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction
The autonomous driving community has shown significant interest in 3D occupancy prediction, driven by its exceptional geometric perception and general object recognition capabilities.
Unveiling the Power of CLIP in Unsupervised Visible-Infrared Person Re-Identification
In this paper, we propose a new prompt learning paradigm for unsupervised visible-infrared person re-identification (USL-VI-ReID) by taking full advantage of the visual-text representation ability from CLIP.
BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation
In light of this, we propose cross-modal learning under bird's-eye view for Domain Generalization (DG) of 3D semantic segmentation, called BEV-DG.
Dual Pseudo-Labels Interactive Self-Training for Semi-Supervised Visible-Infrared Person Re-Identification
Visible-infrared person re-identification (VI-ReID) aims to match a specific person from a gallery of images captured from non-overlapping visible and infrared cameras.
Multi-Centroid Task Descriptor for Dynamic Class Incremental Inference
As a result, our dynamic inference network is trained independently of baseline and provides a flexible, efficient solution to distinguish between tasks.
Efficient Converted Spiking Neural Network for 3D and 2D Classification
Spiking Neural Networks (SNNs) have attracted enormous research interest due to their low-power and biologically plausible nature.
Instance and Category Supervision are Alternate Learners for Continual Learning
Continual Learning (CL) is the constant development of complex behaviors by building upon previously acquired skills.
Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling
In this paper, we propose a space decoupling (SD) algorithm to decouple the feature space into a pair of complementary subspaces, i. e., the stability space I, and the plasticity space R. I is established by conducting space intersection between the historic and current feature space, and thus I contains more task-shared bases.
Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis
In the forward stage, we take advantage of LTH with rewinding weights to progressively shrink the SR model and the pruning-out masks that form nested sets.
Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud
Firstly, we construct a pretext task, \textit{i. e.,} point cloud colorization, with a self-supervised learning to transfer the learned prior knowledge from a large amount of unlabeled point cloud to a weakly supervised network.
Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learning
In this paper, we propose a novel cross-modality weakly supervised method for 3D segmentation, incorporating complementary information from unlabeled images.
Variational Distillation for Multi-View Learning
Information Bottleneck (IB) based multi-view learning provides an information theoretic principle for seeking shared information contained in heterogeneous data descriptions.
Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting
Crowd counting has important applications in public safety and pandemic control.
En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning
Our ICCE promotes intra-class compactness with inter-class separability on both seen and unseen classes in the embedding space and visual feature space.
Boosting Lightweight Single Image Super-resolution via Joint-distillation
The joint-distillation learning consists of internal self-distillation and external mutual learning.
Towards Compact Single Image Super-Resolution via Contrastive Self-distillation
Convolutional neural networks (CNNs) are highly successful for super-resolution (SR) but often require sophisticated architectures with heavy memory cost and computational overhead, significantly restricts their practical deployments on resource-limited devices.
Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning
Our method can significantly improve the backbones in all three datasets.
Ranked #2 on
Semantic Segmentation
on Semantic3D
Contrastive Learning for Compact Single Image Dehazing
In this paper, we propose a novel contrastive regularization (CR) built upon contrastive learning to exploit both the information of hazy images and clear images as negative and positive samples, respectively.
Ranked #5 on
Image Dehazing
on RS-Haze
Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification
The Information Bottleneck (IB) provides an information theoretic principle for representation learning, by retaining all information relevant for predicting label while minimizing the redundancy.
Cross-Modality Person Re-identification
Cross-Modal Person Re-Identification
+3
Learn from Concepts: Towards the Purified Memory for Few-shot Learning
In this paper, we present a novel purified memory mechanism that simulates the recognition process of human beings.
Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds
Boundary information plays a significant role in 2D image segmentation, while usually being ignored in 3D point cloud segmentation where ambiguous features might be generated in feature extraction, leading to misclassification in the transition area between two objects.
Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud Semantic Segmentation
In this way, the graph topology of the whole point cloud can be effectively established by the introduced auxiliary supervision, such that the information propagation between the labeled and unlabeled points will be realized.
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results.
NTIRE 2020 Challenge on NonHomogeneous Dehazing
We focus on the proposed solutions and their results evaluated on NH-Haze, a novel dataset consisting of 55 pairs of real haze free and nonhomogeneous hazy images recorded outdoor.
NTIRE 2020 Challenge on Image Demoireing: Methods and Results
Track 1 targeted the single image demoireing problem, which seeks to remove moire patterns from a single image.
Meta Segmentation Network for Ultra-Resolution Medical Images
MSN can fast generate the weights of fusion layers through a simple meta-learner, requiring only a few training samples and epochs to converge.
Novelty Detection via Non-Adversarial Generative Network
One-class novelty detection is the process of determining if a query example differs from the training examples (the target class).
AIM 2019 Challenge on Image Demoireing: Methods and Results
A new dataset, called LCDMoire was created for this challenge, and consists of 10, 200 synthetically generated image pairs (moire and clean ground truth).
Enhanced Pix2pix Dehazing Network
Inspired by visual perception global-first theory, the discriminator guides the generator to create a pseudo realistic image on a coarse scale, while the enhancer following the generator is required to produce a realistic dehazing image on the fine scale.
Ranked #29 on
Image Dehazing
on SOTS Indoor
Bi-GANs-ST for Perceptual Image Super-resolution
In this paper, motivated by [1], we aim to generate a high-quality SR result which balances between the two indices, i. e., the perception index and root-mean-square error (RMSE).
Jointly Deep Multi-View Learning for Clustering Analysis
To our best knowledge, this is the first work to model the multi-view clustering in a deep joint framework, which will provide a meaningful thinking in unsupervised multi-view learning.
Robust Kernelized Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization
In particular, the original tensor-based multi-view self-representation clustering problem is a special case of our approach and can be solved by our algorithm.
Joint Hierarchical Category Structure Learning and Large-Scale Image Classification
We propose a novel image classification method based on learning hierarchical inter-class structures.
On Unifying Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization
Different from traditional unfolding based tensor norm, this low-rank tensor constraint has optimality properties similar to that of matrix rank derived from SVD, so the complementary information among views can be explored more efficiently and thoroughly.
Distortion-driven Turbulence Effect Removal using Variational Model
To solve, or at least reduce these effects, we propose a new scheme to recover a latent image from observed frames by integrating a new variational model and distortion-driven spatial-temporal kernel regression.
