Search Results for author:
Found 33 papers, 16 papers with code
Exploring Interpretability for Visual Prompt Tuning with Hierarchical Concepts
Visual prompt tuning offers significant advantages for adapting pre-trained visual foundation models to specific tasks.
Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector
Catastrophic forgetting is a critical chanllenge for incremental object detection (IOD).
Mamba-CL: Optimizing Selective State Space Model in Null Space for Continual Learning
Continual Learning (CL) aims to equip AI models with the ability to learn a sequence of tasks over time, without forgetting previously learned knowledge.
Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection
The innovation of our approach is that we leverage the diffusion model's intrinsic data reconstruction ability to distinguish ID samples from OOD samples in the latent feature space.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling
Specifically, we introduce a relationship-guided attention module to capture pair-wise associations among entities and attributes for low-level prompt learning.
Ranked #1 on
Prompt Engineering
on ImageNet V2
Cross-Platform Video Person ReID: A New Benchmark Dataset and Adaptation Approach
In this paper, we construct a large-scale benchmark dataset for Ground-to-Aerial Video-based person Re-Identification, named G2A-VReID, which comprises 185, 907 images and 5, 576 tracklets, featuring 2, 788 distinct identities.
ActPrompt: In-Domain Feature Adaptation via Action Cues for Video Temporal Grounding
Video temporal grounding is an emerging topic aiming to identify specific clips within videos.
Center-Sensitive Kernel Optimization for Efficient On-Device Incremental Learning
Based on an empirical study on the knowledge intensity of the kernel elements of the neural network, we find that the center kernel is the key for maximizing the knowledge intensity for learning new data, while freezing the other kernel elements would get a good balance on the model's capacity for overcoming catastrophic forgetting.
Visual Prompt Tuning in Null Space for Continual Learning
Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL), by selecting and updating relevant prompts in the vision-transformer models.
Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure
It considers the characteristics of the image restoration task with multiple degenerations in continual learning, and the knowledge for different degenerations can be shared and accumulated in the unified network structure.
Exploring Homogeneous and Heterogeneous Consistent Label Associations for Unsupervised Visible-Infrared Person ReID
While prior work focuses on establishing cross-modality pseudo-label associations to bridge the modality-gap, they ignore maintaining the instance-level homogeneous and heterogeneous consistency between the feature space and the pseudo-label space, resulting in coarse associations.
Disentangled Prompt Representation for Domain Generalization
Although there is a growing focus on VFM-based domain prompt tuning for DG effectively learning prompts that disentangle invariant features across all domains remains a major challenge.
Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models
To address this limitation and prioritize harnessing structured knowledge, this paper advocates for leveraging LLMs to build a graph for each description to model the entities and attributes describing the category, as well as their correlations.
Ranked #2 on
Prompt Engineering
on ImageNet V2
EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model
To further clarify the noise of expanded boundaries, we combine mutual learning with a tailored proposal-level contrastive objective to use a learnable approach to harmonize a balance between incomplete yet clean (initial) and comprehensive yet noisy (expanded) boundaries for more precise ones.
Ground-to-Aerial Person Search: Benchmark Dataset and Approach
In this work, we construct a large-scale dataset for Ground-to-Aerial Person Search, named G2APS, which contains 31, 770 images of 260, 559 annotated bounding boxes for 2, 644 identities appearing in both of the UAVs and ground surveillance cameras.
Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID
To this end, we propose a novel bilateral cluster matching-based learning framework to reduce the modality gap by matching cross-modality clusters.
Unsupervised Visible-Infrared Person ReID by Collaborative Learning with Neighbor-Guided Label Refinement
Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims at learning modality-invariant features from unlabeled cross-modality dataset, which is crucial for practical applications in video surveillance systems.
Boosting Weakly-Supervised Temporal Action Localization with Text Information
For the discriminative objective, we propose a Text-Segment Mining (TSM) mechanism, which constructs a text description based on the action class label, and regards the text as the query to mine all class-related segments.
Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint
The proposed Bi-SCC firstly adopts a temporal context augmentation to generate an augmented video that breaks the correlation between positive actions and their co-scene actions in the inter-video; Then, a semantic consistency constraint (SCC) is used to enforce the predictions of the original video and augmented video to be consistent, hence suppressing the co-scene actions.
Weakly-supervised Temporal Action Localization
Weakly Supervised Temporal Action Localization
Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification
In this paper, we propose a Neighbour Consistency guided Pseudo Label Refinement (NCPLR) framework, which can be regarded as a transductive form of label propagation under the assumption that the prediction of each example should be similar to its nearest neighbours'.
Class-Dependent Label-Noise Learning with Cycle-Consistency Regularization Feature Space
We show that the cycle-consistency regularization helps to minimize the volume of the transition matrix T indirectly without exploiting the estimated noisy class posterior, which could further encourage the estimated transition matrix T to converge to its optimal solution.
Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model
To make the final image feature concentrate more on the target visual concept, a Class-Aware Visual Prompt Tuning (CAVPT) scheme is further proposed in our DPT, where the class-aware visual prompt is generated dynamically by performing the cross attention between text prompts features and image patch token embeddings to encode both the downstream task-related information and visual instance information.
Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation
In label-noise learning, estimating the transition matrix has attracted more and more attention as the matrix plays an important role in building statistically consistent classifiers.
Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstruction
To properly address this problem, we propose a novel density-variational learning framework to improve the robustness of the image dehzing model assisted by a variety of negative hazy images, to better deal with various complex hazy scenarios.
Robust Region Feature Synthesizer for Zero-Shot Object Detection
Zero-shot object detection aims at incorporating class semantic vectors to realize the detection of (both seen and) unseen classes given an unconstrained test image.
Ranked #2 on
Zero-Shot Object Detection
on PASCAL VOC'07
Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Id
However, since person Re-Id is an open-set problem, the clustering based methods often leave out lots of outlier instances or group the instances into the wrong clusters, thus they can not make full use of the training samples as a whole.
Text-based Person Search in Full Images via Semantic-Driven Proposal Generation
Finding target persons in full scene images with a query of text description has important practical applications in intelligent video surveillance. However, different from the real-world scenarios where the bounding boxes are not available, existing text-based person retrieval methods mainly focus on the cross modal matching between the query text descriptions and the gallery of cropped pedestrian images.
Single Image Dehazing with An Independent Detail-Recovery Network
In this paper, we propose a single image dehazing method with an independent Detail Recovery Network (DRN), which considers capturing the details from the input image over a separate network and then integrates them into a coarse dehazed image.
Support-Set Based Cross-Supervision for Video Grounding
The contrastive objective aims to learn effective representations by contrastive learning, while the caption objective can train a powerful video encoder supervised by texts.
Complex Event Detection by Identifying Reliable Shots From Untrimmed Videos
relevant) to the given event class, we formulate this task as a multi-instance learning (MIL) problem by taking each video as a bag and the video shots in each video as instances.
Deep Feature Learning via Structured Graph Laplacian Embedding for Person Re-Identification
The proposed method can take full advantages of the structured distance relationships among these training samples, with the constructed complete graph.
Person Re-Identification by Multi-Channel Parts-Based CNN With Improved Triplet Loss Function
Person re-identification across cameras remains a very challenging problem, especially when there are no overlapping fields of view between cameras.
