Search Results for author:
Found 28 papers, 13 papers with code
iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models
iLLaVA can nearly 2$\times$ the throughput, and reduce the memory costs by half with only a 0. 2\% - 0. 5\% performance drop across models of different scales including 7B, 13B and 34B.
Deep Correlated Prompting for Visual Recognition with Missing Modalities
Plentiful ablations are further given to show the generalizability and reliability of our method upon different modality-missing ratios and types.
Completed Feature Disentanglement Learning for Multimodal MRIs Analysis
Specifically, the CFD strategy not only identifies modality-shared and modality-specific features, but also decouples shared features among subsets of multimodal inputs, termed as modality-partial-shared features.
Topicwise Separable Sentence Retrieval for Medical Report Generation
To ensure comprehensive learning of both common and rare topics, we categorize queries into common and rare types to learn differentiated topics, and then propose Topic Contrastive Loss to effectively align topics and queries in the latent space.
CorrNet+: Sign Language Recognition and Translation via Spatial-Temporal Correlation
In specific, CorrNet+ employs a correlation module and an identification module to build human body trajectories.
Elastic Multi-Gradient Descent for Parallel Continual Learning
The goal of Continual Learning (CL) is to continuously learn from new data streams and accomplish the corresponding tasks.
Bilateral Network with Residual U-blocks and Dual-Guided Attention for Real-time Semantic Segmentation
To be precise, we use the Dual-Guided Attention (DGA) module we proposed to replace some multi-scale transformations with the calculation of attention which means we only use several attention layers of near linear complexity to achieve performance comparable to frequently-used multi-layer fusion.
Long-Tailed Learning as Multi-Objective Optimization
Real-world data is extremely imbalanced and presents a long-tailed distribution, resulting in models that are biased towards classes with sufficient samples and perform poorly on rare classes.
Improving the Transferability of Adversarial Examples with Arbitrary Style Transfer
Deep neural networks are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on clean inputs.
Multi-Loss Convolutional Network with Time-Frequency Attention for Speech Enhancement
By combining the DPRNN module with Convolution Recurrent Network (CRN), the DPCRN obtained a promising performance in speech separation with a limited model size.
HybridMIM: A Hybrid Masked Image Modeling Framework for 3D Medical Image Segmentation
Masked image modeling (MIM) with transformer backbones has recently been exploited as a powerful self-supervised pre-training technique.
Diff-UNet: A Diffusion Embedded Network for Volumetric Segmentation
Our experimental results also indicate the universality and effectiveness of the proposed model.
Learning Physical-Spatio-Temporal Features for Video Shadow Removal
Then, we develop a progressive aggregation module to enhance the spatio and temporal characteristics of features maps, and effectively integrate the three kinds of features.
Medical Phrase Grounding with Region-Phrase Context Contrastive Alignment
To enable MedRPG to locate nuanced medical findings with better region-phrase correspondences, we further propose Tri-attention Context contrastive alignment (TaCo).
Measuring Asymmetric Gradient Discrepancy in Parallel Continual Learning
In Parallel Continual Learning (PCL), the parallel multiple tasks start and end training unpredictably, thus suffering from training conflict and catastrophic forgetting issues.
Exploring Example Influence in Continual Learning
Continual Learning (CL) sequentially learns new tasks like human beings, with the goal to achieve better Stability (S, remembering past tasks) and Plasticity (P, adapting to new tasks).
Joint Prediction of Meningioma Grade and Brain Invasion via Task-Aware Contrastive Learning
Preoperative and noninvasive prediction of the meningioma grade is important in clinical practice, as it directly influences the clinical decision making.
NestedFormer: Nested Modality-Aware Transformer for Brain Tumor Segmentation
Multi-modal MR imaging is routinely used in clinical practice to diagnose and investigate brain tumors by providing rich complementary information.
Rethinking Rehearsal in Lifelong Learning: Does An Example Contribute the Plasticity or Stability?
Traditionally, the primary goal of LL is to achieve the trade-off between the Stability (remembering past tasks) and Plasticity (adapting to new tasks).
From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data
Our DID-Net predicts the three component maps by progressively integrating features across scales, and refines each map by passing an independent refinement network.
Ranked #8 on
Image Dehazing
on Haze4k
Triple-cooperative Video Shadow Detection
The bottleneck is the lack of a well-established dataset with high-quality annotations for video shadow detection.
Active Lighting Recurrence by Parallel Lighting Analogy for Fine-Grained Change Detection
Besides, we also theoretically prove the invariance of our ALR approach to the ambiguity of normal and lighting decomposition.
Effects of Blur and Deblurring to Visual Object Tracking
In this paper, we address these two problems by constructing a Blurred Video Tracking benchmark, which contains a variety of videos with different levels of motion blurs, as well as ground truth tracking results for evaluating trackers.
Multiple Human Association between Top and Horizontal Views by Matching Subjects' Spatial Distributions
However, for such collaborative analysis, the first step is to associate people, referred to as subjects in this paper, across these two views.
An Embarrassingly Simple Approach for Knowledge Distillation
Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model.
Learning Dynamic Siamese Network for Visual Object Tracking
How to effectively learn temporal variation of target appearance, to exclude the interference of cluttered background, while maintaining real-time response, is an essential problem of visual object tracking.
Ranked #5 on
Visual Object Tracking
on OTB-2013
Fine-Grained Change Detection of Misaligned Scenes With Varied Illuminations
To guarantee detection sensitivity and accuracy of minute changes, in an observation, we capture a group of images under multiple illuminations, which need only to be roughly aligned to the last time lighting conditions.
Maximum Cohesive Grid of Superpixels for Fast Object Localization
For this purpose, we aim at constructing maximum cohesive SP-grid, which is composed of real nodes, i. e. SPs, and dummy nodes that are meaningless in the image with only position-taking function in the grid.
