Search Results for author:
Found 13 papers, 9 papers with code
IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact
Large language models (LLMs) excel in natural language processing but demand intensive computation.
ChartBench: A Benchmark for Complex Visual Reasoning in Charts
Multimodal Large Language Models (MLLMs) demonstrate impressive image understanding and generating capabilities.
Towards Effective Collaborative Learning in Long-Tailed Recognition
In this paper, we observe that the knowledge transfer between experts is imbalanced in terms of class distribution, which results in limited performance improvement of the minority classes.
Rethink Long-tailed Recognition with Vision Transformers
Hence, we propose to adopt unsupervised learning to utilize long-tailed data.
Accurate 3D Face Reconstruction with Facial Component Tokens
However, the current deep learning-based methods face significant challenges in achieving accurate reconstruction with disentangled facial parameters and ensuring temporal stability in single-frame methods for 3D face tracking on video data.
Learning Imbalanced Data with Vision Transformers
In this paper, we systematically investigate the ViTs' performance in LTR and propose LiVT to train ViTs from scratch only with LT data.
Ranked #7 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
HyP$^2$ Loss: Beyond Hypersphere Metric Space for Multi-label Image Retrieval
Image retrieval has become an increasingly appealing technique with broad multimedia application prospects, where deep hashing serves as the dominant branch towards low storage and efficient retrieval.
REALY: Rethinking the Evaluation of 3D Face Reconstruction
The evaluation of 3D face reconstruction results typically relies on a rigid shape alignment between the estimated 3D model and the ground-truth scan.
HHF: Hashing-guided Hinge Function for Deep Hashing Retrieval
Deep hashing has shown promising performance in large-scale image retrieval.
Semantic-Sparse Colorization Network for Deep Exemplar-based Colorization
To address these two problems, we propose Semantic-Sparse Colorization Network (SSCN) to transfer both the global image style and detailed semantic-related colors to the gray-scale image in a coarse-to-fine manner.
Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective
Real-world data universally confronts a severe class-imbalance problem and exhibits a long-tailed distribution, i. e., most labels are associated with limited instances.
Ranked #24 on
Long-tail Learning
on CIFAR-100-LT (ρ=10)
MoDeRNN: Towards Fine-grained Motion Details for Spatiotemporal Predictive Learning
We carefully design Detail Context Block (DCB) to extract fine-grained details and improve the isolated correlation between upper context state and current input state.
CMS-LSTM: Context Embedding and Multi-Scale Spatiotemporal Expression LSTM for Predictive Learning
To tackle the increasing ambiguity during forecasting, we design CMS-LSTM to focus on context correlations and multi-scale spatiotemporal flow with details on fine-grained locals, containing two elaborate designed blocks: Context Embedding (CE) and Spatiotemporal Expression (SE) blocks.
