Search Results for author:
Found 12 papers, 4 papers with code
Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning
Vision Foundation Models (VFMs) have demonstrated outstanding performance on numerous downstream tasks.
Emerging Pixel Grounding in Large Multimodal Models Without Grounding Supervision
Contrary to the common practice that fine-tunes LMMs with additional grounding supervision, we find that the grounding ability can in fact emerge in LMMs trained without explicit grounding supervision.
SOHES: Self-supervised Open-world Hierarchical Entity Segmentation
Using raw images as the sole training data, our method achieves unprecedented performance in self-supervised open-world segmentation, marking a significant milestone towards high-quality open-world entity segmentation in the absence of human-annotated masks.
TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding
The limited scale of current 3D shape datasets hinders the advancements in 3D shape understanding, and motivates multi-modal learning approaches which transfer learned knowledge from data-abundant 2D image and language modalities to 3D shapes.
Ranked #1 on
Zero-shot 3D Point Cloud Classification
on ScanObjectNN (Pretrained on ShapeNet)
(using extra training data)
HASSOD: Hierarchical Adaptive Self-Supervised Object Detection
The human visual perception system demonstrates exceptional capabilities in learning without explicit supervision and understanding the part-to-whole composition of objects.
Aligning Large Multimodal Models with Factually Augmented RLHF
Large Multimodal Models (LMM) are built across modalities and the misalignment between two modalities can result in "hallucination", generating textual outputs that are not grounded by the multimodal information in context.
Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation
To distill knowledge from a highly accurate but complex teacher model, we construct a sequence of teachers to help the student gradually adapt.
Contrastive Mean Teacher for Domain Adaptive Object Detectors
Object detectors often suffer from the domain gap between training (source domain) and real-world applications (target domain).
Neighborhood-Aware Neural Architecture Search
To facilitate the application to gradient-based algorithms, we also propose a differentiable representation for the neighborhood of architectures.
Efficient Model Performance Estimation via Feature Histories
Using a sampling-based search algorithm and parallel computing, our method can find an architecture which is better than DARTS and with an 80% reduction in wall-clock search time.
Rethinking Transformer-based Set Prediction for Object Detection
DETR is a recently proposed Transformer-based method which views object detection as a set prediction problem and achieves state-of-the-art performance but demands extra-long training time to converge.
Learnable Embedding Space for Efficient Neural Architecture Compression
We also demonstrate that the learned embedding space can be transferred to new settings for architecture search, such as a larger teacher network or a teacher network in a different architecture family, without any training.
