Search Results for author:
Found 30 papers, 21 papers with code
CDI3D: Cross-guided Dense-view Interpolation for 3D Reconstruction
However, challenges remain as 2D diffusion models often struggle to produce dense images with strong multi-view consistency, and LRMs tend to amplify these inconsistencies during the 3D reconstruction process.
Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation
This report presents a comprehensive framework for generating high-quality 3D shapes and textures from diverse input prompts, including single images, multi-view images, and text descriptions.
MARS: Mesh AutoRegressive Model for 3D Shape Detailization
In this paper, we introduce MARS, a novel approach for 3D shape detailization.
MiniMax-01: Scaling Foundation Models with Lightning Attention
This approach enables us to conduct efficient training and inference on models with hundreds of billions of parameters across contexts spanning millions of tokens.
Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention
This eliminates the need for cumsum in the linear attention calculation.
LAM3D: Large Image-Point-Cloud Alignment Model for 3D Reconstruction from Single Image
Large Reconstruction Models have made significant strides in the realm of automated 3D content generation from single or multiple input images.
HGRN2: Gated Linear RNNs with State Expansion
Hierarchically gated linear RNN (HGRN, \citealt{HGRN}) has demonstrated competitive training speed and performance in language modeling while offering efficient inference.
NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation
3D shape generation aims to produce innovative 3D content adhering to specific conditions and constraints.
Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane
We present Frankenstein, a diffusion-based framework that can generate semantic-compositional 3D scenes in a single pass.
BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation
A variational auto-encoder is employed to compress the tri-planes into the latent tri-plane space, on which the denoising diffusion process is performed.
CO2: Efficient Distributed Training with Full Communication-Computation Overlap
CO2 is able to attain a high scalability even on extensive multi-node clusters constrained by very limited communication bandwidth.
Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
With its ability to process tokens in linear computational complexities, linear attention, in theory, can handle sequences of unlimited length without sacrificing speed, i. e., maintaining a constant training speed for various sequence lengths with a fixed memory consumption.
All-pairs Consistency Learning for Weakly Supervised Semantic Segmentation
Given a pair of augmented views, our approach regularizes the activation intensities between a pair of augmented views, while also ensuring that the affinity across regions within each view remains consistent.
Ranked #16 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer
TransNormerLLM evolves from the previous linear attention architecture TransNormer by making advanced modifications that include positional embedding, linear attention acceleration, gating mechanisms, tensor normalization, and inference acceleration and stabilization.
Linearized Relative Positional Encoding
Meanwhile, it emphasizes a general paradigm for designing broadly more relative positional encoding methods that are applicable to linear transformers.
Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder
An alternative approach is to allow interactions between the query and every possible candidate, i. e., reference-text-candidate triplets, and pick the best from the entire set.
Ranked #3 on
Image Retrieval
on Fashion IQ
Toeplitz Neural Network for Sequence Modeling
Sequence modeling has important applications in natural language processing and computer vision.
An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems
The Segment Anything Model (SAM) has demonstrated exceptional performance and versatility, making it a promising tool for various related tasks.
Ranked #3 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
(using extra training data)
Bi-directional Training for Composed Image Retrieval via Text Prompt Learning
Composed image retrieval searches for a target image based on a multi-modal user query comprised of a reference image and modification text describing the desired changes.
Ranked #7 on
Image Retrieval
on Fashion IQ
Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning
Based on this observation, we propose a new learning strategy named False Negative Aware Contrastive (FNAC) to mitigate the problem of misleading the training with such false negative samples.
Audio-Visual Segmentation with Semantics
To deal with these problems, we propose a new baseline method that uses a temporal pixel-wise audio-visual interaction module to inject audio semantics as guidance for the visual segmentation process.
The Devil in Linear Transformer
In this paper, we examine existing kernel-based linear transformers and identify two key issues that lead to such performance gaps: 1) unbounded gradients in the attention computation adversely impact the convergence of linear transformer models; 2) attention dilution which trivially distributes attention scores over long sequences while neglecting neighbouring structures.
Linear Video Transformer with Feature Fixation
Therefore, we propose a feature fixation module to reweight the feature importance of the query and key before computing linear attention.
Neural Architecture Search on Efficient Transformers and Beyond
To address this issue, we propose a new framework to find optimal architectures for efficient Transformers with the neural architecture search (NAS) technique.
Audio-Visual Segmentation
To deal with the AVS problem, we propose a novel method that uses a temporal pixel-wise audio-visual interaction module to inject audio semantics as guidance for the visual segmentation process.
Vicinity Vision Transformer
Based on this observation, we present a Vicinity Attention that introduces a locality bias to vision transformers with linear complexity.
Ranked #295 on
Image Classification
on ImageNet
cosFormer: Rethinking Softmax in Attention
As one of its core components, the softmax attention helps to capture long-range dependencies yet prohibits its scale-up due to the quadratic space and time complexity to the sequence length.
Ranked #6 on
D4RL
on D4RL
GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation
To bridge their gap, a Class Activation Map (CAM) is usually generated to provide pixel level pseudo labels.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Inferring the Class Conditional Response Map for Weakly Supervised Semantic Segmentation
To solve this, most existing approaches follow a multi-training pipeline to refine CAMs for better pseudo-labels, which includes: 1) re-training the classification model to generate CAMs; 2) post-processing CAMs to obtain pseudo labels; and 3) training a semantic segmentation model with the obtained pseudo labels.
Ranked #24 on
Weakly-Supervised Semantic Segmentation
on PASCAL VOC 2012 test
(using extra training data)
3D Guided Weakly Supervised Semantic Segmentation
In this paper, we propose a weakly supervised 2D semantic segmentation model by incorporating sparse bounding box labels with available 3D information, which is much easier to obtain with advanced sensors.
