Search Results for author:
Found 15 papers, 12 papers with code
T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
Sampling from diffusion probabilistic models (DPMs) is often expensive for high-quality image generation and typically requires many steps with a large model.
Efficient Stitchable Task Adaptation
In this work, we present a novel framework, Efficient Stitchable Task Adaptation (ESTA), to efficiently produce a palette of fine-tuned models that adhere to diverse resource constraints.
Stitched ViTs are Flexible Vision Backbones
With extensive experiments on ImageNet-1K, ADE20K, COCO-Stuff-10K and NYUv2, SN-Netv2 demonstrates superior performance over SN-Netv1 on downstream dense predictions and shows strong ability as a flexible vision backbone, achieving great advantages in both training efficiency and deployment flexibility.
Stitchable Neural Networks
As each model family consists of pretrained models with diverse scales (e. g., DeiT-Ti/S/B), it naturally arises a fundamental question of how to efficiently assemble these readily available models in a family for dynamic accuracy-efficiency trade-offs at runtime.
A Survey on Efficient Training of Transformers
Recent advances in Transformers have come with a huge requirement on computing resources, highlighting the importance of developing efficient training techniques to make Transformer training faster, at lower cost, and to higher accuracy by the efficient use of computation and memory resources.
EcoFormer: Energy-Saving Attention with Linear Complexity
To this end, we propose a new binarization paradigm customized to high-dimensional softmax attention via kernelized hashing, called EcoFormer, to map the original queries and keys into low-dimensional binary codes in Hamming space.
An Efficient Spatio-Temporal Pyramid Transformer for Action Detection
The task of action detection aims at deducing both the action category and localization of the start and end moment for each action instance in a long, untrimmed video.
Fast Vision Transformers with HiLo Attention
Therefore, we propose to disentangle the high/low frequency patterns in an attention layer by separating the heads into two groups, where one group encodes high frequencies via self-attention within each local window, and another group encodes low frequencies by performing global attention between the average-pooled low-frequency keys and values from each window and each query position in the input feature map.
Ranked #281 on
Image Classification
on ImageNet
Dynamic Focus-aware Positional Queries for Semantic Segmentation
In this paper, we propose a simple yet effective query design for semantic segmentation termed Dynamic Focus-aware Positional Queries (DFPQ), which dynamically generates positional queries conditioned on the cross-attention scores from the preceding decoder block and the positional encodings for the corresponding image features, simultaneously.
Ranked #21 on
Semantic Segmentation
on ADE20K
Pruning Self-attentions into Convolutional Layers in Single Path
Relying on the single-path space, we introduce learnable binary gates to encode the operation choices in MSA layers.
Ranked #18 on
Efficient ViTs
on ImageNet-1K (with DeiT-T)
Mesa: A Memory-saving Training Framework for Transformers
While Transformers have delivered significant performance improvements, training such networks is extremely memory intensive owing to storing all intermediate activations that are needed for gradient computation during backpropagation, especially for long sequences.
Less is More: Pay Less Attention in Vision Transformers
Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision.
The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation
Vision-and-Language Navigation (VLN) requires an agent to find a path to a remote location on the basis of natural-language instructions and a set of photo-realistic panoramas.
Scalable Vision Transformers with Hierarchical Pooling
However, the routine of the current ViT model is to maintain a full-length patch sequence during inference, which is redundant and lacks hierarchical representation.
Ranked #22 on
Efficient ViTs
on ImageNet-1K (with DeiT-T)
Object-and-Action Aware Model for Visual Language Navigation
The first is object description (e. g., 'table', 'door'), each presenting as a tip for the agent to determine the next action by finding the item visible in the environment, and the second is action specification (e. g., 'go straight', 'turn left') which allows the robot to directly predict the next movements without relying on visual perceptions.
