Search Results for author:
Found 34 papers, 14 papers with code
Residual Connections Harm Self-Supervised Abstract Feature Learning
We demonstrate that adding a weighting factor to decay the strength of identity shortcuts within residual networks substantially improves semantic feature learning in the state-of-the-art self-supervised masked autoencoding (MAE) paradigm.
Deciphering 'What' and 'Where' Visual Pathways from Spectral Clustering of Layer-Distributed Neural Representations
We present an approach for analyzing grouping information contained within a neural network's activations, permitting extraction of spatial layout and semantic segmentation from the behavior of large pre-trained vision models.
SySMOL: A Hardware-software Co-design Framework for Ultra-Low and Fine-Grained Mixed-Precision Neural Networks
The design for mixed-precision networks that achieves optimized tradeoffs corresponds to an architecture that supports 1, 2, and 4-bit fixed-point operations with four configurable precision patterns, when coupled with system-aware training and inference optimization -- networks trained for this design achieve accuracies that closely match full-precision accuracies, while compressing and improving run-time efficiency of the neural networks drastically by 10-20x, compared to full-precision networks.
HyperFields: Towards Zero-Shot Generation of NeRFs from Text
We introduce HyperFields, a method for generating text-conditioned Neural Radiance Fields (NeRFs) with a single forward pass and (optionally) some fine-tuning.
CacheGen: KV Cache Compression and Streaming for Fast Language Model Serving
Compared to the recent systems that reuse the KV cache, CacheGen reduces the KV cache size by 3. 7-4. 3x and the total delay in fetching and processing contexts by 2. 7-3. 2x while having negligible impact on the LLM response quality in accuracy or perplexity.
Automatic and Efficient Customization of Neural Networks for ML Applications
ML APIs have greatly relieved application developers of the burden to design and train their own neural network models -- classifying objects in an image can now be as simple as one line of Python code to call an API.
Structural Adversarial Objectives for Self-Supervised Representation Learning
Within the framework of generative adversarial networks (GANs), we propose objectives that task the discriminator for self-supervised representation learning via additional structural modeling responsibilities.
Factorized Diffusion Architectures for Unsupervised Image Generation and Segmentation
We develop a neural network architecture which, trained in an unsupervised manner as a denoising diffusion model, simultaneously learns to both generate and segment images.
Evaluating Machine Learning Models with NERO: Non-Equivariance Revealed on Orbits
NERO evaluation is consist of a task-agnostic interactive interface and a set of visualizations, called NERO plots, which reveals the equivariance property of the model.
Meta-Learning via Learning with Distributed Memory
We demonstrate that efficient meta-learning can be achieved via end-to-end training of deep neural networks with memory distributed across layers.
Multimodal Contrastive Training for Visual Representation Learning
We first train our model on COCO and evaluate the learned visual representations on various downstream tasks including image classification, object detection, and instance segmentation.
Information-Theoretic Segmentation by Inpainting Error Maximization
We study image segmentation from an information-theoretic perspective, proposing a novel adversarial method that performs unsupervised segmentation by partitioning images into maximally independent sets.
Ranked #1 on
Unsupervised Image Segmentation
on Flowers
Self-Supervised Visual Representation Learning from Hierarchical Grouping
We create a framework for bootstrapping visual representation learning from a primitive visual grouping capability.
Boosting Contrastive Self-Supervised Learning with False Negative Cancellation
While positive pairs can be generated reliably (e. g., as different views of the same image), it is difficult to accurately establish negative pairs, defined as samples from different images regardless of their semantic content or visual features.
Orthogonalized SGD and Nested Architectures for Anytime Neural Networks
We propose a novel variant of SGD customized for training network architectures that support anytime behavior: such networks produce a series of increasingly accurate outputs over time.
Growing Efficient Deep Networks by Structured Continuous Sparsification
We develop an approach to growing deep network architectures over the course of training, driven by a principled combination of accuracy and sparsity objectives.
Pixel Consensus Voting for Panoptic Segmentation
The core of our approach, Pixel Consensus Voting, is a framework for instance segmentation based on the Generalized Hough transform.
Ranked #36 on
Panoptic Segmentation
on COCO test-dev
Winning the Lottery with Continuous Sparsification
Additionally, the recent Lottery Ticket Hypothesis conjectures that, for a typically-sized neural network, it is possible to find small sub-networks which, when trained from scratch on a comparable budget, match the performance of the original dense counterpart.
Domain-independent Dominance of Adaptive Methods
From a simplified analysis of adaptive methods, we derive AvaGrad, a new optimizer which outperforms SGD on vision tasks when its adaptability is properly tuned.
ALERT: Accurate Learning for Energy and Timeliness
An increasing number of software applications incorporate runtime Deep Neural Networks (DNNs) to process sensor data and return inference results to humans.
Multigrid Neural Memory
We introduce a novel approach to endowing neural networks with emergent, long-term, large-scale memory.
Learning Implicitly Recurrent CNNs Through Parameter Sharing
Restricting the number of templates yields a flexible hybridization of traditional CNNs and recurrent networks.
Regularizing Deep Networks by Modeling and Predicting Label Structure
Our technique is applicable when the ground-truth labels themselves exhibit internal structure; we derive a regularizer by learning an autoencoder over the set of annotations.
Sparsely Aggregated Convolutional Networks
We explore a key architectural aspect of deep convolutional neural networks: the pattern of internal skip connections used to aggregate outputs of earlier layers for consumption by deeper layers.
Self-Supervised Relative Depth Learning for Urban Scene Understanding
As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth.
Multigrid Neural Architectures
Most critically, multigrid structure enables networks to learn internal attention and dynamic routing mechanisms, and use them to accomplish tasks on which modern CNNs fail.
FractalNet: Ultra-Deep Neural Networks without Residuals
We introduce a design strategy for neural network macro-architecture based on self-similarity.
Ranked #29 on
Image Classification
on SVHN
Learning Representations for Automatic Colorization
This intermediate output can be used to automatically generate a color image, or further manipulated prior to image formation.
Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding
Spectral embedding provides a framework for solving perceptual organization problems, including image segmentation and figure/ground organization.
Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression
We demonstrate results on both the synthetic images of Sintel and the real images of the classic MIT intrinsic image dataset.
Learning Lightness From Human Judgement on Relative Reflectance
We develop a new approach to inferring lightness, the perceived reflectance of surfaces, from a single image.
Reconstructive Sparse Code Transfer for Contour Detection and Semantic Labeling
We frame the task of predicting a semantic labeling as a sparse reconstruction procedure that applies a target-specific learned transfer function to a generic deep sparse code representation of an image.
Microsoft COCO: Common Objects in Context
We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding.
