Search Results for author:
Found 30 papers, 16 papers with code
Adaptive Cross Batch Normalization for Metric Learning
In particular, it is necessary to circumvent the representational drift between the accumulated embeddings and the feature embeddings at the current training iteration as the learnable parameters are being updated.
Semi-Supervised Semantic Segmentation under Label Noise via Diverse Learning Groups
Each learning group consists of a teacher network, a student network and a novel filter module.
Understanding and Improving the Role of Projection Head in Self-Supervised Learning
Most current contrastive learning approaches append a parametrized projection head to the end of some backbone network to optimize the InfoNCE objective and then discard the learned projection head after training.
Retrieval Augmented Classification for Long-Tail Visual Recognition
We introduce Retrieval Augmented Classification (RAC), a generic approach to augmenting standard image classification pipelines with an explicit retrieval module.
Ranked #4 on
Long-tail Learning
on iNaturalist 2018
Provable Defense Against Clustering Attacks on 3D Point Clouds
Lately, the literature on adversarial robustness spans from images to other domains such as point clouds.
Few-shot Weakly-Supervised Object Detection via Directional Statistics
When the novel objects are localized, we utilize them to learn a linear appearance model to detect novel classes in new images.
RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs
In this work, we introduce a Resource Aware Neuron Pruning (RANP) algorithm that prunes 3D CNNs at initialization to high sparsity levels.
A Chaos Theory Approach to Understand Neural Network Optimization
Then, we empirically show that for a large range of learning rates, SGD traverses the loss landscape across regions with largest eigenvalue of the Hessian similar to the inverse of the learning rate.
Refining Semantic Segmentation with Superpixel by Transparent Initialization and Sparse Encoder
We achieve it with fully-connected layers with Transparent Initialization (TI) and efficient logit consistency using a sparse encoder.
RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs
Specifically, the core idea is to obtain an importance score for each neuron based on their sensitivity to the loss function.
Calibration of Neural Networks using Splines
From this, by approximating the empirical cumulative distribution using a differentiable function via splines, we obtain a recalibration function, which maps the network outputs to actual (calibrated) class assignment probabilities.
Post-hoc Calibration of Neural Networks by g-Layers
Calibration of neural networks is a critical aspect to consider when incorporating machine learning models in real-world decision-making systems where the confidence of decisions are equally important as the decisions themselves.
Bidirectionally Self-Normalizing Neural Networks
The problem of vanishing and exploding gradients has been a long-standing obstacle that hinders the effective training of neural networks.
Improved Gradient based Adversarial Attacks for Quantized Networks
In this work, we systematically study the robustness of quantized networks against gradient based adversarial attacks and demonstrate that these quantized models suffer from gradient vanishing issues and show a fake sense of robustness.
Understanding the Effects of Data Parallelism and Sparsity on Neural Network Training
As a result, we find across various workloads of data set, network model, and optimization algorithm that there exists a general scaling trend between batch size and number of training steps to convergence for the effect of data parallelism, and further, difficulty of training under sparsity.
Pairwise Similarity Knowledge Transfer for Weakly Supervised Object Localization
Weakly Supervised Object Localization (WSOL) methods only require image level labels as opposed to expensive bounding box annotations required by fully supervised algorithms.
Fast and Differentiable Message Passing on Pairwise Markov Random Fields
In addition to differentiability, the two main aspects that enable learning these model parameters are the forward and backward propagation time of the MRF optimization algorithm and its inference capabilities.
Mirror Descent View for Neural Network Quantization
Quantizing large Neural Networks (NN) while maintaining the performance is highly desirable for resource-limited devices due to reduced memory and time complexity.
A Signal Propagation Perspective for Pruning Neural Networks at Initialization
Alternatively, a recent approach shows that pruning can be done at initialization prior to training, based on a saliency criterion called connection sensitivity.
Learning to Adapt for Stereo
Real world applications of stereo depth estimation require models that are robust to dynamic variations in the environment.
On Tiny Episodic Memories in Continual Learning
But for a successful knowledge transfer, the learner needs to remember how to perform previous tasks.
Ranked #7 on
Class Incremental Learning
on cifar100
Proximal Mean-field for Neural Network Quantization
Compressing large Neural Networks (NN) by quantizing the parameters, while maintaining the performance is highly desirable due to reduced memory and time complexity.
Generalized Range Moves
We consider move-making algorithms for energy minimization of multi-label Markov Random Fields (MRFs).
SNIP: Single-shot Network Pruning based on Connection Sensitivity
To achieve this, we introduce a saliency criterion based on connection sensitivity that identifies structurally important connections in the network for the given task.
Efficient Relaxations for Dense CRFs with Sparse Higher Order Potentials
The presented algorithms can be applied to any labelling problem using a dense CRF with sparse higher-order potentials.
DGPose: Deep Generative Models for Human Body Analysis
However, the latent space learned by such approaches is typically not interpretable, resulting in less flexibility.
Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
We observe that, in addition to forgetting, a known issue while preserving knowledge, IL also suffers from a problem we call intransigence, inability of a model to update its knowledge.
Memory Efficient Max Flow for Multi-label Submodular MRFs
Multi-label submodular Markov Random Fields (MRFs) have been shown to be solvable using max-flow based on an encoding of the labels proposed by Ishikawa, in which each variable $X_i$ is represented by $\ell$ nodes (where $\ell$ is the number of labels) arranged in a column.
Efficient Linear Programming for Dense CRFs
To this end, we develop a proximal minimization framework, where the dual of each proximal problem is optimized via block coordinate descent.
Iteratively Reweighted Graph Cut for Multi-label MRFs with Non-convex Priors
While widely acknowledged as highly effective in computer vision, multi-label MRFs with non-convex priors are difficult to optimize.
