Search Results for author:
Found 26 papers, 10 papers with code
DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging
The transformer architecture by Vaswani et al. (2017) is now ubiquitous across application domains, from natural language processing to speech processing and image understanding.
DeepEMD: A Transformer-based Fast Estimation of the Earth Mover's Distance
We propose an attention-based model to compute an accurate approximation of the EMD that can be used as a training loss for generative models.
SequeL: A Continual Learning Library in PyTorch and JAX
Continual Learning is an important and challenging problem in machine learning, where models must adapt to a continuous stream of new data without forgetting previously acquired knowledge.
Efficiently Training Low-Curvature Neural Networks
To achieve this, we minimize a data-independent upper bound on the curvature of a neural network, which decomposes overall curvature in terms of curvatures and slopes of its constituent layers.
HyperMixer: An MLP-based Low Cost Alternative to Transformers
We find that existing architectures such as MLPMixer, which achieves token mixing through a static MLP applied to each feature independently, are too detached from the inductive biases required for natural language understanding.
Uncertainty Reduction for Model Adaptation in Semantic Segmentation
To tackle this problem, we propose a method that reduces the uncertainty of predictions on the target domain data.
DepthInSpace: Exploitation and Fusion of Multiple Video Frames for Structured-Light Depth Estimation
We first propose to use estimated optical flow from ambient information of multiple video frames as a complementary guide for training a single-frame depth estimation network, helping to preserve edges and reduce over-smoothing issues.
Taming GANs with Lookahead-Minmax
Generative Adversarial Networks are notoriously challenging to train.
Rethinking the Role of Gradient-Based Attribution Methods for Model Interpretability
This leads us to hypothesize that the highly structured and explanatory nature of input-gradients may be due to the alignment of this class-conditional model $p_{\theta}(x \mid y)$ with that of the ground truth data distribution $p_{\text{data}} (x \mid y)$.
Real-Time Segmentation Networks should be Latency Aware
We propose a change of objective in the segmentation task, and its associated metric that encapsulates this missing information in the following way: We propose to predict the future output segmentation map that will match the future input frame at the time when the network finishes the processing.
On the Tunability of Optimizers in Deep Learning
There is no consensus yet on the question whether adaptive gradient methods like Adam are easier to use than non-adaptive optimization methods like SGD.
Full-Gradient Representation for Neural Network Visualization
Our experiments reveal that our method explains model behaviour correctly, and more comprehensively than other methods in the literature.
Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching
End-to-end deep-learning networks recently demonstrated extremely good perfor- mance for stereo matching.
Knowledge Transfer with Jacobian Matching
We then rely on this analysis to apply Jacobian matching to transfer learning by establishing equivalence of a recent transfer learning procedure to distillation.
Non-Markovian Globally Consistent Multi-Object Tracking
Many state-of-the-art approaches to multi-object tracking rely on detecting them in each frame independently, grouping detections into short but reliable trajectory segments, and then further grouping them into full trajectories.
Weakly Supervised Learning of Deep Metrics for Stereo Reconstruction
Thirdly, it allows to tune deep metric for a particular stereo system, even if ground truth is not available.
Geometric calibration of Colour and Stereo Surface Imaging System of ESA's Trace Gas Orbiter
There are many geometric calibration methods for "standard" cameras.
Kronecker Recurrent Units
It overcomes the ill-conditioning of the recurrent matrix by enforcing soft unitary constraints on the factors.
Semi-supervised learning of deep metrics for stereo reconstruction
The main contribution of our work is a new semi-supervised method for learning deep metrics from unlabeled stereo images, given coarse information about the scenes and the optical system.
Globally Consistent Multi-People Tracking using Motion Patterns
Many state-of-the-art approaches to people tracking rely on detecting them in each frame independently, grouping detections into short but reliable trajectory segments, and then further grouping them into full trajectories.
Large Scale Hard Sample Mining With Monte Carlo Tree Search
We investigate an efficient strategy to collect false positives from very large training sets in the context of object detection.
Scalable Metric Learning via Weighted Approximate Rank Component Analysis
We are interested in the large-scale learning of Mahalanobis distances, with a particular focus on person re-identification.
Ranked #110 on
Person Re-Identification
on Market-1501
(Rank-1 metric)
Probability Occupancy Maps for Occluded Depth Images
We propose a novel approach to computing the probabilities of presence of multiple and potentially occluding objects in a scene from a single depth map.
Fast Object Detection with Entropy-Driven Evaluation
Cascade-style approaches to implementing ensemble classifiers can deliver significant speed-ups at test time.
Boosting with Maximum Adaptive Sampling
Some applications, in particular in computer vision, may involve up to millions of training examples and features.
Joint Cascade Optimization Using A Product Of Boosted Classifiers
The standard strategy for efficient object detection consists of building a cascade composed of several binary classifiers.
